ProjectVRM

Page 2 of 43

Toward a Personal AI Roadmap for VRM

June 18, 2025 / / 4 Comments

On the ProjectVRM list, John Wunderlich shared a find that makes clear how advanced and widespread  AI-based shopping recommendation has gone so far (and not just with ChatGPT and Amazon). Here it is: Envisioning Recommendations on an LLM-Based Agent Platform: Can LLM-based agents take recommender systems to the next level?

It’s by Jizhi Zhang, Keqin Bao, Wenjie Wang, Yang Zhang, Wentao Shi, Wanhong Xu, Fuli Feng, and Tat-Seng Chua* and is published in the Artificial Intelligence and Machine Learning section of Research and Advances in Communications of the ACM. So it’s serious stuff.

Here’s one graphic from the piece, with its caption:

Illustration of the Rec4Agentverse. The left side depicts three roles in the RecAgentverse: the user, the Agent Recommender, and Item Agents, along with their interconnected relationships. In contrast to traditional recommender systems, the Rec4Agentverse has more intimate relationships among the three roles. For instance, there are multi-round interactions between 1) users and Item Agents and 2) the Agent Recommender and Item Agents. The right side demonstrates how the Agent Recommender can collaborate with Item Agents to affect the information flow of users and offer personalized information services.

With VRM, however, we need our own personal AI agents, and useful data that’s not limited to what’s gathered by surveillance (which we can assume is most if not all of the Information layer).
So I started a conversation with ChatGPT. I’ll divide it into sections:
  1. Who wrote the CACM piece
  2. The state of recommendation science
  3. Who is working on personal AI
  4. How one can get started
  5. Forms of personal data to manage

There’s a lot here. The meat of it, for ProjectVRM purposes, starts in section 3. (The first two are more about what we’re up against.) Please read the whole thing and help us think through where to go with the challenge facing us. As we see in section 3, we do have some stuff on our side.

1. Who wrote the CACM piece
Me:
Can you tell me more about the authors here: https://cacm.acm.org/research/envisioning-recommendations-on-an-llm-based-agent-platform/?
ChatGPT:

🧑‍💼 Jizhi Zhang

Affiliation: University of Science and Technology of China (USTC), Data Science Lab (inferred from USTC page) cacm.acm.org+14data-science.ustc.edu.cn+14x.com+14.
Research Interests: Recommendation systems, LLM-based agent platforms, and interactive intelligent systems—his lead authorship and continued work on Prospect Personalized Recommendation on LLM-Based Agent Platform (arXiv Feb 2024) reinforce this arxiv.org.

🧑‍🔬 Keqin Bao, Wenjie Wang, Yang Zhang, Wentao Shi, Fuli Feng, Tat‑Seng Chua

Affiliations: While CACM doesn’t list this, Jizhi Zhang and Fuli Feng are part of USTC’s Data Science Lab; Tat‑Seng Chua is a distinguished researcher from the National University of Singapore known for multimedia and information retrieval.
Expertise: A mix of recommender system design, LLM-agent evaluation, multimedia analysis, and human-AI interaction—reflecting a blend of USTC’s strengths and CACM relevance data-science.ustc.edu.cn+8cacm.acm.org+8data-science.ustc.edu.cn+8linkedin.com+4arxiv.org+4researchgate.net+4.

🧑‍🎓 Wanhong Xu

Affiliation: USTC Data Science Lab (USTC LDS), contributor to the same article .
Role: Emerging researcher whose latest publication is this Rec4Agentverse article, indicating an early-career focus in LLM-based recommender systems linkedin.com+8data-science.ustc.edu.cn+8linkedin.com+8.

🧠 Broader Context & Contributions

The group operates at the intersection of Large Language Models, agent-oriented systems, and recommender systems, pioneering a Rec4Agentverse paradigm that treats LLM-powered agents as “recommendable” items collaborating with one another—an evolution of traditional recommendation frameworkscacm.acm.org+5cacm.acm.org+5cacm.acm.org+5.
Their work continues earlier research (e.g., Prospect Personalized Recommendation… in Feb 2024), solidifying their ongoing commitment to expanding intelligent, conversational recommendation platforms arxiv.org.

🧭 Why This Matters

Academic Thought Leadership: Jizhi Zhang and colleagues are pushing forward thinking about how recommendations can evolve when agents—not passive items—are central.
Institutional Backing: All deeply connected to USTC’s Data Science Lab, underscoring strong Chinese academic investment in AI-driven recommender innovation.
Collaborative Reach: Including scholars like Tat‑Seng Chua broadens the research to include international perspectives in multimedia and retrieval systems.

In summary: This team is a multidisciplinary cohort—centered at USTC with international collaboration—who are pioneering the idea that LLM agents can become interactive, dynamic items in recommender systems. Their work positions them at the forefront of intelligent agent systems and could reshape how platforms personalize experiences in the future.

If you’re curious about any individual’s past publications, citation impact, or related work (e.g., on Agent4Rec), I’d be happy to dive deeper!

 

3. The state of recommendation science

Me:

How large is the emerging science, within the AI field, of recommendations?

ChatGPT:

The science of recommendations, particularly within the AI field, is not just emerging—it’s a massive, rapidly evolving subfield that is both academically rich and commercially dominant. That said, it’s also entering a new phase, driven by the rise of large language models (LLMs), interactive agents, and multimodal platforms.

📚 Academic Scope

1. Established Field: Recommender Systems

Recommender systems (RecSys) are a well-developed domain within AI and machine learning, with roots in the 1990s.
Annual conferences like:
ACM RecSys (since 2007)
SIGIR, KDD, WSDM, and NeurIPS regularly feature recommendation research.
Thousands of papers annually on topics like:
Collaborative filtering
Matrix/tensor factorization
Deep learning for recommendation
Fairness, transparency, and explainability in RecSys
Reinforcement learning and bandit algorithms for personalization

🔎 As of 2024, over 60,000 papers in academic databases (e.g., Google Scholar) are tagged or indexed under “recommender systems”.

📈 Current Trends & Expanding Frontiers

2. LLMs + Recommendation = New Subfield

A major shift is underway: integrating Large Language Models (LLMs) into recommendation systems.
These go beyond “you may also like” to:
Use natural language context and dialogue
Generate explanations, not just rankings
Support conversational recommendation
Coordinate agent ecosystems, e.g., multi-agent reasoning environments

Example paradigms:

RecMind – reasoning-aware recommendation agents
Rec4Agentverse – treating agents as recommendable entities
ChatRecs – integrating LLMs into live user conversations

3. Multimodal & Multitask Integration

Systems increasingly blend text, image, video, behavior, and user feedback.
LLMs allow richer personalization using complex user intent derived from unstructured data.

4. Industry Investment

FAANG companies (especially YouTube, Netflix, Amazon, TikTok, and Spotify) base their core user experience on AI-driven recommendation.
Billions of dollars are spent optimizing:
Ranking quality
Engagement prediction
Real-time inference
Federated and privacy-preserving personalization

🧭 Estimate of Scope

Area

Estimate (2024–25)

📄 Academic papers (RecSys + AI)

60,000+ overall; thousands per year

📚 Top conferences with recommender tracks

20+ (ACM RecSys, SIGIR, KDD, NeurIPS, etc.)

👩‍💼 Active researchers

Tens of thousands globally

🧠 Emerging subfields

LLM-based Rec, conversational Rec, agent-based Rec, explainable Rec

💰 Industry scale

$10B+ annually invested in personalization tech

🧠 In Summary

The science of recommendation is:

Not new, but rapidly evolving
Core to AI applications, especially with LLMs and agents
One of the most commercially and socially impactful domains in modern AI
Growing into new subfields (e.g. Rec4Agentverse, LLM Rec, multi-agent Rec)

Let me know if you’d like a visual map of how the recommendation science ecosystem is structured—or who the top authors and institutions are in this space

3. Who is working on personal AI
Me:
And who, if anyone, is working to provide customers with their own personal AI tools: ones that work for them, to empower their own agency in the marketplace? By which I mean truly personal AI, and not the kind personalized by some external LLM (or similar) system.
ChatGPT:

That’s an essential and forward-looking question—especially as most “AI for you” today really means “AI about you, for someone else.”

While Big Tech firms dominate personalized AI, a growing ecosystem is focused on truly personal AI—that is, AI you own, that works for you (not advertisers or platforms), and that enhances your agency in the marketplace and your life.

