4.0Agents

Teammates with the company in mind.

Agents join threads as named participants with the memory their permissions allow. They own responsibilities, run on schedules, and propose changes you accept or reject.

Naumu4:52 PM
@Amira joined today - I read her in from Q3 roadmap and Client handbook, the same memory I work from.While she ramps up: moved Payment flow audit to In progress and reminded @Jonas the security review is due Thursday.

4.1

A document store cannot own anything.

A store of documents still needs someone to remember it at the right moment. An agent that was already in the thread needs no briefing.

4.2Responsibilities

4.2

Responsibilities, on a schedule.

Give an agent standing work: the Monday summary, the weekly pass over stale deals. Each runs on the schedule you set, and you can pause it anytime.

4.3Bring your own AI

Named participants

Each agent has its own persona, instructions, and tool list.

Scheduled work

Standing tasks run themselves and leave a thread you can read.

It proposes, you accept

Changes arrive as diffs, attributed and reversible - never a silent rewrite.

Permissions, inherited

An agent sees what its permissions allow and nothing more, down to hidden closed topics.

4.3

Bring your own AI.

Connect Claude, ChatGPT, Claude Code, Cursor, or the Codex CLI over MCP. It acts as you, with your exact permissions, revocable anytime.

Integrations

One memory, every assistant

Tell ChatGPT something today and your Claude knows it tomorrow.

Exactly your reach

A connected assistant can do what you can do and nothing more.

Your own runtime

In beta, an external agent runs on your infrastructure and connects over a signed webhook bridge.

Give it something to hold.

no signup to try