# Articles, sgit.ai > Longer pieces that make an argument across several pages: what a thing means, why it is shaped that way, and what it cost to find out. Each links to the pages that own its facts rather than restating them. *Source: · sgit.ai v0.7.40 · this file is generated from the same content as the page, so the two cannot drift. Every page on this site has a `.md` twin; internal links below point at them.* --- Edition of 2026-10-0867 articles · 4 desk notes · 5 collections · 2 issuessgit.ai · v0.7.40 # SGit Newsroom One page, one argument, with the figures, the data and the links to check it. Every article is live the moment it is written; the front is the [newsroom](../newsroom/index.md)'s choice of where to start. From the editor Third edition. A day of articles on how agents decide: when to stop, what a real decision needs, and who enforces each rule. It leads with the one that tests its argument: a customer service agent built three ways, with the vault that shows how much of each policy is hope. Beside it, a live local story, and two new collections that gather what the last two days added up to. [The desk log →](../newsroom/log.md) [Built three ways2026-10-08Agents & policy**Hope or enforcement: one customer service agent, three designs, and who keeps each promise**One customer service agent built three ways, each with an Agent Behaviour Policy: how much of each policy is hope, and what one run can reach.**Why it leads.** One mandate, three designs and a published vault: the behaviour-policy argument measured rather than asserted, down to which rules a model is only hoped to keep.Read it →](hope-or-enforcement.md) ## Latest 1. 2026-10-10[How to run synthetic users on your own site](how-to-run-synthetic-users.md) 2. 2026-10-10[A link to a persona](a-link-to-a-persona.md) 3. 2026-10-10[Pay after you read](pay-after-you-read.md) 4. 2026-10-10[Where the vault keys live](where-the-vault-keys-live.md) 5. 2026-10-10[The infographic bake-off](the-infographic-bake-off.md) 6. 2026-10-10[Pay to keep your persona](pay-to-keep-your-persona.md) 7. 2026-10-10[Who will game the reading meter? Eight kinds of reader, nine ways to cheat, and the…](who-will-game-the-reading-meter.md) 8. 2026-10-10[Going live with the reading meter](going-live-with-the-reading-meter.md) 9. 2026-10-10[Open source is not free](open-source-is-not-free.md) 10. 2026-10-10[One article, five readers](one-article-five-readers.md) [Every article, 67 →](index.md#all) ## Highlights [A scale for deciding2026-10-08**Agency is not a yes**Seven dimensions, seven levels, and the line below which a decider carries liability rather than agency. Its own vault holds the scale.](agency-is-not-a-yes.md)[Live, local2026-10-08**The waiting room knew first**A hospital IT outage nobody could check from home, kept as evidence in a vault while it was still happening.](the-waiting-room-knew-first.md)[Complexity2026-10-08**Every mistake added a rule**When every agent mistake adds a rule, the rules become the problem. Mapped, with the way back to shipping.](every-mistake-added-a-rule.md)[Pitched, accepted2026-10-07**Zoom into an agent's behaviour policy and you find the business logic**Zoom into an agent's policy and you find the business: the rules the user interface used to enforce by omission.](the-behaviour-policy-is-the-business-logic.md) ## From the desk [all notes →](desk/index.md) [Thread2026-10-08Historian**Range is the feature, so the stop has to be designed**Four articles from one day, written for different reasons, end on the same line: an agent's range is what makes it useful, and it is also why the decision to stop cannot be left to the agent.](desk/range-is-the-feature-so-the-stop-is-designed.md)[The week2026-10-07Journalist**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.](desk/the-week-to-7-october.md)[Thread2026-10-07Historian**Create anywhere, edit your own: a rule learned in the inbox, applied to the newsroom**The agent team tried letting only one agent draft, and it became a bottleneck in two days. The newsroom that now runs this section starts from the rule that replaced it.](desk/create-anywhere-edit-your-own.md)[Nugget2026-10-07Historian**A model that can go in every direction needs someone with a direction**A model that can go in every direction needs someone with a direction.](desk/a-model-that-can-go-in-every-direction.md) ## Collections [all collections →](collections/index.md) [Collection · 6 articles**How agents decide, and when they stop**What a real decision needs, who enforces each rule, and why an agent that can go anywhere has no reason to stop: six articles on deciding, for people and agents alike.](collections/how-agents-decide.md)[Collection · 6 articles**Local news, kept as evidence**A bridge closure followed to the end, a hospital outage nobody could check from home, and the case that local journalism has the most to gain from keeping its reporting as a graph.](collections/local-news-kept-as-evidence.md)[Collection · 11 articles**Behaviour policy in practice**RiskMandate's Agent Behaviour Policy applied to real agents: one inbox, a team of twelve, the personal agents of 2026, and what an agent actually did afterwards.](collections/behaviour-policy-in-practice.md) **Get the SGit Newsroom newsletter.** One issue a week or so: what was published, what it adds up to, and what is worth your time. [Subscribe to the SGit Newsroom →](../subscribe/index.md) ## Every article, newest first [2026-10-10Vaults & method1 thread**How to run synthetic users on your own site: five people who do not exist, a browser, and an afternoon**Five invented users, a model reading screenshots, and a real browser: how to run synthetic users, from three studies.](how-to-run-synthetic-users.md) [2026-10-10Startups & strategy2 threads**A link to a persona: send people to the newsroom as someone, not as nobody**Send a CISO to the newsroom as a CISO: personas kept in a vault by the newsroom's agents, opened from a link, followed or forked.](a-link-to-a-persona.md) [2026-10-10News & evidence6 threads**Pay after you read: how a reading meter became a working business model in one afternoon, one release at a time**Seven releases in one afternoon turned the reading meter into a working model: pay after you read, and the rating sets the price.](pay-after-you-read.md) [2026-10-10Vaults & method4 threads**Where the vault keys live: key management at sgit-ai v0.20.0, and what comes next**Vault key management at sgit-ai v0.20.0: the one secret, where keys are kept, how they travel sealed on append lanes, and what comes next.](where-the-vault-keys-live.md) [2026-10-10Site & engineering2 threads**The infographic bake-off: which image model for which job, judged blind on 10 October 2026**Every image model on OpenRouter, eleven briefs, 101 images judged blind, $10.44: which model for which infographic, and what it costs.](the-infographic-bake-off.md) [2026-10-10Startups & strategy7 threads**Pay to keep your persona: readers should pay because it helps them, not because they feel they should**Readers should pay because it helps them: a persona with a name and a graph, several for focus, and one that follows you between devices.](pay-to-keep-your-persona.md) [2026-10-10Startups & strategy6 threads**Who will game the reading meter? Eight kinds of reader, nine ways to cheat, and the risks that will actually happen**Eight kinds of reader, none of them attackers, nine ways to cheat a browser meter, and the quieter risks that will actually happen.](who-will-game-the-reading-meter.md) [2026-10-10Startups & strategy10 threads**Going live with the reading meter: pay for what you read, go below zero if you like, and the numbers we will check in eight weeks**Pay for the share of a page you read, go below zero with no nagging, top up £5 on Stripe: the plan, and the numbers we check in eight weeks.](going-live-with-the-reading-meter.md) [2026-10-10Startups & strategy2 threads**Open source is not free: who pays to keep the long tail working?