Here are the most notable people, projects, and initiatives advancing truly personal AI today:

🧠 1. Kwaai and pAI-OS (South Africa / Global)

Kwaai is building an open-source, user-sovereign personal AI OS called pAI-OS.
Designed to run locally or at user discretion, with full data ownership, modular agent systems, and plugin capability.
Aligns with IEEE P7012 (“MyTerms”) privacy standards (see below).
Actively exploring intentcasting, customer signaling, and VRM (Vendor Relationship Management).
Site: https://kwaai.ai

🛠️ 2. Indie AI and Personal Agent projects

Several smaller open-source initiatives are trying to build personal agent toolkits that you can host and configure:

Examples:

AutoGen Studio (Microsoft) – allows building agent workflows, some of which can be user-defined. But it’s not yet fully personal or private.
Langroid – open-source framework for local agent-based LLM systems. Designed for extensibility, can be made personal with effort.
OpenDevin, Superagent, Auto-GPT – can be self-hosted, though most are still tool-centric rather than user-centric.
Personal.ai – A commercial startup that says it is personal, but uses centralized storage and fine-tuning, so actual user control is limited.

🔍 Reality check: Most of these still rely on external LLMs (like OpenAI or Anthropic), even if they claim to be “your AI”.

🌐 3. Solid Project (by Tim Berners-Lee)

While not AI per se, Solid is a decentralized identity and data storage architecture that allows individuals to store their own data in personal data pods.
AI tools can be layered on top to access only the data you choose to share.
Foundation for personal AI assistants that can work with your data, not on others’ clouds.
https://solidproject.org

📜 4. IEEE P7012 – MyTerms

A standard being developed to flip the notice-and-consent regime—so individuals, not companies, dictate the terms of data use.
Backed by Customer Commons and designed to support intentcasting and personal marketplace signaling.
This enables a personal AI to serve as your agent, enforcing your terms and engaging the marketplace on your behalf.

🧩 5. Project VRM (Vendor Relationship Management)

Initiated by Doc Searls to empower customers with tools to manage vendors, not just the reverse.
Envisions personal tools (including AI) to:
Signal intent
Manage service contracts
Retain records of offers, purchases, warranties
Avoid manipulation, surveillance, and lock-in

Project VRM is not a software project per se, but a framework guiding developers to build personal tools that support individual autonomy.

🔒 6. Open-source LLM stacks for local use

Several local LLM projects can be combined with personal data layers to build truly personal AI:

LM Studio – runs local models on desktop
PrivateGPT – local inference + local documents
Ollama – macOS-native interface for fast-running models like LLaMA, Mistral
LangChain / LlamaIndex – frameworks for building RAG systems with local documents

These aren’t personal AI systems yet—but they are key ingredients.

🧭 Summary

Name / Project

What They Do

Status

Kwaai / pAI-OS

Open, personal AI OS and agent platform

Early but active

Solid

Personal data control layer

Stable; in use

IEEE P7012

Standards for user-enforced data terms

In development

Project VRM

Framework for tools that empower buyers

Thought leadership; toolkits emerging

Local AI frameworks

Tech foundations for personal AI

Available, DIY-friendly

🚧 The Gap

Despite this promising landscape, no major platform today delivers a fully integrated, easy-to-use personal AI that you own, configure, and direct—yet. But:

A personal AI revolution is underway, led by privacy advocates, open-source communities, and a few visionary developers—not Big Tech.

Would you like help putting together a DIY stack for your own personal AI toolkit based on this landscape?

Me:
Can you name some of the people in the personal AI revolution, and tell me what that DIY stack would contain?
ChatGPT:

Absolutely. Here’s a breakdown of key people involved in the personal AI movement, followed by a practical DIY stack you can start building today.

👤 People Leading or Advancing the Personal AI Revolution

These individuals aren’t all working on the same projects, but they’re aligned in trying to build AI that’s owned, run, and controlled by the individual—not centralized platforms.

🧑‍🔬 Tim Berners-Lee

Project: Solid (stewarded by ODI, commercially implemented by companies including TBLs Inrupt)
Focus: Decentralized web and personal data ownership via data pods
Impact: Infrastructure for privacy-respecting personal AI agents
https://solidproject.org

👤 Doc Searls

Project: Project VRM, Customer Commons, IEEE P7012
Focus: Customer empowerment, intentcasting, reversing surveillance capitalism
Impact: Philosophy and standards for customer-directed personal AI
https://projectvrm.org

🧠 Tawanda Kembo & Kwaai team

Project: pAI-OS (personal AI operating system)
Focus: Agent-centric open-source operating system for personal AI
Impact: One of the few efforts aiming to create a complete personal AI stack
https://kwaai.ai

🧑‍💻 Simon Willison

Project: Datasette, open tools for data management
Focus: Personal data control, lightweight databases, LLM + local tooling
Impact: Key figure in the open data + local AI tooling space
https://simonwillison.net

🤖 Brian Roemmele

Project: Multiplex (personal voice AI)
Focus: Voice-first personal assistants you run locally
Impact: Vocal advocate for true personal AI, often referencing “software you own”

🛠️ A DIY Personal AI Stack (2025 Edition)

This stack assumes local-first, modular, privacy-respecting tools. You can mix and match based on your needs.

🧩 Core Components

Layer

Tools / Projects

Notes

1. OS Layer

Linux, pAI-OS (in dev)

Linux gives flexibility; pAI-OS aims to be a full personal AI OS

2. Local LLM Inference

Ollama, LM Studio, PrivateGPT, LocalAI

Run models like LLaMA 3, Mistral, Phi-3 entirely offline

3. Vector Database

Chroma, Weaviate, Milvus, or SQLite with FTS5

Store and retrieve embedded text data

4. Personal Indexing

LlamaIndex, LangChain, AutoGen, GPTPilot

Feed personal documents and data to your LLM

5. Personal Data Storage

Solid POD, Datasette, Obsidian

Your life’s data, structured and queryable

6. Personal Agent Framework

Superagent, CrewAI, Langroid, AutoGen

Design agents that act on your behalf, modular and scriptable

7. Front-end Interface

Gradio, Streamlit, Tauri app, Electron

Local GUI/UX to interact with your agent

8. Voice Interface (optional)

OpenVoice, Vosk, Whisper.cpp, Coqui TTS

Build voice-in/voice-out agent on your machine

🧠 Optional Add-ons

Offline search: Chat over your files, PDFs, photos, and emails with LlamaIndex + PrivateGPT
Calendar/notes: Sync with Obsidian or local markdown-based knowledge base
Browser agent: Auto-control browser via Puppeteer/Playwright for marketplace navigation

🧭 What’s Still Missing?

True personal OS integration (like what pAI-OS is trying to do)
Seamless data portability and contract enforcement (IEEE P7012 is working on it)
Trusted personal AI app ecosystem (some apps, like Beeper or Obsidian, are getting close)

Would you like a tailored recommendation for building a personal AI stack based on your technical skill level or use cases (e.g., journaling, research, negotiation, shopping, data querying)?

4. How can I get started?
Me:
Yes. My technical skill level is modest at best. I can write HTML and do very basic stuff in the command line. I have an extra laptop I can devote to solo work, and Ethernet to a 2.1GB/s symmetrical fiber connection to the Internet with no data limits.
ChatGPT:

Great — with your setup (modest technical skills, spare laptop, blazing-fast fiber), you’re in an excellent position to begin building a practical personal AI system without diving too deep into complex dev work. Here’s a recommended stack tailored to your current skills and goals:

🧰 YOUR PERSONAL AI STARTER STACK (2025)

🔧 1. Platform Base

Use a Linux distribution designed for ease of use and AI tinkering:

Recommended: Pop!_OS or Ubuntu 24.04
Easy GUI, good hardware compatibility, lots of online support
Optional: Use your laptop in “air-gapped” mode for privacy and full local control

🤖 2. Run a Local LLM with LM Studio

LM Studio (macOS/Windows/Linux) lets you run LLaMA 3, Mistral, Phi-3, and others without coding.
Built-in UI — chat with models locally, no internet required after download.
You can download 7B or 13B models based on your hardware.
Best for: private journaling, summarizing files, answering questions.

