The week to 7 October: the agent team, written up from the inside

The busiest week of articles on the site so far, and most of it is one story told three times at increasing depth: a team of agents running a business, from the walkthrough to the field notes to the full stack.

Twenty articles published from 2026-10-01 to 2026-10-07, newest first, each with the one-sentence teaser from its graph.

2026-10-07 An open AI governance framework, and what its licence let us build Twenty open AI governance controls under CC BY-SA, why the licence matters, and the same day's conversion into a graph, a database and a walk down to EU law.
2026-10-07 A locked-down desktop for an agent, by the minute, is still hard to rent Nine properties a safe agent desktop needs, nine products against them, the macOS day-long lease, and the startup credits that would pay for testing it.
2026-10-07 Where is the why? A permission prompt asked me to decide, and kept the reason A prompt asked for a decision and kept the reason. Read through the policy, the law on uninformed consent, and the fixes that worked: put the why in the prompt.
2026-10-06 A personal agent that keeps your secrets: the 2026 agents read through behaviour policy and encryption, and a privacy-first design on vaults, enclaves and the browser The 2026 personal agents read through behaviour policy and encryption, and a design on vaults, an attested enclave and the browser where no vendor holds a key.
2026-10-06 The agent team as it runs: one person, twelve agents, encrypted vaults, and a mailbox nobody sends from Twelve agents on dedicated accounts, encrypted vaults as the only memory, messages as files, a folder per person, and a mailbox nobody sends from.
2026-10-06 The deck I could not download: an author-first home for presentations, as a business plan somebody else can build One download offered as a subscription, an author paid nothing, and a design for the service the author would have chosen: vaults, keys, seven roles, 85% to the author.
2026-10-06 The Mandate Stack: a multi-agent system in production, layer by layer A multi-agent system that runs a business every few hours: eight layers, one written mandate per agent, everything a graph, one human who sends.
2026-10-06 Why my agents do not run on my laptop: chat, Cowork and Code in the cloud, a vault as the shared drive, and the two walls an operating system has An OS has two hard walls, the kernel and the user; an agent on a laptop runs inside the one marked you, so the agents run in the cloud with a vault as shared drive.
2026-10-05 How much of this did I write? The numbers behind twenty articles in four weeks, and what the input actually was Twenty articles in four weeks, measured from the session record: 63,000 words in, 85,000 out, no one-line prompts, and the real input is twenty years of writing.
2026-10-05 If somebody built a company on code review: how I would do it, and why it is only now possible A reader's seven questions answered as a company plan: one reader for every layer, review as a science, and the layers as the customer's own.
2026-10-05 Send an agent, not a spreadsheet: the next generation of software due diligence, and why the companies that stopped reading their code are about to be asked about it Due diligence never scaled because it was a form; a buyer can now send an agent into a vendor's environment and read what the code and the practices are.
2026-10-05 The identity we wanted to give the agents: a week of design, the line in Google's terms, and why login plus secrets is still too hard A week of designing identities for agents and users met Google's terms; what survived is a passkey-unlocked keyring and a gap nobody sells.
2026-10-05 The investigation GitHub owes its customers: why a global outage of a platform the world deploys through deserves an aviation-style inquiry, and how the evidence could now be gathered A global GitHub Actions outage read the way aviation reads an incident: independent inquiry, near-miss reporting, second and third stories, vaults for the evidence.
2026-10-04 The wall under the reply: end an email with the state of the thread, not the thread End an email reply with the state of the thread for this reader, not the quoted wall: decided, open, next, who is on copy, with links to the record.
2026-10-03 Code review as a fractal semantic graph: source code is already one, and the review should read every layer of it Source code is layers within layers, each a graph with its own vocabulary; code review should read a change at every one, and a vault shows it done on real code.
2026-10-03 Memory is not a spectator sport: how a web of open sites, graphs and vaults became the memory for sessions like this one Agentic memory as context management: many published, fractal, provenance-carrying memories rather than one store, shown in the session that wrote the article.
2026-10-02 Footprint and blast radius: what the agent actually did, and what it would have cost Footprint is what an agent actually did, read afterwards from logs and vault history; blast radius is what a row of its reach would cost the business today.
2026-10-02 Price it, then give it away: the early access programme as the next step after "do they miss it" Define the product, price it, deliver it at a cost that grows a step at a time, then offer it free to people who know you and measure what it costs them.
2026-10-02 Replicating the agentic inbox: a walkthrough from one Claude session to a team of agents that never press send How to copy a working agentic email setup in phases: a mailbox and Claude seat of the agent's own, one session with a policy, then roles talking in files.
2026-10-01 Custom UIs are not the exception: the inbox in 2026, where every message has its own universe Every message has a graph, so it can be shaped for the reader's moment; a custom interface per moment is now how interfaces get made, and each gets a policy.

One story, three depths. Replicating the agentic inbox said how to build it in phases. The agent team as it runs wrote up the same team from its own field notes. The Mandate Stack described it in eight layers from a briefing its CRM agent wrote, with two Wardley maps and their sources, and was revised twice in the week.

Personal agents, read through policy. A personal agent that keeps your secrets read the year's personal agents through the behaviour policy and through encryption; why my agents do not run on my laptop asked the reach question of the operating system.

Review as a science, and the input measured. Code review as a fractal semantic graph drew a reader's seven questions, answered in if somebody built a company on code review. And how much of this did I write? counted the author's input across the month, which the desk has pulled out as a nugget.

Rests on

Replicating the agentic inbox: a walkthrough from one Claude session to a team of agents that never press send How to copy a working agentic email setup in phases: a mailbox and Claude seat of the agent's own, one session with a policy, then roles talking in files.
The agent team as it runs: one person, twelve agents, encrypted vaults, and a mailbox nobody sends from Twelve agents on dedicated accounts, encrypted vaults as the only memory, messages as files, a folder per person, and a mailbox nobody sends from.
The Mandate Stack: a multi-agent system in production, layer by layer A multi-agent system that runs a business every few hours: eight layers, one written mandate per agent, everything a graph, one human who sends.
A personal agent that keeps your secrets: the 2026 agents read through behaviour policy and encryption, and a privacy-first design on vaults, enclaves and the browser The 2026 personal agents read through behaviour policy and encryption, and a design on vaults, an attested enclave and the browser where no vendor holds a key.
Why my agents do not run on my laptop: chat, Cowork and Code in the cloud, a vault as the shared drive, and the two walls an operating system has An OS has two hard walls, the kernel and the user; an agent on a laptop runs inside the one marked you, so the agents run in the cloud with a vault as shared drive.
Code review as a fractal semantic graph: source code is already one, and the review should read every layer of it Source code is layers within layers, each a graph with its own vocabulary; code review should read a change at every one, and a vault shows it done on real code.
If somebody built a company on code review: how I would do it, and why it is only now possible A reader's seven questions answered as a company plan: one reader for every layer, review as a science, and the layers as the customer's own.
How much of this did I write? The numbers behind twenty articles in four weeks, and what the input actually was Twenty articles in four weeks, measured from the session record: 63,000 words in, 85,000 out, no one-line prompts, and the real input is twenty years of writing.

← From the desk · The front page