**An old iMac, the long tail of old versions that projects are not paid to support, measured from public data, and five ways to pay for it, simulated.](open-source-is-not-free.md) [2026-10-10News & evidence12 threads**One article, five readers: a librarian, a cartographer, a historian, an explainer and a storyteller read the same piece**Write the article first, then send five agent readers through it: a catalogue, an ontology and maps, the arc, two minutes, and a deck.](one-article-five-readers.md) [2026-10-10Startups & strategy9 threads**A meter in the browser: a penny a page, a history you keep, and a site that picks for you**Every page now costs a few pence from £5 of credit kept in your browser, and the reading history it keeps is what personalises the site.](a-meter-in-the-browser.md) [2026-10-10Agents & policy3 threads**Re-anchoring: keeping an agent's rules alive through every summary, and a canary that shows when they are not**Summaries keep under 2% of a long session. Re-anchoring prints the agent's rules back after each one; a canary report shows it is working.](re-anchoring-agent-behaviour-policies.md) [2026-10-09Agents & policy4 threads**A second reader the agent cannot skip: how two wrong emails became a gate on every draft**Two emails went out in my voice despite a written rule. The fix: a hook that makes a second model approve every draft, failing closed.](a-second-reader-the-agent-cannot-skip.md) [2026-10-09Graphs & knowledge2 threads**The AI governance stack, as a graph: an answer to Hari Kota, built**Hari Kota's ten-layer AI governance stack, kept as posted and turned into a fractal semantic graph: the gaps become missing edges, and queries.](the-ai-governance-stack-as-a-graph.md) [2026-10-09Vaults & method2 threads**RFC 0001: two ways to add public-key cryptography to sgit, and the questions we want you to answer**A Request for Comments: two key pairs so a reader cannot write, sealed files only named people can open, and fourteen questions for reviewers.](rfc-0001-public-key-cryptography-for-sgit.md) [2026-10-09Startups & strategy7 threads**A Mac of the agent's own: a business plan for agent desktops, what Apple's licence allows, and three behaviour policies**A business plan for a Mac of the agent's own: what Apple's licence allows, a desktop built from vaults per run, and three behaviour policies for one agent.](a-mac-of-the-agents-own.md) [2026-10-09Agents & policy19 threads**Ten hard questions for RiskMandate, answered: the mandate, the reach, the gap, and what we are deliberately not**Ten hard questions from a conference, answered in a two-hour interview: what RiskMandate does, what it deliberately is not, and how mature each part is.](riskmandate-ten-questions.md) [2026-10-09Agents & policy7 threads**How I work with Claude: one session per topic, agents with names, and memory you curate**A practical guide from a year of daily use: one Claude session per topic, named agents with a role.md, curated memory, vaults, and policy before connectors.](how-i-work-with-claude.md) [2026-10-08News & evidence2 threads**The waiting room knew first: a live local story, and the gap where local information used to be**Staff at two London hospitals said the IT was down; nothing a local could check showed it. A live local story about where local information comes from now.](the-waiting-room-knew-first.md) [2026-10-08Vaults & method9 threads**Encrypted memory for agents that run somewhere else: sgit deployment patterns, from a Mac mini to Kubernetes**Agents in isolated, ephemeral places need memory that outlives them. Five sgit deployment patterns, from a Mac mini to Kubernetes, with ciphertext-only servers.](encrypted-memory-for-isolated-agents.md) [2026-10-08Agents & policy8 threads**Knowing when to stop: what experience gives people, and what we have to design into agents**Knowing when to stop is the hard part for people and agents: what experience gives people, and the constraints that give agents the same perspective.](knowing-when-to-stop.md) [2026-10-08Agents & policy9 threads**Agency is not a yes: a scale for human and agent decisions, from rubber stamp to the reviewer who fixes the source**A yes or no is not agency: seven dimensions, a seven-level scale for people and agents, and the review as a QA step that fixes the source.](agency-is-not-a-yes.md) [2026-10-08Agents & policy9 threads**Hope or enforcement: one customer service agent, three designs, and who keeps each promise**One customer service agent built three ways, each with an Agent Behaviour Policy: how much of each policy is hope, and what one run can reach.](hope-or-enforcement.md) [2026-10-08Agents & policy4 threads**Who are you protecting against? Draw the security line where the attacker is, not above it**Before deciding how secure to be, name the attacker: a six-tier ladder, an air-gapped Mac mini read against it, and eight startups drawing their line.](who-are-you-protecting-against.md) [2026-10-08Agents & policy11 threads**Every mistake added a rule: complexity, agents, and the way back to shipping**When every agent mistake adds a rule, complexity wins: map the process, move each piece right as a small shipped component, and keep the rigour for the work.](every-mistake-added-a-rule.md) [2026-10-07News & evidence8 threads**Liquid content needs water: liquefy the journalist's notebook, not the finished product**A reply to FT Strategies on liquid content: the water is the reporting, so liquefy the journalist's notebook, keep the writing theirs, and pay per use.](liquid-content-needs-water.md) [2026-10-07News & evidence6 threads**The bridge, followed to the end: what one local story is worth when it is kept as a graph**A bridge closure simulated on a story vault: newsworthy on 5 days, needed on 57, used by three readers, four buyers and an agent, and paid back to its sources.](the-bridge-followed-to-the-end.md) [2026-10-07News & evidence5 threads**Story vault underneath, Reader Skills on top: why local journalism has the most to gain**Markus Franz's Reader Skills on top, the story vault underneath: each skill is a graph query, and local stories can pay back down their chain of sources.](story-vault-meets-reader-skills.md) [2026-10-07Agents & policy7 threads**Zoom into an agent's behaviour policy and you find the business logic**Below the first rules, an agent's behaviour policy is the business: functions, processes, clients, values. Layered, owned, counted, and where vendors plug in.](the-behaviour-policy-is-the-business-logic.md) [2026-10-07Agents & policy5 threads**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.](an-agent-desktop-by-the-minute.md) [2026-10-07Graphs & knowledge7 threads**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.](ai-baseline-control-framework.md) [2026-10-07Agents & policy13 threads**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.](where-is-the-why.md) [2026-10-06Agents & policy24 threads**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.](the-mandate-stack.md) [2026-10-06Agents & policy11 threads**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.](why-my-agents-do-not-run-on-my-laptop.md) [2026-10-06Startups & strategy6 threads**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.](the-deck-i-could-not-download.md) [2026-10-06Agents & policy24 threads**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-agent-team-as-it-runs.md) [2026-10-06Agents & policy14 threads**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.](a-personal-agent-that-keeps-your-secrets.md) [2026-10-05Agents & policy6 threads**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.](the-investigation-github-owes-its-customers.md) [2026-10-05Agents & policy8 threads**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.](send-an-agent-not-a-spreadsheet.md) [2026-10-05Graphs & knowledge10 threads**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.](how-much-of-this-did-i-write.md) [2026-10-05Graphs & knowledge11 threads**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.](if-somebody-built-a-company-on-code-review.md) [2026-10-05Agents & policy11 threads**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.](the-identity-we-wanted-to-give-the-agents.md) [2026-10-04Agents & policy8 threads**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.](the-wall-under-the-reply.md) [2026-10-03Graphs & knowledge15 threads**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.](memory-is-not-a-spectator-sport.md) [2026-10-03Graphs & knowledge13 threads**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.](code-review-as-a-fractal-semantic-graph.md) [2026-10-02Agents & policy13 threads**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.](replicating-the-agentic-inbox.md) [2026-10-02Startups & strategy5 threads**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.](price-it-then-give-it-away.md) [2026-10-02Agents & policy20 