✅ Why it’s ideal for you:

GUI-based
Just click and download models
No API keys or command-line needed once installed

📁 3. Chat with Your Files (PrivateGPT / LlamaIndex)

PrivateGPT or GPTPilot can let you ask questions across PDFs, emails, and notes stored on your machine.
Start simple: drop files into a folder, let the AI index them.
Optionally install via Docker (one command), or use their prebuilt apps.

✅ Use case:

“Summarize this research PDF”
“What did I write about project X last month?”
“Find the email where someone mentioned a refund”

📚 4. Knowledge Base + Journaling with Obsidian

Obsidian = Markdown-based knowledge base.
Everything you write stays local.
You can point LM Studio to your notes to query your own memory.

✅ Easy way to:

Keep private journals
Index your life
Ask your AI things like “What are my goals for June?”

🗂️ 5. Personal Data Management with Datasette

Datasette by Simon Willison lets you browse and query your own data with simple SQL and CSV files.
Feeds AI with structured personal info (purchases, inventory, plans, etc.)
You can install it with a single terminal command:
bash
pip install datasette datasette serve your-data.db
datasette serve your-data.db

✅ Combine with LM Studio to get responses like:

“What subscriptions do I need to cancel?”
“When did I last back up my photos?”

🌐 6. Optional: Browser Helper Agent (Local, Simple)

Use AutoBrowser or a simpler Puppeteer script to automate browsing tasks (like checking prices, news, account activity).
Start with prebuilt scripts. No coding needed if you copy/paste working examples.

🔒 7. Privacy Boosters

Run Tailscale or WireGuard to access your AI remotely if needed.
Use LocalAI or Ollama if you later want to run everything without GUI (more advanced).

🧭 Putting It All Together

Task

Tool

Chat privately with an AI

LM Studio

Summarize your own notes or PDFs

PrivateGPT or GPTPilot

Store and reflect on your life data

Obsidian, Datasette

Manage subscriptions and tasks

Datasette + Chat

Ask about your files or history

LlamaIndex or GPT over Obsidian notes

Use voice later (optional)

Whisper.cpp, OpenVoice (easy tools)

🪜 Next Steps (in plain order)

Install Pop!_OS or Ubuntu on your spare laptop
Install LM Studio and download a 7B model like Mistral or LLaMA 3
Start using it to answer personal questions and summarize documents
Add Obsidian to start journaling and reflecting
Try PrivateGPT or Datasette to search your past or track your life

Would you like a checklist or an install script to get started with this stack? I can also help you set up a file structure to begin tracking and querying your own data.

5. Forms of personal data to manage
Me:
The personal data I need to manage are health records (from 20-plus providers), financial records (fewer than health), travel records (including the kind kept by apps that watch my movements), subscriptions and other recurring payments, shows I have watched and on what channels or services (data gathered by my Samsung and Roku TVs and presumably shared with others but to which I don’t yet have access), continuing work and work history with various clients and employers, contacts, archival and current calendars, real estate, personal items bought or acquired from various sources and where they are kept or stored, and business dealings. What would be the file structure for all that, and how would I manage it? Note that I am not talking about shopping yet; that’s a separate concern.
ChatGPT:

Thanks for the detailed breakdown — you’re describing the foundation of a true personal data architecture: structured, queryable, and under your control. Let’s build you a file structure and management strategy that matches your needs without overcomplicating the tech.

📁 Recommended Top-Level Folder Structure

This folder structure is designed to be future-proof, machine-readable, and human-usable. Use plain folders, CSV/JSON/Markdown files, and optional SQLite databases to store structured data. You can later layer tools (like LLMs or Datasette) on top.

markdown
/PersonalAI_Data
│
├── Health/
│ ├── Providers/
│ ├── Visits/
│ ├── Prescriptions/
│ ├── Labs_Imaging/
│ └── Insurance_Claims/
│
├── Finance/
│ ├── Bank_Accounts/
│ ├── Credit_Cards/
│ ├── Investments/
│ └── Taxes/
│
├── Travel/
│ ├── Trips/
│ ├── Locations_History/
│ └── Maps_GPX_KML/
│
├── Subscriptions/
│ ├── Streaming/
│ ├── News_Publications/
│ ├── Software_Tools/
│ └── Utilities_Bills/
│
├── Media_Viewed/
│ ├── TV_Shows/
│ ├── Movies/
│ ├── Channels_Services/
│ └── Watch_History.csv
│
├── Work/
│ ├── Employers/
│ ├── Clients/
│ ├── Projects/
│ └── Timesheets_Invoices/
│
├── Contacts/
│ └── contacts.csv
│
├── Calendar/
│ ├── Archive_ICS/
│ ├── Current_ICS/
│ └── Events_Tags.csv
│
├── Real_Estate/
│ ├── Properties_Owned/
│ ├── Rentals/
│ └── Maintenance_Records/
│
├── Personal_Items/
│ ├── Furniture/
│ ├── Electronics/
│ ├── Art_Collectibles/
│ └── Inventory.csv
│
└── Business/
├── Deals/
├── Agreements/
├── Partners/
└── Notes/

🧠 Strategy for Managing It All

1. Use Consistent File Types

Data Type File Format
Structured entries .csv, .json, .sqlite
Notes or logs .md (markdown)
Documents .pdf, .docx, .txt
Images/attachments store in attachments/ subfolder per topic

2. Naming Conventions (Machine + Human Friendly)

Use ISO-like formats to make things sortable and parseable:

yaml
2024-06-16_labresults_providerX.csv
2023_Q4_taxes_federal.pdf
clientA_2022-11_contract.pdf

3. Data Capture Tools

You don’t need to build it all manually:

  • Use Obsidian for ongoing notes (e.g. travel journal, work logs)

  • Use Paperless-ngx (optional) to OCR and tag your scanned PDFs (health, finance)

  • Use GPS History Export from Google and Apple for travel/locations

  • Use email filters or Zapier to auto-download bills, statements, confirmations

4. Querying and Reviewing

Add one or more of these later:

  • Datasette → browse and search CSVs/SQLite locally

  • LM Studio + PrivateGPT → ask, “When did I last visit Dr. Chen?” or “What devices are in storage?”

  • LlamaIndex → index your file tree and let AI search/summarize it

✅ Summary of Benefits

Goal This Setup Delivers
Total local control You decide access, storage, retention
Future AI-readiness Structured enough for agents to use
Easy to back up Plain files, portable databases
Modular growth Start simple, layer in AI when ready

Would you like me to generate a starter template with folder structure and some CSV/Markdown file formats filled in with mock data for each domain? That way you can load it directly into your system and start customizing.

Me again:

That’s it for now.

What should my next request be, or what other direction would you like me (or us) to take this?
Or, what are the learnings we have so far in this field that barely exists?
Oh, and excuse whatever inaccuracies ChatGPT may have floated above. Or give me fixes.
Thanks.
*The links are mine and based on searches for those names. I might have some of them wrong, however, since searches for those names bring up many scholars with the same names. And, while each name had a link, they all went to an author archive page that was absent (with one exception) of other contributions to the publication.

Four Roads to The Intention Economy

May 16, 2025 / / 5 Comments

Thirteen years after The Intention Economy was published by Harvard Business Review Press, there are now four clear paths toward making it come true.

  1. IEEE P7012, aka MyTerms. This will make individuals first parties in their agreements with companies, completely flipping the status quo that has been with us since industry won the Industrial Revolution and manifests today in those insincere and annoying cookie notices that interrupt your experience every time you visit a new website or open a new app. MyTerms makes each of us first parties in agreements with sites and services, and in full charge of personal privacy online.
  2. The First Person Project, or FPP  (website pending). With help on the buy side from Customer Commons and on the sell side by Ayra, we can finally replace “show your ID” with verifiable credentials presented on an as-needed basis by independent and self-sovereign individuals operating inside their own webs of trust.
  3. Visa Intelligent Commerce, which will make intentcasting happen in a big way. It will also elevate the roles of Inrupt and the open-source  Solid Project.
  4. Personal AI. This is AI that is as much yours as your shoes, your bike, and your PC. Personal, not personalized.

