Product
AI Agent
The agent answers questions about your brand using your data, by calling the same read paths the dashboards use. It is not a general chatbot with your logo on it — every claim it makes traces back to a tool call you can see.
Where to find it
- The AI Agent page — full width, with a rail of past conversations you can rename or delete.
- In place, anywhere in the app — press
⌘J(Ctrl-Jon Windows and Linux) to open it as a panel without losing the view you are on.
What it can read
The read tools are exactly the surfaces you already have, reachable in conversation instead of by navigation:
| Tool | What it fetches |
|---|---|
get_visibility_ranking | The visibility leaderboard — you against your competitor set. |
get_visibility_timeseries | Visibility over time. |
get_change_events | What changed, and when. |
get_mentions | Individual brand mentions in model answers. |
get_sources | The URLs the models cited. |
get_sentiment | How you are being talked about. |
get_knowledge_base | Your own brand profile, tone, entities and documents. |
get_site_health | Site health and AEO score. |
get_onpage_issues | The on-page issue backlog. |
get_prompt_performance | How individual prompts are performing. |
get_traffic_summary | Search traffic from your connected providers. |
fetch_web_page | A page on the open web, when you ask it to look at one. |
The tool ledger
As the agent works, each call appears as a plain-English line — Pulled the visibility leaderboard, Read sentiment — with the raw tool name beside it in monospace. You can see what it looked at before you decide whether to believe the answer.
Actions are proposed, never silently performed
Six tools write rather than read: draft_content, create_llms_txt, fix_issue, activate_prompts, add_competitor and publish_content. These never appear as a completed ledger line. They render as a confirmation card showing precisely what will happen, and nothing is written until you accept it.