threads**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.](footprint-and-blast-radius.md) [2026-10-01Graphs & knowledge16 threads**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.](custom-uis-are-not-the-exception.md) [2026-09-30Agents & policy15 threads**The ultimate insider: agents, the infrastructure that cannot hold them, and risk management that cannot keep up**Agents, the infrastructure meant to contain them, and risk management run on spreadsheets are arriving at once, and together they are one scenario.](ultimate-insider-three-collisions.md) [2026-09-29News & evidence8 threads**The reader was always the product: a corrected history of how news got into this mess**News has sold the reader to advertisers since 1833; the web took the monopoly, the platforms made the reader measurable, and AI took the traffic.](how-news-got-here.md) [2026-09-29Agents & policy20 threads**Six agents, one inbox: what a real multi-agent setup taught me about access policies**An access policy for an agent is only as real as its worst row: every rule in a real six-agent setup, graded by how it is enforced today.](six-agents-one-inbox.md) [2026-09-28News & evidence8 threads**Sixteen thousand fetches, ten clicks, and a token bill nobody is sending: the case for paying publishers to be easy to read**AI answer engines pay to read the web as HTML; a publisher who serves markdown, dates, hashes and a typed graph saves them tokens and should get a share.](token-bill-nobody-is-sending.md) [2026-09-27Vaults & method5 threads**A supply chain of vaults: how GenAI, open data and small custom tools could bring the price of food down**The food chain is a data problem: one encrypted vault per party, joined by append lanes and a typed graph, could cut the waste that keeps prices high.](supply-chain-of-vaults.md) [2026-09-24Agents & policy16 threads**Every risk is already accepted. The only question is by whom, and for how long.**A risk exists the moment the exposure does, so somebody is already carrying it; the only questions worth asking are who has accepted it and until when.](every-risk-is-already-accepted.md) [2026-09-24Agents & policy12 threads**Before you give an agent a connector, give the connector a twin**An agent with a Gmail or Calendar connector can do things the platform cannot undo; a journal of every call, replayed, shows what it did and what can go back.](connector-twin-before-you-deploy-an-agent.md) [2026-09-22News & evidence7 threads**The future of news is the story vault, not the paywall**A story is a graph of claims and evidence and the article is one projection of it; keep the graph in a vault and sell what the article was made from.](future-of-news-story-vault-not-paywall.md) [2026-09-21Startups & strategy6 threads**For a startup, the most important question is whether they miss it**Ship something usable, give it away briefly, take it away and see whether anybody misses it; charge at a profit before you talk to investors.](the-question-is-whether-they-miss-it.md) [2026-09-21Startups & strategy3 threads**The SaaS apocalypse will be decided by inertia, not by AI**Incumbents and newcomers have the same AI; what separates them is how much past success each has to protect, so inertia decides which SaaS companies survive.](saas-apocalypse-decided-by-inertia-not-by-ai.md) [2026-09-20Graphs & knowledge20 threads**Fractal Semantic Graphs: everything connects to everything, and nobody has to share a schema**A fractal semantic graph has no privileged level and no single schema: each world keeps its own vocabulary and connects to others through named edges.](introducing-fractal-semantic-graphs.md) [2026-09-07Site & engineering1 thread**The proof moved up, the homepage after the rebuild, next to the before pictures**The rebuilt homepage puts four real vaults under one sentence, picks six by the job they do, and computes its numbers at build time from the site's own data.](proof-moved-up.md) [2026-09-07Site & engineering1 thread**The proof is two clicks behind the claim, what the homepage gets wrong, and the fix**The homepage leads with encryption, which cannot be seen, while twenty-five vaults a stranger can open in one click sit two clicks away in a table.](proof-behind-the-claim.md) [2026-08-27Site & engineering1 thread**A chat box on a site with no server, the plan, and the trade it makes**sgit.ai has no server, so its directory chat runs a local matcher by default, takes your own key as an opt-in, and leaves the vault bridge unbuilt.](chat-on-a-static-site.md) [2026-08-26Site & engineering2 threads**Twenty sites in fifteen days, and what that did to the writing**One site became twenty repositories in fifteen days because each argument needed its own version history, and the index now starts from a question.](nineteen-sites.md) [2026-08-25Vaults & method6 threads**Git for things you cannot put on GitHub**sgit is git for files you cannot put on GitHub: encrypted before they leave your machine, versioned like git, stored where the server cannot read a byte.](what-sgit-is.md) [2026-08-19Vaults & method2 threads**Seven vaults, one method**Publishing seven encrypted vaults in a fortnight produced a method, and every rule in it exists because something went wrong first.](seven-vaults-one-method.md) [2026-08-17Site & engineering2 threads**Green does not mean live**Two releases passed every check and never reached the site because the checks stopped at the git remote; a release now ends by asking the live site its version.](green-does-not-mean-live.md) Nothing matches. Clear the search or pick another topic. ## How they connect Read from the links the articles make to each other. [The same thing drawn as a map](graphs.md#map), and every article as its own graph. - [**How to run synthetic users on your own site**](how-to-run-synthetic-users.md) builds on [A link to a persona](a-link-to-a-persona.md). - [**A link to a persona**](a-link-to-a-persona.md) builds on [Pay to keep your persona](pay-to-keep-your-persona.md); continued by [How to run synthetic users on your own site](how-to-run-synthetic-users.md). - [**Pay after you read**](pay-after-you-read.md) builds on [Open source is not free](open-source-is-not-free.md), [Every mistake added a rule](every-mistake-added-a-rule.md), [Going live with the reading meter](going-live-with-the-reading-meter.md), [A meter in the browser](a-meter-in-the-browser.md), [Who will game the reading meter? Eight kinds of…](who-will-game-the-reading-meter.md), [Pay to keep your persona](pay-to-keep-your-persona.md). - [**Where the vault keys live**](where-the-vault-keys-live.md) builds on [RFC 0001](rfc-0001-public-key-cryptography-for-sgit.md), [The identity we wanted to give the agents](the-identity-we-wanted-to-give-the-agents.md), [Encrypted memory for agents that run somewhere else](encrypted-memory-for-isolated-agents.md), [A personal agent that keeps your secrets](a-personal-agent-that-keeps-your-secrets.md). - [**The infographic bake-off**](the-infographic-bake-off.md) builds on [Re-anchoring](re-anchoring-agent-behaviour-policies.md), [One article, five readers](one-article-five-readers.md). - [**Pay to keep your persona**](pay-to-keep-your-persona.md) builds on [Going live with the reading meter](going-live-with-the-reading-meter.md), [Who will game the reading meter? Eight kinds of…](who-will-game-the-reading-meter.md), [Git for things you cannot put on GitHub](what-sgit-is.md), [One article, five readers](one-article-five-readers.md); continued by [A link to a persona](a-link-to-a-persona.md), [Pay after you read](pay-after-you-read.md), [Going live with the reading meter](going-live-with-the-reading-meter.md). - [**Who will game the reading meter? Eight kinds of…**](who-will-game-the-reading-meter.md) builds on [Who are you protecting against? Draw the security…](who-are-you-protecting-against.md), [Going live with the reading meter](going-live-with-the-reading-meter.md), [Sixteen thousand fetches, ten clicks, and a token…](token-bill-nobody-is-sending.md); continued by [Pay after you read](pay-after-you-read.md), [Pay to keep your persona](pay-to-keep-your-persona.md), [Going live with the reading meter](going-live-with-the-reading-meter.md). - [**Going live with the reading meter**](going-live-with-the-reading-meter.md) builds on [A meter in the browser](a-meter-in-the-browser.md), [Pay to keep your persona](pay-to-keep-your-persona.md), [For a startup, the most important question