To explain how these will work together, start here:

Not long after The Intention Economy came out in May, 2012, Robert Thomson, Managing Editor of The Wall Street Journal, wanted the book’s opening chapter to serve as the cover essay for the Marketplace section of an upcoming issue. Harvard Business Review Press didn’t like that idea, so I wrote an original piece based on one idea in the book: that shoppers will soon be able to tell the market what they’re looking for, in safe, secure and anonymous ways—a kind of advertising in reverse that the book called “personal RFPs” and has since come to be called “intentcasting.” This became The Customer as a God: The image above was the whole cover of the Marketplace section on Monday,  July 23, 2012. The essay opened with these prophetic words: “It’s a Saturday morning in 2022…”

It is now a Friday morning in 2025, and that godly future for customers is still not here. Yes, we have more market power than in 2012, but we are digital serfs whose powers are limited to those granted by  Amazon, Apple, Facebook, Google, Microsoft, and other feudal overlords. This system is a free market only to the degree that you can choose your captor.  This has led to—

The IONBA (Internet Of Notning But Accounts) is based on a premise: that the best customers are captive ones. In this relic of the industrial age, customers are captive to every entity that requires logins and passwords. Customers also have no ways of their own to globally control what data is collected about them, or how. Or to limit how that data is used.  This is why our digital lives are infected by privacy-killing data-collection viruses living inside our computers, phones, TVs, and cars.

If you didn’t know about those last two, dig:

  • Consumer Reports says “All smart TVs—from Samsung, LG, you name it—collect personal data.” They also come with lame “privacy” controls, typically buried deep in a settings menu. (Good luck exhuming them. The ones in our TCL and Samsung TVs have all but disappeared.)
  • Mozilla calls new cars “the Worst Product Category We Have Ever Reviewed for Privacy.” There is also nothing you can do to stop your car from reporting on everything your car does—and everything you do, including sexual ativity—to the carmaker, insurance companies, law enforcement, and who knows who else. This data goes out through your car’s cell phone, misleadingly called a telematics control unit. The antenna is hidden in the shark fin on your car’s roof or in an outside mirror.

Businesses are also starting to lose faith in surveillance, for at least eight reasons:

  1. People hate it.
  2. They also fight it. By 2015 ad blocking and tracking protection were the biggest boycott in world history.
  3. It tarnishes brands.
  4. Ad fraud is a gigantic problem, and built into the system.
  5. It commits Chrysoogocide (killing golden geese, most notably publishers). Bonus link.
  6. Regulatory pressure against it is getting bigger all the time.
  7. Advertisers are finally remembering that brands are made by ads aimed at populations, while personalized ads are just digital junk mail.
  8. Customers are using AI tools for guidance toward a final purchase, bypassing marketing schemes to bias purchasing decisions along the way. For more on that, see Tom Fishburne’s cartoon, and Bain’s report about it.

So our four roads to The Intention Economy start with the final failings of the systems built to prevent it. Now let’s look at those roads.

1—IEEE P7012 “MyTerms”

MyTerms, the most important standard in development today, will be a keystone service of Customer Commons, the nonprofit spinoff of ProjectVRM. It will do for contract what Creative Commons did for copyright: give individuals a new form of control. With MyTerms, agreements between customers and companies will be far more genuine mutual, and open to new forms of innovation not based on the kind of corporate control that typifies the IONBA. For example, it can open Visa Intelligent Commerce to conversations and relationships that go far past transaction. Take for example Market intelligence that flows both ways. While this has been thinkable for a decade or more (that last link is from 2016), it’s far more do-able when customers and companies have real relationships based on equal power and mutual interests. These are best framed up on agreements that start on the customer’s side, and give customers scale across all the companies with which they have genuine relationships.

2—First Person Project (FPP)

To me, FPP begins with the vision “Big Davy” Sallis came up with while he was working for VISA Europe in 2012, and read the The Intention Economy. At the time, he wanted Visa to make VRM a real category, but assumed that would take too long. So he decided to create a VRM startup called Qredo. Joyce and I consulted Qredo until  Davy died (far too young) in 2015. Qredo went into a different business, but a draft I created for Qredo’s original website survives, and it outlines much of what the  FPP will make possible. That effort is led by Drummond Reed, another friend and collaborator of Davy’s and a participant in ProjectVRM from the start. Drummond says the FPP is inspired by Why We Need First Person Technologies on the Net, a post published here in 2014. That post begins,

We need first person technologies for the same reason we need first person voices: because there are some things only a person can say and do.

Only a person can use the pronouns  “I,” “me,” “my” and “mine.” Likewise, only a person can use tools such as screwdrivers, eyeglasses and pencils. Those things are all first person technologies. They were invented for individual persons to use.

We use first person technologies the same unique ways we use our voices.

Among other things, the First Person Project will fix how identity works on the Internet. With FPI—First Person Identity—interactions with relying parties (the ones wanting “your ID”) don’t need your drivers license, passport, birth certificate, credit card, or account information. You just give them what’s required, on an as-needed basis, in the form of verifiable credentials. The credentials you provide can verify that you are a citizen of a country, licensed to drive, have a ticket to a game, or whatever. In other words, they do what Kim Cameron outlined in his Laws of Identity: disclose minimum information for constrained uses (Law 2) to justifiable parties (Law 3) under your control and consent (Law 1). The credential you present is called a DID: a Decentralized Identifier. No account is required.

Trust in FPI also expands from individual to community. Here is how Phil Windley explains it in Establishing First Person Digital Trust:

When Alice and Bob met at IIW, they didn’t rely on a platform to create their connection. They didn’t upload keys to a server or wait for some central authority to vouch for them. They exchanged DIDs, authenticated each other directly, and established a secure, private communication channel.

That moment wasn’t just a technical handshake—it was a statement of first-person identity. Alice told Bob, “This is who I am, on my terms.” Bob responded in kind. And when they each issued a verifiable relationship credential, they gave that relationship form: a mutual, portable, cryptographically signed artifact of trust. This is the essence of first-person identity—not something granted by an institution, but something expressed and constructed in the context of relationships. It’s identity as narrative, not authority; as connection, not classification.

And because these credentials are issued peer-to-peer, scoped to real interactions, and managed by personal agents, they resist commodification and exploitation. They are not profile pages or social graphs owned by a company to be monetized. They are artifacts of human connection, held and controlled by the people who made them. In this world, Alice and Bob aren’t just users—they’re participants.

This also expands outward into community, and webs of trust. You get personal agency plus community agency.

The FPP covers a lot more ground than identity alone, but that’s where it starts. Also, Customer Commons is a funding source for the FPP, and I’m involved there as well.

3—Visa Intelligent Commerce

The press release is Find and Buy with AI: Visa Unveils New Era of Commerce. Less blah is Enabling AI agents to buy securely and seamlessly. Here’s the opening copy.

Imagine a future where an AI agent can shop and buy for you. AI commerce — commerce powered by an AI agent — is going to transform the way consumers around the world shop.

Introducing Visa Intelligent Commerce, an initiative that will empower AI agents to deliver personalized and secure shopping experiences for consumers – at scale.

From browsing and selection to purchase and post-purchase management, this program will equip AI agents to seamlessly manage key phases of the shopping process.

Visa CEO Ryan McInerney says a lot more in a 1:22 talk at Visa Product Drop 2025. The most relevant part starts about 26 minutes in, with a demo starting at about 31:30. Please watch it. Much of what you see there owes to Inrupt and Solid, which Sir Tim Berners-Lee says were inspired by The Intention Economy. For more about where Inrupt and Solid fit in Visa Intelligent Commerce, see Standards for Agentic Commerce: Visa’s Bold Move and What It Means: Visa’s investment in safe Intelligent Commerce points to a future of standards-forward personal AI, by John Bruce, Inrupt’s CEO. John briefed Joyce and me over Zoom the other day. Very encouraging, with lots to develop on and talk about.

More links:

Some news being made about Visa Intelligent Commerce:

4—Personal AI

Reza Rassool was also inspired by The Intention Economy when he started Kwaai.ai, a nonprofit community developing open-source personal AI. I now serve Kwaai as its volunteer Chief Intention Officer.

