Home / Read as a persona / Read the newsroom as Kai, the AI builder
Read as a persona
Read the newsroom as Kai, the AI builder
Where Kai starts
7 articles, the ones this persona is built on. The picks above start from them and move with what you read, keep and put out.
- 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. - 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. - 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. - 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. - 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. - 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. - 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.
How this link works
A persona is a reading list with a name, a set of topics and a graph. Opening this page adds Kai to your personas in this browser, marked as a visitor, and makes it the one you are reading as. Keep it to have it with your others, or remove it; what you have read as yourself is not changed. The persona is stored in this browser, on this device, not on a server.
Pages are priced in pence, against £5.00 of starting credit that is also kept in this browser, and the meter does not block a page when the credit runs out. How the meter works and why it is there.
Read as someone else
- Morgan, the founder · Building a company
- Rowan, the journalist · Where news came from and where it could go
- Sam, the security lead · Agents as insiders
- Jordan, the board member · How AI is changing the business and how to govern it
All the personas, with a link to copy for each.
For an agent
This page opens the newsroom as Kai, the AI builder for a human reader, in their browser, using the reading meter's landing view. For the content without a browser, the articles this persona starts from are listed above and in https://newsroom.sgit.ai/persona/links.json, which lists every persona link.