is…](the-question-is-whether-they-miss-it.md), [The reader was always the product](how-news-got-here.md), [Price it, then give it away](price-it-then-give-it-away.md), [Who will game the reading meter? Eight kinds of…](who-will-game-the-reading-meter.md); continued by [Pay after you read](pay-after-you-read.md), [Pay to keep your persona](pay-to-keep-your-persona.md), [Who will game the reading meter? Eight kinds of…](who-will-game-the-reading-meter.md), [A meter in the browser](a-meter-in-the-browser.md). - [**Open source is not free**](open-source-is-not-free.md) builds on [A meter in the browser](a-meter-in-the-browser.md); continued by [Pay after you read](pay-after-you-read.md). - [**One article, five readers**](one-article-five-readers.md) builds on [Liquid content needs water](liquid-content-needs-water.md), [Zoom into an agent's behaviour policy and you find…](the-behaviour-policy-is-the-business-logic.md), [Every mistake added a rule](every-mistake-added-a-rule.md), [Hope or enforcement](hope-or-enforcement.md), [A second reader the agent cannot skip](a-second-reader-the-agent-cannot-skip.md), [Re-anchoring](re-anchoring-agent-behaviour-policies.md), [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md), [Footprint and blast radius](footprint-and-blast-radius.md), [The Mandate Stack](the-mandate-stack.md), [Every risk is already accepted](every-risk-is-already-accepted.md); continued by [The infographic bake-off](the-infographic-bake-off.md), [Pay to keep your persona](pay-to-keep-your-persona.md). - [**A meter in the browser**](a-meter-in-the-browser.md) builds on [Going live with the reading meter](going-live-with-the-reading-meter.md), [For a startup, the most important question is…](the-question-is-whether-they-miss-it.md), [Price it, then give it away](price-it-then-give-it-away.md), [The reader was always the product](how-news-got-here.md), [Sixteen thousand fetches, ten clicks, and a token…](token-bill-nobody-is-sending.md), [The bridge, followed to the end](the-bridge-followed-to-the-end.md); continued by [Pay after you read](pay-after-you-read.md), [Going live with the reading meter](going-live-with-the-reading-meter.md), [Open source is not free](open-source-is-not-free.md). - [**Re-anchoring**](re-anchoring-agent-behaviour-policies.md) builds on [A second reader the agent cannot skip](a-second-reader-the-agent-cannot-skip.md); continued by [The infographic bake-off](the-infographic-bake-off.md), [One article, five readers](one-article-five-readers.md). - [**A second reader the agent cannot skip**](a-second-reader-the-agent-cannot-skip.md) builds on [Hope or enforcement](hope-or-enforcement.md), [Every mistake added a rule](every-mistake-added-a-rule.md); continued by [One article, five readers](one-article-five-readers.md), [Re-anchoring](re-anchoring-agent-behaviour-policies.md). - [**The AI governance stack, as a graph**](the-ai-governance-stack-as-a-graph.md) builds on [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md), [Code review as a fractal semantic graph](code-review-as-a-fractal-semantic-graph.md). - [**RFC 0001**](rfc-0001-public-key-cryptography-for-sgit.md) builds on [Encrypted memory for agents that run somewhere else](encrypted-memory-for-isolated-agents.md); continued by [Where the vault keys live](where-the-vault-keys-live.md). - [**A Mac of the agent's own**](a-mac-of-the-agents-own.md) builds on [A locked-down desktop for an agent, by the minute…](an-agent-desktop-by-the-minute.md), [Why my agents do not run on my laptop](why-my-agents-do-not-run-on-my-laptop.md), [Six agents, one inbox](six-agents-one-inbox.md), [The agent team as it runs](the-agent-team-as-it-runs.md), [Encrypted memory for agents that run somewhere else](encrypted-memory-for-isolated-agents.md), [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [Hope or enforcement](hope-or-enforcement.md). - [**Ten hard questions for RiskMandate, answered**](riskmandate-ten-questions.md) builds on [Footprint and blast radius](footprint-and-blast-radius.md), [Hope or enforcement](hope-or-enforcement.md), [Zoom into an agent's behaviour policy and you find…](the-behaviour-policy-is-the-business-logic.md), [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md), [Before you give an agent a connector, give the…](connector-twin-before-you-deploy-an-agent.md), [The agent team as it runs](the-agent-team-as-it-runs.md), [Where is the why? A permission prompt asked me to…](where-is-the-why.md), [Agency is not a yes](agency-is-not-a-yes.md), [The ultimate insider](ultimate-insider-three-collisions.md), [The Mandate Stack](the-mandate-stack.md), [Six agents, one inbox](six-agents-one-inbox.md), [The identity we wanted to give the agents](the-identity-we-wanted-to-give-the-agents.md), [Git for things you cannot put on GitHub](what-sgit-is.md), [Encrypted memory for agents that run somewhere else](encrypted-memory-for-isolated-agents.md), [Every risk is already accepted](every-risk-is-already-accepted.md), [Code review as a fractal semantic graph](code-review-as-a-fractal-semantic-graph.md), [Knowing when to stop](knowing-when-to-stop.md), [The investigation GitHub owes its customers](the-investigation-github-owes-its-customers.md); continued by [A Mac of the agent's own](a-mac-of-the-agents-own.md). - [**How I work with Claude**](how-i-work-with-claude.md) builds on [Memory is not a spectator sport](memory-is-not-a-spectator-sport.md), [The agent team as it runs](the-agent-team-as-it-runs.md), [Replicating the agentic inbox](replicating-the-agentic-inbox.md), [Agency is not a yes](agency-is-not-a-yes.md), [Why my agents do not run on my laptop](why-my-agents-do-not-run-on-my-laptop.md), [Encrypted memory for agents that run somewhere else](encrypted-memory-for-isolated-agents.md), [Hope or enforcement](hope-or-enforcement.md). - [**The waiting room knew first**](the-waiting-room-knew-first.md) builds on [The bridge, followed to the end](the-bridge-followed-to-the-end.md), [Story vault underneath, Reader Skills on top](story-vault-meets-reader-skills.md). - [**Encrypted memory for agents that run somewhere else**](encrypted-memory-for-isolated-agents.md) builds on [Why my agents do not run on my laptop](why-my-agents-do-not-run-on-my-laptop.md), [A locked-down desktop for an agent, by the minute…](an-agent-desktop-by-the-minute.md), [Who are you protecting against? Draw the security…](who-are-you-protecting-against.md), [The agent team as it runs](the-agent-team-as-it-runs.md); continued by [Where the vault keys live](where-the-vault-keys-live.md), [RFC 0001](rfc-0001-public-key-cryptography-for-sgit.md), [A Mac of the agent's own](a-mac-of-the-agents-own.md), [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [How I work with Claude](how-i-work-with-claude.md). - [**Knowing when to stop**](knowing-when-to-stop.md) builds on [Agency is not a yes](agency-is-not-a-yes.md), [How much of this did I write? The numbers behind…](how-much-of-this-did-i-write.md), [Who are you protecting against? Draw the security…](who-are-you-protecting-against.md), [Every mistake added a rule](every-mistake-added-a-rule.md), [Hope or enforcement](hope-or-enforcement.md), [Memory is not a spectator sport](memory-is-not-a-spectator-sport.md), [The agent team as it runs](the-agent-team-as-it-runs.md); continued by [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md). - [**Agency is not a yes**](agency-is-not-a-yes.md) builds on [Where is the why? A permission prompt asked me to…](where-is-the-why.md), [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md), [Hope or enforcement](hope-or-enforcement.md), [How much of this did I write? The numbers behind…](how-much-of-this-did-i-write.md), [Every risk is already accepted](every-risk-is-already-accepted.md), [The agent team as it runs](the-agent-team-as-it-runs.md); continued by [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [How I work with Claude](how-i-work-with-claude.md), [Knowing when to stop](knowing-when-to-stop.md). - [**Hope or enforcement**](hope-or-enforcement.md) builds on [Zoom into an agent's behaviour policy and you find…](the-behaviour-policy-is-the-business-logic.md), [The agent team as it runs](the-agent-team-as-it-runs.md); continued by [One article, five readers](one-article-five-readers.md), [A second reader the agent cannot skip](a-second-reader-the-agent-cannot-skip.md), [A Mac of the agent's own](a-mac-of-the-agents-own.md), [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [How I work with Claude](how-i-work-with-claude.md), [Knowing when to stop](knowing-when-to-stop.md), [Agency is not a yes](agency-is-not-a-yes.md). - [**Who are you protecting against? Draw the security…**](who-are-you-protecting-against.md) builds on [Every risk is already accepted](every-risk-is-already-accepted.md); continued by [Who will game the reading meter? Eight kinds of…](who-will-game-the-reading-meter.md), [Encrypted memory for agents that run somewhere else](encrypted-memory-for-isolated-agents.md), [Knowing when to stop](knowing-when-to-stop.md). - [**Every mistake added a rule**](every-mistake-added-a-rule.md) builds on [The agent team as it runs](the-agent-team-as-it-runs.md), [Memory is not a spectator sport](memory-is-not-a-spectator-sport.md), [Git for things you cannot put on GitHub](what-sgit-is.md), [Every risk is already accepted](every-risk-is-already-accepted.md), [Footprint and blast radius](footprint-and-blast-radius.md), [The bridge, followed to the end](the-bridge-followed-to-the-end.md), [Green does not mean live](green-does-not-mean-live.md); continued by [Pay after you read](pay-after-you-read.md), [One article, five readers](one-article-five-readers.md), [A second reader the agent cannot skip](a-second-reader-the-agent-cannot-skip.md), [Knowing when to stop](knowing-when-to-stop.md). - [**Liquid content needs water**](liquid-content-needs-water.md) builds on [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md), [The future of news is the story vault, not the…](future-of-news-story-vault-not-paywall.md), [Custom UIs are not the exception](custom-uis-are-not-the-exception.md), [The bridge, followed to the end](the-bridge-followed-to-the-end.md), [How much of this did I write? The numbers behind…](how-much-of-this-did-i-write.md), [The reader was always the product](how-news-got-here.md), [Sixteen thousand fetches, ten clicks, and a token…](token-bill-nobody-is-sending.md); continued by [One article, five readers](one-article-five-readers.md). - [**The bridge, followed to the end**](the-bridge-followed-to-the-end.md) builds on [Story vault underneath, Reader Skills on top](story-vault-meets-reader-skills.md); continued by [A meter in the browser](a-meter-in-the-browser.md), [The waiting room knew first](the-waiting-room-knew-first.md), [Every mistake added a rule](every-mistake-added-a-rule.md), [Liquid content needs water](liquid-content-needs-water.md), [Story vault underneath, Reader Skills on top](story-vault-meets-reader-skills.md). - [**Story vault underneath, Reader Skills on top**](story-vault-meets-reader-skills.md) builds on [The future of news is the story vault, not the…](future-of-news-story-vault-not-paywall.md), [The reader was always the product](how-news-got-here.md), [The bridge, followed to the end](the-bridge-followed-to-the-end.md); continued by [The waiting room knew first](the-waiting-room-knew-first.md), [The bridge, followed to the end](the-bridge-followed-to-the-end.md). - [**Zoom into an agent's behaviour policy and you find…**](the-behaviour-policy-is-the-business-logic.md) builds on [Six agents, one inbox](six-agents-one-inbox.md), [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md), [Every risk is already accepted](every-risk-is-already-accepted.md), [An open AI governance framework, and what its…](ai-baseline-control-framework.md); continued by [One article, five readers](one-article-five-readers.md), [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [Hope or enforcement](hope-or-enforcement.md). - [**A locked-down desktop for an agent, by the minute…**](an-agent-desktop-by-the-minute.md) builds on [Why my agents do not run on my laptop](why-my-agents-do-not-run-on-my-laptop.md), [The Mandate Stack](the-mandate-stack.md), [Where is the why? A permission prompt asked me to…](where-is-the-why.md); continued by [A Mac of the agent's own](a-mac-of-the-agents-own.md), [Encrypted memory for agents that run somewhere else](encrypted-memory-for-isolated-agents.md). - [**An open AI governance framework, and what its…**](ai-baseline-control-framework.md) builds on [Six agents, one inbox](six-agents-one-inbox.md), [The identity we wanted to give the agents](the-identity-we-wanted-to-give-the-agents.md), [Where is the why? A permission prompt asked me to…](where-is-the-why.md), [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md), [Every risk is already accepted](every-risk-is-already-accepted.md), [Code review as a fractal semantic graph](code-review-as-a-fractal-semantic-graph.md); continued by [Zoom into an agent's behaviour policy and you find…](the-behaviour-policy-is-the-business-logic.md). - [**Where is the why? A permission prompt asked me to…**](where-is-the-why.md) builds on [Footprint and blast radius](footprint-and-blast-radius.md), [Every risk is already accepted](every-risk-is-already-accepted.md), [The Mandate Stack](the-mandate-stack.md), [Six agents, one inbox](six-agents-one-inbox.md), [Before you give an agent a connector, give the…](connector-twin-before-you-deploy-an-agent.md), [The ultimate insider](ultimate-insider-three-collisions.md), [Why my agents do not run on my laptop](why-my-agents-do-not-run-on-my-laptop.md), [The agent team as it runs](the-agent-team-as-it-runs.md), [A personal agent that keeps your secrets](a-personal-agent-that-keeps-your-secrets.md); continued by [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [Agency is not a yes](agency-is-not-a-yes.md), [A locked-down desktop for an agent, by the minute…](an-agent-desktop-by-the-minute.md), [An open AI governance framework, and what its…](ai-baseline-control-framework.md). - [**The Mandate Stack**](the-mandate-stack.md) builds on [The agent team as it runs](the-agent-team-as-it-runs.md), [Why my agents do not run on my laptop](why-my-agents-do-not-run-on-my-laptop.md), [Six agents, one inbox](six-agents-one-inbox.md), [Before you give an agent a connector, give the…](connector-twin-before-you-deploy-an-agent.md), [The identity we wanted to give the agents](the-identity-we-wanted-to-give-the-agents.md), [Git for things you cannot put on GitHub](what-sgit-is.md), [Replicating the agentic inbox](replicating-the-agentic-inbox.md), [Custom UIs are not the exception](custom-uis-are-not-the-exception.md), [Memory is not a spectator sport](memory-is-not-a-spectator-sport.md), [Seven vaults, one method](seven-vaults-one-method.md), [A supply chain of vaults](supply-chain-of-vaults.md), [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md), [If somebody built a company on code review](if-somebody-built-a-company-on-code-review.md), [Code review as a fractal semantic graph](code-review-as-a-fractal-semantic-graph.md), [Footprint and blast radius](footprint-and-blast-radius.md), [Every risk is already accepted](every-risk-is-already-accepted.md), [The ultimate insider](ultimate-insider-three-collisions.md), [How much of this did I write? The numbers behind…](how-much-of-this-did-i-write.md), [The wall under the reply](the-wall-under-the-reply.md), [Twenty sites in fifteen days, and what that did to…](nineteen-sites.md); continued by [One article, five readers](one-article-five-readers.md), [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [A locked-down desktop for an agent, by the minute…](an-agent-desktop-by-the-minute.md), [Where is the why? A permission prompt asked me to…](where-is-the-why.md). - [**Why my agents do not run on my laptop**](why-my-agents-do-not-run-on-my-laptop.md) builds on [Six agents, one inbox](six-agents-one-inbox.md), [The agent team as it runs](the-agent-team-as-it-runs.md), [Footprint and blast radius](footprint-and-blast-radius.md), [The ultimate insider](ultimate-insider-three-collisions.md), [A personal agent that keeps your secrets](a-personal-agent-that-keeps-your-secrets.md); continued by [A Mac of the agent's own](a-mac-of-the-agents-own.md), [How I work with Claude](how-i-work-with-claude.md), [Encrypted memory for agents that run somewhere else](encrypted-memory-for-isolated-agents.md), [A locked-down desktop for an agent, by the minute…](an-agent-desktop-by-the-minute.md), [Where is the why? A permission prompt asked me to…](where-is-the-why.md), [The Mandate Stack](the-mandate-stack.md). - [**The deck I could not download**](the-deck-i-could-not-download.md) builds on [The agent team as it runs](the-agent-team-as-it-runs.md), [A personal agent that keeps your