Let’s look at what personal AI will do for this woman:

Looks great, but we’re stuck in IONBA, she has little control over her personal data in all those spaces. For example,

  • She doesn’t have the digital version of what George Carlin called “a place for my stuff.” (Watch that video. It’s brilliant—and correct.)
  • She has few records of where she’s been, who she’s been with and when—even though apps on her phone know that stuff and are keeping it inside the records of her giant overlords and/or selling it to parties unknown, with no way yet for getting it back for her own use.
  • Her finances are possibly organized, but scattered between the folders she keeps for taxes, plus the ones that live with banks, brokers, and other entities she hardly thinks about. It would be mighty handy to have a place of her own where she could easily see all her obligations, recurring payments, subscriptions, and other stuff her counterparties would rather she not know completely.
  • Her schedules are in Apple, Google, and/or Microsoft calendars, which are well app’d and searchable, but not integrated. She has no digital calendar that is independent and truly her own.
  • Her business and personal relationship records are scattered across her contact apps, her Linkedin page, and piles of notes and business cards. She has no place or way of her own to manage all of them.
  • Her health care records (at least here in the U.S.) are a total mess. Some of them ares inside the MyCharts and patient portals provided by separate (and mostly unconnected) health care specialists and medical systems. Some of it is in piles of printouts she has accumulated (if she’s kept them) from all the different providers she has seen. Some of it is in fitness and wellness apps, all with exclusive ways of dealing with users. None of it is in a unified and coherent form.

So the challenge for personal AI is pulling all that data out of all her accounts, and putting it into forms that give her full agency, with the help of her personal AIs.  Personalized AIs from giants can’t do that. We need our own personal AIs.

And there we have it: Four roads to a world where free customers prove more valuable than captive ones. And we’re making it happen. Now.

The MyTerms PAR

April 6, 2025 / / 14 Comments

With MyTerms, the person (and their electronic agent) is the first party, and the corporate entity (with its agent) is the second party. This is essential for assuring full respect for personal privacy in the digital world.

Every IEEE standard starts with a PAR: a Project Authorization Request.

Here is the PAR for EEE P7012 (nicknamed MyTerms—much as IEEE 802.11 is nicknamed Wi-Fi). It launched a working group in 2017 (that I now chair), and is expected to go from draft to done by early 2026.

Because what the standard will do is plainly laid out in the PAR, I’m breaking its paragraph into separate sentences to make reading it easier:

This draft standard covers contractual interactions and agreements between individuals and the service providers they engage on a network, including websites.

It describes how individuals, acting as first parties, can proffer their privacy requirements as contractual terms and arrive at agreements recorded and kept by both sides.

These terms shall be chosen from a collection of standard-form agreements in a roster kept by an independent and neutral non-business entity.

Computing devices and software performing as agents for both first and second parties shall engage using any protocol that serves the purpose.

The first party shall point to a preferred agreement, or a set of agreements, from which the second party shall accept one.

Party-to-party negotiations over terms in any of these contracts or other agreements are outside the scope of this standard. If both parties agree, the chosen contract or agreement shall be signed electronically by both parties or their agents.

A matching record shall be kept by both sides in a form that can be retrieved, audited, or disputed, if necessary, at some later time–and which is available to do so easily.*

I can’t share the draft before the final version is published, but I can say that what it says is about as simple as what you read above. It also does not specify what tech or protocol to use. This is to leave development as open as possible.

The main thing is that MyTerms obsolesces notice-and-consent by basing privacy agreements on contracts that individuals proffer as first parties, and sites and services agree to as second parties.

Never mind that this hardly seems thinkable to the status quo. The same was once said of the Internet, the Web, email, and other free and open graces we take for granted today.

Putting each of us in charge of our privacy online is what makes MyTerms the most important standard in development today. But only if we make it so.

If you want to get involved, help us build out Customer Commons, so it can play the same role for personal privacy terms that Creative Commons plays for personal copyright.

*Shall is  IEEE-speak for will or must. The purpose of that rule is to make clear that it does not mean should, could, or any other modal auxiliary verb.

A simple plan to de-enshittify CVS

February 12, 2025 / / 16 Comments

Fifteen years ago, The Onion published this story:

Study Finds Paint Aisle At Lowe’s Best Place To Have Complete Meltdown

Now it’s the vitamin aisle at CVS:

Enshittification at work.

When Cory Doctorow coined enshittification, he was talking about how online platforms such as Google, Amazon, and TikTok get shitty over time. Well, the same disease also afflicts many big retail operations, especially ones that flood their zones with discounts and other gimmicks, enshittifying what marketers call “the customer experience” (aka CX).

Take the vitamin aisle, above. The only people who will ever get down on all fours to read the yellow tags near the floor are the cursed employees who have to creep the length of the aisle putting them there.

For customers, the main cost of shopping at CVS is cognitive overhead. Think about—

  • All those yellow stickies
  • All the slow-downs at check-out when you wave your barcode at a reader, punch your phone number into a terminal, or have a CVS worker to do the same
  • All the conditionalities in every discount or “free” offer that  isn’t
  • All the yard-long receipts, such as this one:

And the app!

OMFG,  all we really need the damned app for is the one CVS function our life depends on: the pharmacy.

To be fair, the app doesn’t suck at the basics (list of meds, what needs to be refilled, etc.). But it does suck at helping you take advantage of CVS’s greatest strength: that there are so many of them. Specifically,

While that’s down a bit from the peak in 2021, CVS is still the Starbucks of pharmacies. And while they are busy laying off people while investing in tech, you’d think they would at least make it easy to move your prescription from one store to another, using the app.  But noooo.

What the app is best for is promotional crap. For example, this:

Look at the small gray type in the red oval: 198 coupons!

After I scroll down past the six Extrabucks Rewards (including the two above), I get these:

First, who wants a full-priced item when it seems damn near everything is discounted?

Second, you’d think after all these years of checking out with my Extracare barcode, and the app shows me (under “Buy It Again”) all the stuff I’ve purchased recently, that CVS would know I am a standard-issue dude with no interest in cosmetics. So why top the list of coupons with that shit? I suppose it’s to make me scroll down through the other 178 coupons to find other stuff I might want at a cheaper price.

I just did that and found nothing. Why? Because most of the coupons are for health products I already bought or don’t need. (I’m not sick right now.) Also, almost all of the coupons (as you see) expire three days from now.

Now think about the cognitive and operational overhead required to maintain that whole program at CVS. Good gawd.

And is it necessary? At all? When you’re the Starbucks of pharmacies?

Without exception, all loyalty programs like this one are coercive. They are about trapping and milking customers.

But do stores need them? Do customers? Does CVS?  Really? When its customers are already biased by convenience.

Pro Tip: Real loyalty is earned, not coerced.

Want your store, or your chain, to be loved? Take some lessons from the most loved chain in the country: Trader Joe’s. In a chapter of The Intention Economy called “The Dance,” I list some reasons why TJ’s is loved by its customers. My main source for that list is Doug Rauch, the retired president of TJ’s, where he worked for 31 years. Here are the top few:

  1. They never use the word “consumer.” They call us “customers,” “persons,” or “individuals.”
  2. They have none of what Doug calls “gimmicks.” No loyalty programs, ads, promotions, or anything else that manipulates customers, raises cognitive overhead or insults anyone’s intelligence. In other words, none of what marketing obsesses about. “Those things are a huge part of retailing today, and have huge hidden costs,” Doug says. (I think the company’s biggest marketing expense is its float in the Rose Parade.)
  3. They never discount anything, or say anything is “on sale.” Those kinds of signals add more cognitive overhead. TJ’s wants customers not just to assume, but to know. A single price takes care of that.
  4. They have less than no interest in industry fashion. TJ’s goes to no retail industry meetings or conferences, belongs to no associations, and avoids all settings where the talk is about gaming customers. That’s not TJ’s style because that’s not its substance.
  5. They believe, along with Cluetrain, that markets are conversations—with customers. Doug told me his main job, as president of the company, was “shopping along with customers.” That’s how he spent most of his time. “We believe in honesty and directness between human beings…We do this by engaging with the whole person, rather than just with the part that ‘consumes….We’ll even open packages with customers to taste and talk about the goods.” As a result, “There’s nothing sold at Trader Joe’s that customers haven’t improved.”

Then there’s what Walmart CEO Lee Scott told me in 2000 (at this event) when I asked him “What happened to K-Mart?” From The Intention Economy:

His answer, in a word, was “Coupons.” As Lee explained it, K-Mart overdid it with coupons, which became too big a hunk of their overhead, while also narrowing their customer base toward coupon-clippers. They had other problems, he said, but that was a big one. By contrast, Wal-Mart minimized that kind of thing, focusing instead on promising “everyday low prices,” which was a line of Sam Walton’s from way back. The overhead for that policy rounded to zero.

Which brings me to trust.

