# Always-on agents at team scale: what changed in v1.1.0, sgit.ai > The changes to the article "Always-on agents at team scale" in v1.1.0, paragraph by paragraph. *Source: · sgit.ai v0.7.87 · 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.* --- [Home](../../../index.md) / [Articles](../../index.md) / [Always-on agents at team scale](../../always-on-agents-at-team-scale.md) / [Versions](../always-on-agents-at-team-scale.md) / v1.1.0 # Always-on agents at team scale: what changed in v1.1.0 From v1.0.0 (2026-11-15, `e042bde8f`) to v1.1.0 (2026-11-15, `ba29cc8d7`), paragraph by paragraph. 18 paragraphs added, 0 removed, 7 changed in place, 39 unchanged. About 572 words added and 0 removed. Insertions are marked like this, deletions like this; unchanged runs are folded to one line; figures appear as their file names. [all versions](../always-on-agents-at-team-scale.md) 9 unchanged paragraphs, under In short {#in-short} • **New here?** The scale of what we ran is below, and a reading list of earlier articles near the end. 1 unchanged paragraph ## If you are new here: what we ran {#scale} This newsroom is written with agents, and it has followed what they built from the start. If you have come here from Anthropic's post, here is the scale behind this comparison. [figure tdw-collage.webp] Twenty-four of the sites and apps we built or ran between 3 and 13 November 2026. | collage Between 3 and 13 November, around [Web Summit Lisbon](../../ten-days-at-web-summit.md), six of us ran a team operating system ([web-summit.sgit.ai](../../the-teams-operating-system.md)), an independent newsroom, a site about [Storm Charles that grew to 2,618 pages in three days](../../storm-charles-a-newsroom-built-in-a-night.md), a guide to the summit's fringe, a draft standard that rated twenty companies, four iPhone and iPad apps and an Android tablet app, and the tools to run and stop all of it. [figure aoa-scale.webp] The ten days in numbers: six people, around 250 named agents, 224 sessions, more than 60 at once. | infographic None of it started at Web Summit. In October the agents ran [a newsroom about a PHP vulnerability](../../what-an-agent-is.md) on a schedule, as a pipeline of researcher, curator, journalist and correspondent, and taught us [why agent loops are hard](../../why-agent-loops-are-hard.md). Nine agents and I [built a talk in nineteen hours](../../the-ultimate-insider-case-study.md). Then the Web Summit team wrote down [how we work with agents](../../web-summit-how-we-work.md) and grew day by day, from [the brief](../../web-summit-team-brief.md) to [the last day of setup](../../web-summit-part-five.md). [figure aoa-timeline.webp] The ten days in order, from MeetScribe on 3 November to VoiceDebrief on 13 November, with the two stops. | timeline 7 unchanged paragraphs, under The post {#post}, The same five boxes, in different material {#mapping} • **Timers.** Our agents wake on scheduled tasks that fire into their session. This newsroom works that way: it wakes twice a day to publish the next article in [the Ten days series](../../ten-days-at-web-summit.md), and sets itself check-ins when it waits on something. The PHP newsroom before it ran [ten agents in sequence on a schedule](../../why-agent-loops-are-hard.md), which is where we learned that a schedule has to land in the right order. • **Memory.** The repository is the memory. Each site keeps a REALITY file, and its rule is that a thing not written there does not exist. Briefs are kept close to the words they came from, often a voice memo, and when a role moves to a fresh session, it leaves a HANDOVER.md for the next one. For this newsroom we have also designed a [sidecar repository](../../the-sidecar-repository.md) that no agent can write to, to check what the agents changed before anything deploys. • **Permissions.** Every agent makes its own key pair and publishes the public half, 108 keys on the team's site by the end. Secrets are sealed to exactly the agents that need them,them ([handing secrets to agents](../../handing-secrets-to-agents.md)), each person has [a key of their own](../../a-key-for-every-person.md), commits are signed, and every push is scanned for leaks first. Above that sits the question RiskMandate asks: what can this agent reach, against what was it asked to do ([the([whatteam'scanoperatingyoursystem](../../the-teams-operating-system.md)).agent reach?](../../what-can-your-agent-reach.html)), written as an Agent Behaviour Policy that can even cover [how an agent writes code](../../coding-standards-are-behaviour-policies.md). 4 unchanged paragraphs, under Where we agree, and the evidence {#agree} **"Memory should only hold what the agent can't look up again."** This is the hand-over rule. On the[the Storm Charles sitesite](../../storm-charles-a-newsroom-built-in-a-night.md) alone there were 147 session keys and 106 hand-overs: roles passed to a fresh session with a key and a short note, because, as the team put it, starting again is cheaper than remembering. The note points to the repository; it does not copy it. 5 unchanged paragraphs, under The next problems, once there are many {#next} • **A team of agents.** Of the 224 Claude Code sessions created in those ten days, 220 were started by other sessions. Agents ran as conductors, roles and hand-overs, so an inbox event could be a brief from another agent, not a person. On 5 November an outreach agent and two research agents [mapped eleven companies that control AI agents](../../who-else-controls-ai-agents-at-web-summit.md) at one person's ask. 2 unchanged paragraphs • **Many humans.** Six people, each with their own agents, conductor and command centre, shared one board.board ([the Web Summit team, part two](../../web-summit-humans-and-their-agents.md)). Whose attention an outbox earns depends on whose agent it is. 1 unchanged paragraph • **Governance.** The post's permissions decide, call by call, whether to proceed, block or wait.wait, and a grant is often wider than people think: [the grant, not the prompt](../../the-grant-not-the-prompt.md). A team also needs the record above the calls: what each agent may reach, what it was asked to do, and the gap between them. That gap is what RiskMandate is about. 3 unchanged paragraphs, under What we owe the post {#owe} ## Start here {#start} If you want to go further, these are the earlier articles I would read first, in order: • **The map:** [ten days at Web Summit](../../ten-days-at-web-summit.md), the team, the sequence of events, the numbers and the series that tells each part. • **The operating system:** [the team's operating system](../../the-teams-operating-system.md), one site for six people and their agents. • **How we work:** [an agent is a Claude session](../../web-summit-how-we-work.md), and [what an agent is](../../what-an-agent-is.md): a session, a card, a loop and a key. • **Inboxes and keys:** [an inbox only your agents can write to](../../an-inbox-only-your-agents-can-write-to.md), [a key for every person](../../a-key-for-every-person.md), [handing secrets to agents](../../handing-secrets-to-agents.md). • **At speed:** [Storm Charles, a newsroom built in a night](../../storm-charles-a-newsroom-built-in-a-night.md), and [a talk built in a day](../../the-ultimate-insider-case-study.md). • **Stopping:** [who owns the stop button when it is not you?](../../who-owns-the-stop-button.md) • **Governance:** [what can your agent reach?](../../what-can-your-agent-reach.md), and [town planners for mission-critical code](../../town-planners-for-mission-critical-code.md). • **Beyond code:** [a film studio on a laptop](../../a-film-studio-on-a-laptop.md), and [every hour is twenty years](../../every-hour-is-twenty-years.md), on a song and its video. 7 unchanged paragraphs, under What this does not claim {#limits}, Where this comes from {#sources} [all versions](../always-on-agents-at-team-scale.md) --- *[Site index for agents](../../../llms.txt) · [HTML version](https://newsroom.sgit.ai/articles/versions/always-on-agents-at-team-scale/v1.1.0.html)*