secrets](a-personal-agent-that-keeps-your-secrets.md), [A supply chain of vaults](supply-chain-of-vaults.md), [The future of news is the story vault, not the…](future-of-news-story-vault-not-paywall.md), [The reader was always the product](how-news-got-here.md), [The SaaS apocalypse will be decided by inertia, not…](saas-apocalypse-decided-by-inertia-not-by-ai.md). - [**The agent team as it runs**](the-agent-team-as-it-runs.md) builds on [Replicating the agentic inbox](replicating-the-agentic-inbox.md), [Six agents, one inbox](six-agents-one-inbox.md), [A personal agent that keeps your secrets](a-personal-agent-that-keeps-your-secrets.md), [Footprint and blast radius](footprint-and-blast-radius.md), [Every risk is already accepted](every-risk-is-already-accepted.md), [Custom UIs are not the exception](custom-uis-are-not-the-exception.md), [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md), [Memory is not a spectator sport](memory-is-not-a-spectator-sport.md), [Before you give an agent a connector, give the…](connector-twin-before-you-deploy-an-agent.md), [The wall under the reply](the-wall-under-the-reply.md), [The identity we wanted to give the agents](the-identity-we-wanted-to-give-the-agents.md); continued by [A Mac of the agent's own](a-mac-of-the-agents-own.md), [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [How I work with Claude](how-i-work-with-claude.md), [Encrypted memory for agents that run somewhere else](encrypted-memory-for-isolated-agents.md), [Knowing when to stop](knowing-when-to-stop.md), [Agency is not a yes](agency-is-not-a-yes.md), [Hope or enforcement](hope-or-enforcement.md), [Every mistake added a rule](every-mistake-added-a-rule.md), [Where is the why? A permission prompt asked me to…](where-is-the-why.md), [The Mandate Stack](the-mandate-stack.md), [Why my agents do not run on my laptop](why-my-agents-do-not-run-on-my-laptop.md), [The deck I could not download](the-deck-i-could-not-download.md), [A personal agent that keeps your secrets](a-personal-agent-that-keeps-your-secrets.md). - [**A personal agent that keeps your secrets**](a-personal-agent-that-keeps-your-secrets.md) builds on [The agent team as it runs](the-agent-team-as-it-runs.md), [Footprint and blast radius](footprint-and-blast-radius.md), [The ultimate insider](ultimate-insider-three-collisions.md), [Git for things you cannot put on GitHub](what-sgit-is.md), [Six agents, one inbox](six-agents-one-inbox.md), [The identity we wanted to give the agents](the-identity-we-wanted-to-give-the-agents.md), [Memory is not a spectator sport](memory-is-not-a-spectator-sport.md), [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md), [Before you give an agent a connector, give the…](connector-twin-before-you-deploy-an-agent.md); continued by [Where the vault keys live](where-the-vault-keys-live.md), [Where is the why? A permission prompt asked me to…](where-is-the-why.md), [Why my agents do not run on my laptop](why-my-agents-do-not-run-on-my-laptop.md), [The deck I could not download](the-deck-i-could-not-download.md), [The agent team as it runs](the-agent-team-as-it-runs.md). - [**The investigation GitHub owes its customers**](the-investigation-github-owes-its-customers.md) builds on [Send an agent, not a spreadsheet](send-an-agent-not-a-spreadsheet.md), [Footprint and blast radius](footprint-and-blast-radius.md), [Green does not mean live](green-does-not-mean-live.md), [The ultimate insider](ultimate-insider-three-collisions.md), [Every risk is already accepted](every-risk-is-already-accepted.md); continued by [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md). - [**Send an agent, not a spreadsheet**](send-an-agent-not-a-spreadsheet.md) builds on [If somebody built a company on code review](if-somebody-built-a-company-on-code-review.md), [Footprint and blast radius](footprint-and-blast-radius.md), [Six agents, one inbox](six-agents-one-inbox.md), [Every risk is already accepted](every-risk-is-already-accepted.md), [Code review as a fractal semantic graph](code-review-as-a-fractal-semantic-graph.md), [Before you give an agent a connector, give the…](connector-twin-before-you-deploy-an-agent.md), [A supply chain of vaults](supply-chain-of-vaults.md); continued by [The investigation GitHub owes its customers](the-investigation-github-owes-its-customers.md). - [**How much of this did I write? The numbers behind…**](how-much-of-this-did-i-write.md) builds on [Memory is not a spectator sport](memory-is-not-a-spectator-sport.md), [If somebody built a company on code review](if-somebody-built-a-company-on-code-review.md), [Code review as a fractal semantic graph](code-review-as-a-fractal-semantic-graph.md), [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md), [Replicating the agentic inbox](replicating-the-agentic-inbox.md), [The wall under the reply](the-wall-under-the-reply.md); continued by [Knowing when to stop](knowing-when-to-stop.md), [Agency is not a yes](agency-is-not-a-yes.md), [Liquid content needs water](liquid-content-needs-water.md), [The Mandate Stack](the-mandate-stack.md). - [**If somebody built a company on code review**](if-somebody-built-a-company-on-code-review.md) builds on [Code review as a fractal semantic graph](code-review-as-a-fractal-semantic-graph.md), [Six agents, one inbox](six-agents-one-inbox.md), [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md), [The SaaS apocalypse will be decided by inertia, not…](saas-apocalypse-decided-by-inertia-not-by-ai.md), [Footprint and blast radius](footprint-and-blast-radius.md), [Before you give an agent a connector, give the…](connector-twin-before-you-deploy-an-agent.md), [For a startup, the most important question is…](the-question-is-whether-they-miss-it.md); continued by [The Mandate Stack](the-mandate-stack.md), [Send an agent, not a spreadsheet](send-an-agent-not-a-spreadsheet.md), [How much of this did I write? The numbers behind…](how-much-of-this-did-i-write.md), [Code review as a fractal semantic graph](code-review-as-a-fractal-semantic-graph.md). - [**The identity we wanted to give the agents**](the-identity-we-wanted-to-give-the-agents.md) builds on [The wall under the reply](the-wall-under-the-reply.md), [Six agents, one inbox](six-agents-one-inbox.md), [Replicating the agentic inbox](replicating-the-agentic-inbox.md), [Footprint and blast radius](footprint-and-blast-radius.md), [The ultimate insider](ultimate-insider-three-collisions.md); continued by [Where the vault keys live](where-the-vault-keys-live.md), [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [An open AI governance framework, and what its…](ai-baseline-control-framework.md), [The Mandate Stack](the-mandate-stack.md), [The agent team as it runs](the-agent-team-as-it-runs.md), [A personal agent that keeps your secrets](a-personal-agent-that-keeps-your-secrets.md). - [**The wall under the reply**](the-wall-under-the-reply.md) builds on [Custom UIs are not the exception](custom-uis-are-not-the-exception.md), [Replicating the agentic inbox](replicating-the-agentic-inbox.md), [Memory is not a spectator sport](memory-is-not-a-spectator-sport.md), [Six agents, one inbox](six-agents-one-inbox.md); continued by [The Mandate Stack](the-mandate-stack.md), [The agent team as it runs](the-agent-team-as-it-runs.md), [How much of this did I write? The numbers behind…](how-much-of-this-did-i-write.md), [The identity we wanted to give the agents](the-identity-we-wanted-to-give-the-agents.md). - [**Memory is not a spectator sport**](memory-is-not-a-spectator-sport.md) builds on [Sixteen thousand fetches, ten clicks, and a token…](token-bill-nobody-is-sending.md), [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md), [Replicating the agentic inbox](replicating-the-agentic-inbox.md), [Custom UIs are not the exception](custom-uis-are-not-the-exception.md), [Six agents, one inbox](six-agents-one-inbox.md), [Code review as a fractal semantic graph](code-review-as-a-fractal-semantic-graph.md), [Price it, then give it away](price-it-then-give-it-away.md); continued by [How I work with Claude](how-i-work-with-claude.md), [Knowing when to stop](knowing-when-to-stop.md), [Every mistake added a rule](every-mistake-added-a-rule.md), [The Mandate Stack](the-mandate-stack.md), [The agent team as it runs](the-agent-team-as-it-runs.md), [A personal agent that keeps your secrets](a-personal-agent-that-keeps-your-secrets.md), [How much of this did I write? The numbers behind…](how-much-of-this-did-i-write.md), [The