We trust Trader Joe’s and Walmart to be what they are. In simple and fundamental ways, they haven’t changed. The ghosts of Joe Coloumbe and Sam Walton still run Trader Joe’s and Walmart. TJ’s is still the “irreverent but affordable” grocery store Joe built for what (in his book) Joe called “the overeducated and underpaid,” and based in Los Angeles. Walmart is still Sam’s five-and-dime from Bentonville, Arkansas. (Lee Scott told me that.)

CVS’s equivalent to Joe and Sam was Ralph Hoagland, a good friend of good friends of ours in Santa Barbara. All of us also shared history around Harvard and Cambridge, where Ralph lived when he co-founded CVS, which stood for Consumer Value Store, in 1963. In those days CVS mostly sold health and beauty products, cheaply. I remember Ralph saying the store’s main virtue was just good prices on good products. Hence the name.

CVS can do a much better job of signaling bargain prices by just making them as low as possible, on the model of Trader Joe’s and Walmart.

I think there is also a good Health position for CVS: one that bridges its health & beauty origins and its eminence as the leading pharmacy chain in the U.S. And it could rest on trust.

I’m thinking now about tech. Specifically, FPCs, for First-Person Credentials. Read what Jamie Smith says about them in his Customer Futures newsletter under the headline The most important credentials you’ve never heard of. Also check out—

  • What I wrote last year about Identity as Root
  • What DIF is doing
  • What Ayra is doing
  • Other stuff you’ll be hearing about first-person credentials (but isn’t published yet) when you come to the next IIW (April 8-10).
  • What you’ll be learning soon about re-basing everything (meaning every SKU, as well as every person) on a new framework that is far more worthy of trust than any of the separate collections of records, databases, and namespaces that currently divides a digital world that desperately needs unity and interop—especially around health. And:::
  • MyTerms, which is the new name for IEEE P7012, the upcoming standard (for which I am the working group chair) that should become official later this year, though nothing prevents anyone from putting its simple approach to work.

MyTerms can be huge and world-changing because it flips around the opt-out consent mechanisms that have been pro forma since industry won the industrial revolution and metastasized in the Digital Age. With MyTerms, the sites and services of the world agree to your terms, not the other way around. With MyTerms, truly trusting relationships can be established between customers and companies. This is why I immodestly call it the most important standard in development today.

So I have five simple recommendations for CVS, all to de-enshittify corporate operations and customer experiences:

  1. Drop the whole loyalty thing. Completely. Cold turkey. Hell, fire the marketing department. Put the savings into employees you incentivize to engage productively (not promotionally) with customers. And publicize the hell out of it. Should be fun.
  2. Confine your research to what your human employees learn directly from their human customers.
  3. Be the best version of what you are: a great pharmacy/convenience store chain that’s still long in health and beauty products.
  4. Simplify the app by eliminating all the promotional shit, and by making it as easy as possible for customers to move prescriptions from one  CVS store to another.
  5. Watch what’s happening with first-person credentials and MyTerms. Getting on board with those will make CVS a leader, rather than a follower.

Coupon-clipping addicts may feel some pain at first, but if you market the new direction well—making clear that you have “everyday low prices” rather than annoying and labor-intensive discounts (many of which expire in three days), customers will come to love you.

Blocking Tracking ≠ Blocking Ads

February 8, 2025 / / 0 Comments

I started reading BoiongBoing when it was a ‘zine back in the last millennium. I stopped when I began hitting this:

boingboing popover

In fact I don’t block ads. I block tracking, specifically with Privacy Badger, from the EFF.

But BoingBoing, like countless other websites, confuses tracking protection with ad blocking. This is because they are in the surveillance-aimed advertising business, aka adtech.

It’s essential to know that adtech is descended from the junk mail business, euphemistically called “direct response marketing.” As I put it in Separating Advertising’s Wheat and Chaff,

Remember the movie “Invasion of the Body Snatchers?” (Or the remake by the same name?) Same thing here. Madison Avenue fell asleep, direct response marketing ate its brain, and it woke up as an alien replica of itself.

As surveillance-based publications go, BoingBoing is especially bad. Here is a PageXray of BoingBoing.net:

And here is a PageXray of the same page’s URL, to which  tracking cruft from the email I opened was appended:


Look at that: 461 adserver requests, 426 tracking requests, and 199 other requests, which BoingBoing is glad to provide. (Pro tip: always strip tracking cruft from URLs that feature a “?” plus lots of alphanumeric jive after the final / of the URL itself. Take out the “?” and everything after it. )

Here is a close-up of one small part of that vast spread of routes down which data about you flows:

Some sites, such as FlightAware, interrupt your experience with a notice that kindly features an X in a corner, so you can make it go away:

flightaware notice
Which I do.

But BoingBoing doesn’t. Its policy is “Subscribe or pay with lost privacy.”  So I go away.

Other sites use cookie notices that give you options such as these from a Disney company (I forget which):

Nice that you can Reject All. Which I do.

This one from imgur let’s you “manage” your “options.” Those, if they are kept anywhere (you can’t tell), are in some place you can’t reach or use to see what your setting was, or if they haven’t violated your privacy:

imgur notice
This one at Claude defaults to no tracking for marketing purposes (analytics and marketing switches are set to Off):

TED here also lets you Accept All or Reject All:

ted-cookie

I’ve noticed that Reject All tends to be a much more prominent option lately. This makes me think a lot of these sites should be ready for IEEE P7012, nicknamed MyTerms, which we expect to become a working standard sometime this year. (I chair the working group.) I believe MyTerms is the most important standard in development today because it gets rid of this shit—at least for sites that respect the Reject All signal, plus the millions (perhaps billions?) of sites that don’t participate in the surveillance economy.

With MyTerms, sites and services agree to your terms—not the other way around. And it’s a contract. Also, both sides record the agreement, so either can audit compliance later.

Your agent (typically your browser, through an extension or a header) will choose to proffer one of a small list of contractual agreements maintained by a disinterested nonprofit. Customer Commons was created for this purpose (as a spin-off of ProjectVRM). It will be for your terms what Creative Commons is for your copyright licenses.

Customer Commons also welcomes help standing up the system—and, of course, getting it funded. If you’re interested in working on either or both, talk to me. I’m first name at last name dot com. Thanks!

 

Derailing the Customer Journey

January 2, 2025 / / 0 Comments

This came in the mail today:

Everything they list is something I don’t want to do. I’d rather just accumulate the miles. But I can’t, unless I choose one of the annoyances above, or book a flight in the next three months.

So my customer journey with American is now derailed.

There should be better ways for customers and companies to have journeys together.

Hmm… Does United have one?

Here’s a picture of my customer journey with United Airlines, as of today:

I’m also a lifetime member of the United Club, thanks to my wife’s wise decision in 1990 to get us both in on that short-lived deal.

Premier Platinum privileges include up to three checked bags, default seating in Economy Plus (more legroom than in the rest of Economy), Premium lines at the ticket counter and Security, and boarding in Group One. There are more privileged castes, but this one is a serious tie-breaker against other airlines. Also, in all our decades of flying with United, we have no bad stories to tell, and plenty of good ones.

But now we’re mostly based in Bloomington, Indiana, so Indianapolis (IND) is our main airport. (And it’s terrific. We recommend it highly.) It is also not a hub for any of the airlines. The airline with the most flights connecting to IND is American, and we’ve used them. I joined their frequent flier program, got their app, and started racking up miles with them too.

So here is one idea, for every airline: having respect for one’s established status with other airlines means something. Because that status (or those stati) are credentials: They say something about me as a potential passenger. It would be nice also if what I carry, as an independent customer, is a set of verifiable preferences—such as that I always prefer a window seat, never tow a rolling bag on board (I only have a backpack), and am willing to change seats so a family can sit together. Little things that might matter.

I bring all this up because fixing “loyalty” programs shouldn’t be left up only to the sellers of the world. They’ll all do their fixes differently, and they’ll remain deaf to good input that can only come from independent customers with helpful tools of their own.

Developing those solutions to the loyalty problem is one of our callings at ProjectVRM. I also know some that are in the works. Stay tuned. 🙂

The Independent Customer

November 21, 2024 / / 1 Comment

How dow we get from this—

To this—

?

By making customers independent.

Hmm… maybe The Independent Customer should be the title of my follow-up to The Intention Economy.

