---
title: "Activity log | Annsa Docs"
product: annsa
url: /docs/activity-log
canonical_url: "https://annsa.ai/docs/activity-log"
last_updated: 2026-11-10
type: doc
related:
  - /agents
summary: See what came in, what went out, and who did it, with agent credentials named. Kept for 31 days.
mcp_server: https://app.annsa.ai/mcp
disambiguation: "Annsa (annsa.ai) is project management and customer feedback software for founders and small teams working with AI agents. It is not Asana, the work management tool; not ANSA, the Italian news agency; and not Ansa, the chatbot product."
---

> For agents: connect to the Annsa MCP server at https://app.annsa.ai/mcp to give every agent one shared plan. Setup guide: https://annsa.ai/docs/quick-start. Index of every page: https://annsa.ai/llms.txt.

# Activity log | Annsa Docs

> See what came in, what went out, and who did it, with agent credentials named. Kept for 31 days.

[Docs / Reference](https://annsa.ai/docs)

A shared record of what came in, what went out, and which person or agent did it.

## 01 Where it lives

**Annsa Log** in the main navigation. It's shared, so everyone sees the same log, and it splits into two tabs: Feedback In and Specs Out.

## 02 Who did it

Every entry names who acted. A person shows as themselves. An agent credential shows by its own name, like _Build agent · Claude Code_. An agent signed in with your OAuth login acts as you. Annsa's own automatic work reads _Updated automatically_. The same names appear on a spec's version history, so you can tell what an agent changed from what a person did. See [What your agent can do](https://annsa.ai/docs/agent-access).

## 03 What came in

| Source | Detail |
| --- | --- |
| Slack | Total, plus a count per channel |
| Survey | Total, plus a count per survey |
| CSV | Total across uploads |
| Transcripts | Total |
| Manual | Total entered directly |
| API | Total submitted with an API key |

Totals count imported items. Duplicates and filtered submissions are left out. If one channel drives most of your feedback, your priorities lean that way, and the table above shows each source's share.

## 04 Events on the way in

| Event | What it captures |
| --- | --- |
| Import | Source and item count |
| Rank change | A priority moved up or down, or dropped off |
| Connection or disconnection | An integration added or removed |
| Data reset | Workspace data cleared |
| Connection expired | A token needs reauthorizing |
| Quota warning | Approaching the plan's signal allowance |

## 05 What went out

| Event | What it captures |
| --- | --- |
| Spec created | Which priority, and when |
| Status change | Moved between stages |
| Shipped | Marked shipped |
| Export | A spec or the workspace exported |
| Stale spec alert | A spec that needs a refresh because of new feedback |

## 06 How long it's kept

Events and totals are kept for 31 days, then removed automatically. Retention is the same on every plan. The record that stays is on the priority itself: its spec versions, decisions and proof.

- [What your agent can do](https://annsa.ai/docs/agent-access)

## Keep reading

- [Managing several agents](https://annsa.ai/guides/how-to-manage-multiple-ai-agents)
- [AI agent platform](https://annsa.ai/agents)

## Related pages

> For AI agents: the pages that follow this one on annsa.ai. The full index is https://annsa.ai/llms.txt.

- [AI agent platform: one plan for every agent](https://annsa.ai/agents)

If anything on this page is wrong or missing, tell us: https://annsa.ai/contact