wall under the reply](the-wall-under-the-reply.md). - [**Code review as a fractal semantic graph**](code-review-as-a-fractal-semantic-graph.md) builds on [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md), [Footprint and blast radius](footprint-and-blast-radius.md), [Custom UIs are not the exception](custom-uis-are-not-the-exception.md), [Every risk is already accepted](every-risk-is-already-accepted.md), [If somebody built a company on code review](if-somebody-built-a-company-on-code-review.md); continued by [The AI governance stack, as a graph](the-ai-governance-stack-as-a-graph.md), [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [An open AI governance framework, and what its…](ai-baseline-control-framework.md), [The Mandate Stack](the-mandate-stack.md), [Send an agent, not a spreadsheet](send-an-agent-not-a-spreadsheet.md), [How much of this did I write? The numbers behind…](how-much-of-this-did-i-write.md), [If somebody built a company on code review](if-somebody-built-a-company-on-code-review.md), [Memory is not a spectator sport](memory-is-not-a-spectator-sport.md). - [**Replicating the agentic inbox**](replicating-the-agentic-inbox.md) builds on [Six agents, one inbox](six-agents-one-inbox.md), [Custom UIs are not the exception](custom-uis-are-not-the-exception.md), [Footprint and blast radius](footprint-and-blast-radius.md), [Before you give an agent a connector, give the…](connector-twin-before-you-deploy-an-agent.md), [The ultimate insider](ultimate-insider-three-collisions.md); continued by [How I work with Claude](how-i-work-with-claude.md), [The Mandate Stack](the-mandate-stack.md), [The agent team as it runs](the-agent-team-as-it-runs.md), [How much of this did I write? The numbers behind…](how-much-of-this-did-i-write.md), [The identity we wanted to give the agents](the-identity-we-wanted-to-give-the-agents.md), [The wall under the reply](the-wall-under-the-reply.md), [Memory is not a spectator sport](memory-is-not-a-spectator-sport.md), [Six agents, one inbox](six-agents-one-inbox.md). - [**Price it, then give it away**](price-it-then-give-it-away.md) builds on [For a startup, the most important question is…](the-question-is-whether-they-miss-it.md); continued by [Going live with the reading meter](going-live-with-the-reading-meter.md), [A meter in the browser](a-meter-in-the-browser.md), [Memory is not a spectator sport](memory-is-not-a-spectator-sport.md), [For a startup, the most important question is…](the-question-is-whether-they-miss-it.md). - [**Footprint and blast radius**](footprint-and-blast-radius.md) builds on [The ultimate insider](ultimate-insider-three-collisions.md), [Before you give an agent a connector, give the…](connector-twin-before-you-deploy-an-agent.md), [Custom UIs are not the exception](custom-uis-are-not-the-exception.md), [Every risk is already accepted](every-risk-is-already-accepted.md), [Six agents, one inbox](six-agents-one-inbox.md); continued by [One article, five readers](one-article-five-readers.md), [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [Every mistake added a rule](every-mistake-added-a-rule.md), [Where is the why? A permission prompt asked me to…](where-is-the-why.md), [The Mandate Stack](the-mandate-stack.md), [Why my agents do not run on my laptop](why-my-agents-do-not-run-on-my-laptop.md), [The agent team as it runs](the-agent-team-as-it-runs.md), [A personal agent that keeps your secrets](a-personal-agent-that-keeps-your-secrets.md), [The investigation GitHub owes its customers](the-investigation-github-owes-its-customers.md), [Send an agent, not a spreadsheet](send-an-agent-not-a-spreadsheet.md), [If somebody built a company on code review](if-somebody-built-a-company-on-code-review.md), [The identity we wanted to give the agents](the-identity-we-wanted-to-give-the-agents.md), [Code review as a fractal semantic graph](code-review-as-a-fractal-semantic-graph.md), [Replicating the agentic inbox](replicating-the-agentic-inbox.md), [The ultimate insider](ultimate-insider-three-collisions.md). - [**Custom UIs are not the exception**](custom-uis-are-not-the-exception.md) builds on [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md), [Six agents, one inbox](six-agents-one-inbox.md), [The future of news is the story vault, not the…](future-of-news-story-vault-not-paywall.md), [Before you give an agent a connector, give the…](connector-twin-before-you-deploy-an-agent.md), [A chat box on a site with no server, the plan, and…](chat-on-a-static-site.md), [Seven vaults, one method](seven-vaults-one-method.md), [Sixteen thousand fetches, ten clicks, and a token…](token-bill-nobody-is-sending.md), [The ultimate insider](ultimate-insider-three-collisions.md); continued by [Liquid content needs water](liquid-content-needs-water.md), [The Mandate Stack](the-mandate-stack.md), [The agent team as it runs](the-agent-team-as-it-runs.md), [The wall under the reply](the-wall-under-the-reply.md), [Memory is not a spectator sport](memory-is-not-a-spectator-sport.md), [Code review as a fractal semantic graph](code-review-as-a-fractal-semantic-graph.md), [Replicating the agentic inbox](replicating-the-agentic-inbox.md), [Footprint and blast radius](footprint-and-blast-radius.md). - [**The ultimate insider**](ultimate-insider-three-collisions.md) builds on [Every risk is already accepted](every-risk-is-already-accepted.md), [Footprint and blast radius](footprint-and-blast-radius.md), [Six agents, one inbox](six-agents-one-inbox.md), [Before you give an agent a connector, give the…](connector-twin-before-you-deploy-an-agent.md), [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md); continued by [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [Where is the why? A permission prompt asked me to…](where-is-the-why.md), [The Mandate Stack](the-mandate-stack.md), [Why my agents do not run on my laptop](why-my-agents-do-not-run-on-my-laptop.md), [A personal agent that keeps your secrets](a-personal-agent-that-keeps-your-secrets.md), [The investigation GitHub owes its customers](the-investigation-github-owes-its-customers.md), [The identity we wanted to give the agents](the-identity-we-wanted-to-give-the-agents.md), [Replicating the agentic inbox](replicating-the-agentic-inbox.md), [Footprint and blast radius](footprint-and-blast-radius.md), [Custom UIs are not the exception](custom-uis-are-not-the-exception.md). - [**The reader was always the product**](how-news-got-here.md) builds on [The future of news is the story vault, not the…](future-of-news-story-vault-not-paywall.md), [Sixteen thousand fetches, ten clicks, and a token…](token-bill-nobody-is-sending.md), [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md); continued by [Going live with the reading meter](going-live-with-the-reading-meter.md), [A meter in the browser](a-meter-in-the-browser.md), [Liquid content needs water](liquid-content-needs-water.md), [Story vault underneath, Reader Skills on top](story-vault-meets-reader-skills.md), [The deck I could not download](the-deck-i-could-not-download.md). - [**Six agents, one inbox**](six-agents-one-inbox.md) builds on [Before you give an agent a connector, give the…](connector-twin-before-you-deploy-an-agent.md), [Replicating the agentic inbox](replicating-the-agentic-inbox.md); continued by [A Mac of the agent's own](a-mac-of-the-agents-own.md), [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [Zoom into an agent's behaviour policy and you find…](the-behaviour-policy-is-the-business-logic.md), [An open AI governance framework, and what its…](ai-baseline-control-framework.md), [Where is the why? A permission prompt asked me to…](where-is-the-why.md), [The Mandate Stack](the-mandate-stack.md), [Why my agents do not run on my laptop](why-my-agents-do-not-run-on-my-laptop.md), [The agent team as it runs](the-agent-team-as-it-runs.md), [A personal agent that keeps your secrets](a-personal-agent-that-keeps-your-secrets.md), [Send an agent, not a spreadsheet](send-an-agent-not-a-spreadsheet.md), [If somebody built a company on code review](if-somebody-built-a-company-on-code-review.md), [The identity we wanted to give the agents](the-identity-we-wanted-to-give-the-agents.md), [The wall under the reply](the-wall-under-the-reply.md), [Memory is not a spectator sport](memory-is-not-a-spectator-sport.md), [Replicating the agentic inbox](replicating-the-agentic-inbox.md), [Footprint and blast radius](footprint-and-blast-radius.md), [Custom