Because, to have an Intention Economy, one needs independent customers: ones who are in charge of their own lives in the digital world:

  • Who they are—to themselves, and to all the entities they know, including other people, and organizations of all kinds, including companies.
  • What they know about their lives (property, health, relationships, plans, histories)—and the lives of others with whom they have relationships.
  • Their plans—for everything.: what they will do, what they will buy, where they will go, what tickets they hold, you name it.

Add whatever you want to that list. It can be anything. Eventually it will be everything that has a digital form.

What will hold all that information, and what will make that information safely engageable with other people and entities?

A wallet.

Not a digital version of the container for cash and cards we carry in our purses and pockets. Apple and Google think they own that space already, which is fine, because that space is confined by the mobile app model. Wallets will be bigger and deeper than that.

Wallets will embody two A’s: archives and abilities. Among those abilities is AI: your AI. Personal AI. One that is agentic for you, and not just for the sellers of the world.

Interesting harbinger: Inrupt now calls Solid pods “wallets.” (Discussion.)

Wallets are how we move e-commerce from a world of accounts to a world of independent customers with personal agency. With AI agents working for them and not just for sellers.

In his latest newsletter, titled ‘A-Commerce’ will be the biggest disruption since the web, and Digital Wallets are the new accounts, Jamie Smith says this:

The Web3 crowd say digital wallets are about transferrable digital assets and ownership without a central authority. And they are right.

But there’s more.

Many payments and identity experts will say that digital wallets are really about identity. Proving who you are and what you are entitled to do (tickets, access). Maybe even with fancy selective disclosure features.

They are also right. But that’s not the whole picture.

A pioneering group of others believe that digital wallets are really about the portability of any verifiable information, and digital authenticity.

And they too are right. We’re now getting much, much closer to what I’m talking about. But there’s still more.

Once individuals can show up independently, with their own digital tools – digital wallets with verifiable, data, identity and digital assets – then we have something new, something special.

It’s a New. Customer. Channel.

Once a business asks for some data from a customer’s digital wallet, they have the opportunity to form a new digital connection with that customer.

A persistent one.

A verifiable one.

A private one.

An auditable, secure and intelligent one.

My goodness, what business wouldn’t want that? Imagine plugging that customer connection directly into business systems and processes, like CRM.

Yes, digital wallets can hold and manage assets. And identity. And portable, verifiable, authentic data.

But with the narrower ‘data and assets’ framing, we risk missing the larger market opportunity.

Digital wallets become the new account.

For everything.

OK so what is an account?

With money, it’s a shared and trusted record of all your transactions. Who did what, who paid what, and who owes who.

With business, it’s a shared record of all your products and interactions. It’s a critical customer channel and interface. The place people come to check things. To ask things. To ‘do business’.

Each customer account has a number. A unique identifier. It has a way to message customers. A way to record what’s been sent to, and received from, the customer.

Ring a bell?

Digital wallets will be able to do all this and much more.

They will also be more secure. More private. More flexible. And more portable.

So it’s possible – I’d even argue more likely – that digital wallets may be more disruptive than browsers were in the 1990s.

But like browsers, they will first be misunderstood.

Digital wallets will become the new account.

For business? For government? For banking? For health? For travel?

For life.

I have said for over a decade that the only 360° view of the customer, is the customer.

Just imagine, once a customer can bring their own wallet – their own account – to each business:

  • The economics change. Why would a business maintain a complex and proprietary account platform when digital interactions can be handled – indeed automated – via a verifiable digital wallet that’s available on every smart device?
  • The data flows change. Why would a business store unnecessary customer data when they can just ask for it on demand, with consent, from the customer’s digital wallet? Then delete it again once used?
  • The risks change. What if we could reduce fraud and account takeover to near zero, when every customer interaction has to be authenticated via the customer’s digital wallet (likely with biometrics)?

The very fabric of the customer relationship changes.

This is just a glimpse of what‘s possible, and what’s coming. Especially when you tie it to digital AI agents….

When you look closely, you’ll see that digital wallets aren’t even The Thing. They are ‘below the surface’ of the customer channel.

Lots to be written about that. Coming soon.

For now, it’s a simple switch: when you hear ‘account’, just think ‘wallet’.

Here is the challenge: making wallets a must-have: an invention that mothers necessity.

We’ve had those before, with—

  • PCs
  • word processors and spreadsheets
  • the Net and the Web,
  • graphical browsers
  • personal publishing and syndication
  • smartphones and apps
  • streams and podcasts.

Wallets need to be like all of those: must-haves that transform and not just disrupt.

It’s a tall order, but—given the vast possibilities—one that is bound to be filled.
As for why this won’t be something one of the bigs (e.g. Apple and Google) do for themselves, consider these five words you hear often online:

“Wherever you get your podcasts.”

Those five words were made possible by RSS.

It’s why all of the things in the bullet list above are NEA:

  • Nobody owns them
  • Everybody can use them
  • Anyone can improve them

When we have wallets with those required features, and they become inventions that mother necessity, we will have truly independent customers.

And we will finally prove ProjectVRM’s prime thesis: that free customers are more valuable than captive ones—to themselves and to the marketplace.

ONDC, Beckn, and VRM

November 17, 2024 / / 0 Comments

This is important. Be there.

If we want VRM to prove out globally, we have to start locally. That’s what’s happening right now in India, using ONDC (the Open Network for Digital Commerce), which runs on the Beckn protocol.

ONDC is a happening thing:

One big (and essential) goal for VRM is individual customer scale across many vendors.  ONDC and Beckn are for exactly that. Here is how kaustubh yerkade explains it in Understanding Beckn Protocol: Revolutionizing Open Networks in E-commerce:

Beckn protocol in the Real World
The Beckn Protocol is part of a larger movement toward creating open digital ecosystems, particularly in India. For example, the ONDC (Open Network for Digital Commerce) initiative in India is built using the Beckn protocol, aiming to democratize e-commerce and bring small retailers into the digital economy. The Indian government supports ONDC for making digital commerce more accessible and competitive.

Here are some practical examples of how the Beckn Protocol can be used in different industries:

1. Ride-Hailing and Mobility Services
Example: Imagine a city with multiple ride-hailing services (e.g., Uber, Ola, Rapido). Instead of using individual apps for each service, a user can use one app powered by the Beckn Protocol. This app aggregates all available ride-hailing services, showing nearby cars, prices, and estimated arrival times from multiple providers. The user can choose the best option, book the ride, and pay directly through the unified app.

Benefit: Service providers gain broader visibility, and users can easily compare services in one place without switching between apps.

https://becknprotocol.io/imagining-mobility-with-beckn/

2. Food Delivery Services
Example: A consumer uses a food delivery app that leverages Beckn to show restaurants from multiple food delivery services (like Zomato, Swiggy, and local food delivery providers). Instead of sticking to just one platform, the user sees menus from different services and can order based on price, availability, or delivery time.

Benefit: Restaurants get listed on more platforms, increasing their exposure, and users can find more options without hopping between different apps.

3. E-Commerce and Local Retail
Example: A shopper is looking for a product (like a phone charger) and uses an app built on the Beckn Protocol. The app aggregates inventory from big e-commerce players (like Amazon or Flipkart) as well as small local retailers. The user can compare prices and delivery times from both big platforms and nearby local stores, then make a purchase from the most convenient provider.

Benefit: Small businesses and local stores can compete with larger e-commerce platforms and reach a wider audience without needing their own app or website.

4. Healthcare Services
Example: A patient needs to book a doctor’s appointment but doesn’t want to manually search through different healthcare platforms. A healthcare app using Beckn shows available doctors and clinics across multiple platforms (like Practo, 1mg, or even independent clinics). The patient can choose a doctor based on location, specialization, and availability, all in one place.

Benefit: Patients get access to a larger pool of healthcare providers, and doctors can offer their services on multiple platforms through a single integration.

5. Logistics and Courier Services
Example: An online seller wants to ship products to customers but doesn’t want to manage multiple courier services. With an app built on Beckn, they can see delivery options from multiple logistics providers (like FedEx, Blue Dart, and local couriers) and choose the best one based on cost, speed, or reliability.

Benefit: Businesses can streamline shipping operations by comparing various logistics providers through one interface, optimizing for cost and delivery time.

6. Public Transportation
Example: A commuter is planning a trip using public transit in a city. Using a Beckn-powered app, they can view transportation options from multiple transit services (like metro, bus, bike-sharing services, or even ride-hailing). The app provides real-time schedules, available options, and payment methods across different transport networks.

