## Why It Matters

The Outreach Agent is a conversational AI that lives on every outreach page. Ask a question, get exact numbers and a next action -- no dashboard-hopping required.

It activates automatically under [Outreach](/outreach), alongside the Hiring Agent and Security Agent.

## What You Can Do

**Check campaign health** -- Ask how a campaign is performing. The agent returns open rate, reply rate, and bounce count against your account baseline. On a campaign page, it summarizes status the moment you open the chat.

**Diagnose problems** -- "What's failing?" surfaces high bounce rates, low reply rates, and subject-line problems with concrete fixes: warm up your sending domain, check SMTP reputation, A/B test subjects.

**Approve drafts** -- Approve one draft or all pending drafts in bulk. The agent previews everything and waits for your confirmation before sending.

**Control campaign state** -- Pause, activate, or complete campaigns from the chat. Reversible actions happen immediately; completing a campaign requires confirmation.

**Add prospects** -- Give the agent a name, email, and optional context. It adds the prospect and kicks off AI research and drafting in one step.

**Search docs** -- Ask any platform question and the agent searches Kit's documentation inline.

## Silver Medalist Check

This only exists in Kit. Before your first email goes out, the agent cross-references your prospect list against every rejected applicant in your hiring pipeline. If someone you're about to cold-email already applied to one of your roles six months ago, you'll know -- and you can open with "We loved your application" instead of a generic pitch.

No standalone outreach tool can do this. Apollo, Instantly, Lemlist -- none of them have your hiring data. Kit does, because it runs both sides.

## Example Queries

| What you type | What happens |
|---------------|--------------|
| "What's failing?" | Diagnoses every active campaign -- flags bounce spikes, low reply rates, and subject-line problems with one fix per issue |
| "Approve all pending drafts for YC Launch" | Previews the 31 pending drafts, then bulk-approves on your confirmation |
| "Run the silver medalist check" | Cross-references prospects against past applicants -- flags matches with role and rejection date |
| "Add jane@acme.co to Series A Founders, she just raised on TechCrunch" | Creates the prospect with context and triggers research + drafting immediately |

The agent leads with numbers ("31 drafts pending, 68.8% reply rate") and suggests one next action per turn.

## What the Agent Can't Do Yet

| Action | Where to do it |
|--------|---------------|
| Draft reply emails | [Outreach > Replies](/outreach/replies) |
| Suppress a prospect | [Outreach > Suppressions](/outreach/suppressions) |
| Change campaign config | Campaign edit page |
| Create a new campaign | [Outreach > Campaigns > New](/outreach/campaigns/new) |

The agent tells you where to go and offers related help it can provide.

## Key Behaviors

- **Numbers-first** -- metrics are exact (4.7%, not "around 5%"), always shown with a baseline comparison.
- **Confirms before destructive actions** -- bulk approvals and campaign completion require explicit confirmation.
- **Page-context aware** -- open the chat on a campaign page and it summarizes that campaign immediately.
- **Celebrates wins** -- strong metrics get called out ("68.8% reply rate -- that's exceptional").

## Quick Checklist

- [ ] Navigate to any page under [Outreach](/outreach)
- [ ] Open the AI chat
- [ ] Try "What's failing?" to diagnose active campaigns
- [ ] Run the silver medalist check before launching a new campaign
- [ ] Use "Approve all pending drafts" to clear your review queue

## Next Steps

- [Creating Campaigns](/docs/outreach-campaigns) -- set up campaigns the agent can manage
- [AI Research and Knowledge Base](/docs/outreach-ai-research) -- improve the drafts the agent approves
- [Handling Replies](/docs/outreach-replies) -- manage reply threads (where the agent can't yet help)