UIs are not the exception](custom-uis-are-not-the-exception.md), [The ultimate insider](ultimate-insider-three-collisions.md). - [**Sixteen thousand fetches, ten clicks, and a token…**](token-bill-nobody-is-sending.md) builds on [The future of news is the story vault, not the…](future-of-news-story-vault-not-paywall.md), [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md); continued by [Who will game the reading meter? Eight kinds of…](who-will-game-the-reading-meter.md), [A meter in the browser](a-meter-in-the-browser.md), [Liquid content needs water](liquid-content-needs-water.md), [Memory is not a spectator sport](memory-is-not-a-spectator-sport.md), [Custom UIs are not the exception](custom-uis-are-not-the-exception.md), [The reader was always the product](how-news-got-here.md). - [**A supply chain of vaults**](supply-chain-of-vaults.md) builds on [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md), [The SaaS apocalypse will be decided by inertia, not…](saas-apocalypse-decided-by-inertia-not-by-ai.md); continued by [The Mandate Stack](the-mandate-stack.md), [The deck I could not download](the-deck-i-could-not-download.md), [Send an agent, not a spreadsheet](send-an-agent-not-a-spreadsheet.md). - [**Every risk is already accepted**](every-risk-is-already-accepted.md) builds on [Fractal Semantic Graphs](introducing-fractal-semantic-graphs.md); continued by [One article, five readers](one-article-five-readers.md), [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [Agency is not a yes](agency-is-not-a-yes.md), [Who are you protecting against? Draw the security…](who-are-you-protecting-against.md), [Every mistake added a rule](every-mistake-added-a-rule.md), [Zoom into an agent's behaviour policy and you find…](the-behaviour-policy-is-the-business-logic.md), [An open AI governance framework, and what its…](ai-baseline-control-framework.md), [Where is the why? A permission prompt asked me to…](where-is-the-why.md), [The Mandate Stack](the-mandate-stack.md), [The agent team as it runs](the-agent-team-as-it-runs.md), [The investigation GitHub owes its customers](the-investigation-github-owes-its-customers.md), [Send an agent, not a spreadsheet](send-an-agent-not-a-spreadsheet.md), [Code review as a fractal semantic graph](code-review-as-a-fractal-semantic-graph.md), [Footprint and blast radius](footprint-and-blast-radius.md), [The ultimate insider](ultimate-insider-three-collisions.md). - [**Before you give an agent a connector, give the…**](connector-twin-before-you-deploy-an-agent.md) continued by [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [Where is the why? A permission prompt asked me to…](where-is-the-why.md), [The Mandate Stack](the-mandate-stack.md), [The agent team as it runs](the-agent-team-as-it-runs.md), [A personal agent that keeps your secrets](a-personal-agent-that-keeps-your-secrets.md), [Send an agent, not a spreadsheet](send-an-agent-not-a-spreadsheet.md), [If somebody built a company on code review](if-somebody-built-a-company-on-code-review.md), [Replicating the agentic inbox](replicating-the-agentic-inbox.md), [Footprint and blast radius](footprint-and-blast-radius.md), [Custom UIs are not the exception](custom-uis-are-not-the-exception.md), [The ultimate insider](ultimate-insider-three-collisions.md), [Six agents, one inbox](six-agents-one-inbox.md). - [**The future of news is the story vault, not the…**](future-of-news-story-vault-not-paywall.md) builds on [For a startup, the most important question is…](the-question-is-whether-they-miss-it.md); continued by [Liquid content needs water](liquid-content-needs-water.md), [Story vault underneath, Reader Skills on top](story-vault-meets-reader-skills.md), [The deck I could not download](the-deck-i-could-not-download.md), [Custom UIs are not the exception](custom-uis-are-not-the-exception.md), [The reader was always the product](how-news-got-here.md), [Sixteen thousand fetches, ten clicks, and a token…](token-bill-nobody-is-sending.md). - [**For a startup, the most important question is…**](the-question-is-whether-they-miss-it.md) builds on [Price it, then give it away](price-it-then-give-it-away.md); continued by [Going live with the reading meter](going-live-with-the-reading-meter.md), [A meter in the browser](a-meter-in-the-browser.md), [If somebody built a company on code review](if-somebody-built-a-company-on-code-review.md), [Price it, then give it away](price-it-then-give-it-away.md), [The future of news is the story vault, not the…](future-of-news-story-vault-not-paywall.md). - [**The SaaS apocalypse will be decided by inertia, not…**](saas-apocalypse-decided-by-inertia-not-by-ai.md) continued by [The deck I could not download](the-deck-i-could-not-download.md), [If somebody built a company on code review](if-somebody-built-a-company-on-code-review.md), [A supply chain of vaults](supply-chain-of-vaults.md). - [**Fractal Semantic Graphs**](introducing-fractal-semantic-graphs.md) continued by [One article, five readers](one-article-five-readers.md), [The AI governance stack, as a graph](the-ai-governance-stack-as-a-graph.md), [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [Agency is not a yes](agency-is-not-a-yes.md), [Liquid content needs water](liquid-content-needs-water.md), [Zoom into an agent's behaviour policy and you find…](the-behaviour-policy-is-the-business-logic.md), [An open AI governance framework, and what its…](ai-baseline-control-framework.md), [The Mandate Stack](the-mandate-stack.md), [The agent team as it runs](the-agent-team-as-it-runs.md), [A personal agent that keeps your secrets](a-personal-agent-that-keeps-your-secrets.md), [How much of this did I write? The numbers behind…](how-much-of-this-did-i-write.md), [If somebody built a company on code review](if-somebody-built-a-company-on-code-review.md), [Memory is not a spectator sport](memory-is-not-a-spectator-sport.md), [Code review as a fractal semantic graph](code-review-as-a-fractal-semantic-graph.md), [Custom UIs are not the exception](custom-uis-are-not-the-exception.md), [The ultimate insider](ultimate-insider-three-collisions.md), [The reader was always the product](how-news-got-here.md), [Sixteen thousand fetches, ten clicks, and a token…](token-bill-nobody-is-sending.md), [A supply chain of vaults](supply-chain-of-vaults.md), [Every risk is already accepted](every-risk-is-already-accepted.md). - [**The proof moved up, the homepage after the rebuild…**](proof-moved-up.md) builds on [The proof is two clicks behind the claim, what the…](proof-behind-the-claim.md). - [**The proof is two clicks behind the claim, what the…**](proof-behind-the-claim.md) continued by [The proof moved up, the homepage after the rebuild…](proof-moved-up.md). - [**A chat box on a site with no server, the plan, and…**](chat-on-a-static-site.md) continued by [Custom UIs are not the exception](custom-uis-are-not-the-exception.md). - [**Twenty sites in fifteen days, and what that did to…**](nineteen-sites.md) builds on [Git for things you cannot put on GitHub](what-sgit-is.md); continued by [The Mandate Stack](the-mandate-stack.md). - [**Git for things you cannot put on GitHub**](what-sgit-is.md) continued by [Pay to keep your persona](pay-to-keep-your-persona.md), [Ten hard questions for RiskMandate, answered](riskmandate-ten-questions.md), [Every mistake added a rule](every-mistake-added-a-rule.md), [The Mandate Stack](the-mandate-stack.md), [A personal agent that keeps your secrets](a-personal-agent-that-keeps-your-secrets.md), [Twenty sites in fifteen days, and what that did to…](nineteen-sites.md). - [**Seven vaults, one method**](seven-vaults-one-method.md) continued by [The Mandate Stack](the-mandate-stack.md), [Custom UIs are not the exception](custom-uis-are-not-the-exception.md). - [**Green does not mean live**](green-does-not-mean-live.md) continued by [Every mistake added a rule](every-mistake-added-a-rule.md), [The investigation GitHub owes its customers](the-investigation-github-owes-its-customers.md). **Two rules keep these from going stale.** An article never restates a fact it does not own, it links to the page that does, so when the fact changes the article does not start lying. And an article that makes a testable claim links to the test, the same way [the comparison pages](https://sgit.ai/compare/index.md) do. --- *[Site index for agents](../llms.txt) · [HTML version](https://newsroom.sgit.ai/articles/index.html)*