Benefit: The commuter has a unified experience with multiple transportation modes, improving convenience and access to more options.

7. Local Services (Home Services, Repair, Cleaning)
Example: A user needs a home repair service (e.g., a plumber or electrician). Instead of browsing different service provider platforms (like UrbanClap or Housejoy), a Beckn-enabled app aggregates professionals from multiple service providers. The user can compare prices, reviews, and availability and book a service directly from the app.

Benefit: Service providers get access to more customers, and consumers can quickly find professionals based on location, reviews, and price.

8. Travel and Hospitality
Example: A traveler uses a travel booking app based on Beckn to find accommodations. The app aggregates listings from various hotel chains, Airbnb, and local guesthouses. The traveler can filter by price, location, and amenities, then book the best option without switching between platforms.

Benefit: Smaller accommodation providers can compete with big brands, and travelers get access to more choices across different platforms in one app.

9. Government Services and Civic Engagement
Example: A citizen uses a Beckn-enabled app to access multiple government services. They can apply for a driver’s license, pay taxes, and book a health checkup at a government hospital—all from one platform that integrates services from different government departments and third-party providers.

Benefit: Governments can offer a unified experience across various services, and citizens get easier access to public services without visiting multiple websites or offices.

He adds,

The ONDC (Open Network for Digital Commerce) initiative in India is built using the Beckn protocol, aiming to democratize e-commerce and bring small retailers into the digital economy. The Indian government supports ONDC for making digital commerce more accessible and competitive.

While it is nice to have government support, anyone anywhere can deploy open and decentralized tech, or integrate it into their apps and services.

On Tuesday we’ll have a chance to talk about all this at our latest salon at Indiana University and live on Zoom. Our speaker, Shwetha Rao, will be here in person, which always makes for a good event—even for those zooming in.

So please be there. As a salon, it will be short on lecture and long on dialog, so bring your questions. The Zoom link is here.

 

 

VRM Day and IIW next week

October 22, 2024 / / 0 Comments

A pano from VRM Day in April 2015

VRM Days always happen the day before IIW starts, twice each year. Usually, we have about 50 registered and 30 showing up. (Some are online, though we’d rather have their bodies in the room.)  For the VRM Day this coming Monday, we’re expecting more than 100 people. So, like Sheriff Brody said in Jaws, we need a bigger room.

And we have one. So that’s good. Logistics will be challenging, but we’re on top of them.

IIW is also close to sold out. Last I checked, there were just nine tickets left.

Here is copy from our Eventbrite page as it now stands:

The Main Thing

At this VRM Day, Ben Moskowitz, VP Innovation and Ginny Fahs, Director of Product R&D at Consumer Reports will lead discussion of some of their early R&D concepts around a new approach to customer service: one in which personal AI agents represent customers’ best interests.

This is CX (Customer Experience) re-imagined and re-implemented in ways that are no less real and human but far more intelligent, mutually informative, and useful than what all of us have experienced thus far in the Digital Age. CR is looking for feedback and collaboration as they move forward. They plan to participate in IIW as well.

As usual, everyone who wants to share what they’re working on in the VRM space will have time to present, discuss, and prep for IIW.

Schedule

Morning:

  • 9am – Noon. Consumer Reports presentation and discussion (on the above)

Lunch

  • Noon – 1:30 (Sports Page or Zareen’s (diagonal across the intersection)

Afternoon

  1. Adrian Gropper on HIE of One, Medical AI Assistant (MAIA) and personal AI in health care
  2. Joe Andrieu on the Digital Fiduciary Initiative
  3. Cryptid / KwaaiNet demo
  4. Iain Henderson on Data Pal
  5. Richard Whitt on GliaNet Alliance
  6. Customer Commons on IEEE P7012
  7. Paul Trevithick (Mee.Foundation) on Private Advertising

  • Discussion on any or all of the above

  • Listing planned IIW sessions

Subject to change, of course.

Since we have a lot to cover, please be there at 9am sharp, and be back from lunch at 1:30.

Note that there are only three lunch places nearby. Cucina Venti is good but relatively expensive and service is slow. Sports Page is makes good sandwiches and has lots of picnic tables. It’s where most of us usually go. Haven’t tried Zareen’s, behind the Sports Page, where Sunny Bowl and other restaurants used to be. It has “familiar & innovative halal spins on Indian & Pakistani cooking.”

 

 

 

On Intentcasting

August 28, 2024 / / 4 Comments

The cover page of the Weekend Review section of The Wall Street Journal, July 20, 2012

On July 9, 2012, not long after The Intention Economy came out, I got word from Gary Rosen of The Wall Street Journal that the paper’s publisher, Robert Thomson, loved the book and wanted “an excerpt/adaptation” from the book for the cover story of  the WSJ’s Weekend Review section. The image above is the whole cover of that section, which appeared later that month.

In the article I described a new way to shop:

An “intentcast” goes out to the marketplace, revealing only what’s required to attract offers. No personal information is revealed, except to vendors with whom you already have a trusted relationship.

I also said that this form of shopping—

…can be made possible only by the full empowerment of individuals—that is, by making them both independent of controlling organizations and better able to engage with them. Work toward these goals is going on today, inside a new field called VRM, for vendor relationship management. VRM works on the demand side of the marketplace: for you, the customer, rather than for sellers and third parties on the supply side.

The scenario I described was set ten years out: in 2022, a future now two years in the past. In the meantime, many approaches to intentcasting have come and gone. The ones that have stayed are Craigslist, Facebook Marketplace, Instacart, TaskRabbit, Thumbtack, and a few others. (Thumbtack participated in the early days of ProjectVRM.) We include them in our list of intentcasting services because they model at least some of what we’d like intentcasting to be. What they don’t model is the full empowerment of individuals as independent actors: ones whose intentions can scale across whole markets and many sellers:

Scale gives the customer single ways to deal with many companies. For example, she should be able to change her address or last name with every company she deals with in one move—or to send an intention-to-buy “intentcast” to a whole market.

Should we call the sum of it “i-commerce“? Just a thought.

Back to the Wall Street Journal article. It is clear to me now that The Customer as a God would have been a much better title for my book than The Intention Economy, which needs explaining and sounds too much like The Attention Economy, which was the title of the book that came out ten years earlier. (I’ve met people who have read that one and thought it was mine—or worse, called my book “The Attention Economy” and sent readers to the wrong one.)

Of course, calling customers gods is hyperbole: exaggeration for effect.  VRM has always been about customers coming to companies as equals. The “revolution in personal empowerment” in the subhead of “The Customer as a God” is about equality, not supremacy. For more on that, see the eleven posts before this one that mention the R-button:

That symbol (or pair of symbols) is about two parties who attract each other (like two magnets) and engage as equals. It’s a symbol that only makes full sense in open markets where free customers prove more valuable than captive ones. Not markets where customers are mere “targets” to “acquire,” “capture,” “manage,” “control” or “lock in” as if they were slaves or cattle.

The stage of Internet growth called Web 2.0 was all about those forms of capture, control, and coerced dependency. We’re still in it. (What’s being called Web3 is, while “decentralized” (note: not distributed), it is also based on tokens and blockchain. ) Investment in customer independence rounds to nil.

And that’s probably the biggest reason intentcasting as we imagined it in the first place has not taken off. It is very hard, inside industrial-age business norms (which we still have) to see customers as equals, or as human beings who should be equipped to lead in the dance between buyers and sellers, or demand and supply, in truly open marketplaces. It’s still easier to see us as mere consumers (which Jerry Michalski calls “gullets with wallets and eyeballs”).

So, where is there hope?

How about AI? It’s at the late end of its craze stage, but still here to stay, and hot as ever:

Can AI provide the “revolution in personal empowerment” we’ve been looking for here since 2006? Can it prove our thesis—that free customers are more valuable than captive ones—to themselves and to the marketplace?

Only if it’s personal.

If it is, then the market is a greenfield.

Some of us here are working at putting AI on both sides of intentcasting ceremonies. If you have, or know about, one or more of those approaches (or any intentcasting approaches), please share what you know, or what you’re got, in the comments below. And come to VRM Day on October 28. I’ll be putting up the invite for that shortly.

 

« Older posts Newer posts »

© 2026 ProjectVRM

Theme by Anders Noren — Up ↑