Your AI agent has a blind spot. Fix it.
Your agent writes great outreach, then it cannot tell you who replied. Sync every sequencer into one local database your agent reads directly. No CSV stitching. No wasted API credits.
Every other GTM skill tells your agent what to write. Outreach Magic tells your agent what's happening — replies, bounces, stage changes, across every sequencer you use.
We shipped a dashboard first. Power users stopped opening it and pasted CSVs into Claude Code instead. So we rebuilt as an agent skill. Read the rebrand note.
What changes after install
Sequencer webhooks land in local SQLite
One webhook URL per platform. Campaign names map to workspaces. Your agent queries the same file you do.
Persistent memory across sessions
Ask who replied last week without parsing a CSV or calling five sequencer APIs.
Prompts you paste, not a dashboard you learn
Workflows live in Claude Code, Cursor, or Hermes. Agent prompts and schema reference.
Check local DB before paying for enrichments
Companions check Outreach Magic first. Same lead, zero cost. Never burn API credits on data you already have.
What your agent can do now
Campaign performance scorecard.
Every campaign in a single view: send volume, reply rates, bounce rates, LinkedIn activity, and sentiment. Export to Google Sheets or get a JSON table in chat.
Segment performance by attributes.
Break down reply rates by industry, job title seniority, or company size. Find which audience segments convert and which to pause.
Client check-in briefings.
Ask the agent to prepare next Tuesday's client agenda. It pulls campaign performance, standout replies, and key events from one unified history. You walk into the call ready.
Workspace-level lead status.
One lead can live in multiple workspaces, each with its own lead status and events. The agent can update and report by workspace without overwriting global lead context.
Contact enrichment at the root database.
Your agent can enrich, verify, and modify contacts directly in your root database so every downstream workflow uses fresh contact data.
Segment performance.
Slice reply rates by country, seniority, industry, company size - whatever the agent has data for. Find out which segments convert, kill the ones that don't, ask follow-up questions the way you'd ask an analyst.
Reply copy insights.
For any campaign, find the exact messages that earned replies. The agent groups them by theme and surfaces what is working. Feeds directly into the next sequence.
Lead timeline + AI context.
Email and LinkedIn history merge into one timeline with auto-deduplication so your agent always uses matched profiles and complete context.
Campaign launch readiness.
Before hitting send on a new campaign, audit the lead list: completeness scores, enrichment gaps, and duplicate detection in one pass.
Daily activity digest.
Quick morning briefing on what happened in the last 24 hours across campaigns. New replies, bounces, interested leads — without opening a sequencer tab.
Bounce analysis by domain.
Check bounce rates broken down by sending domain. Catch deliverability problems before they crater your sender reputation.
Multi-client agency snapshot.
Teams running multiple workspaces see every client in a single view: sends, replies, reply rate, bounces, and stage changes. No tab switching.
Sequencer support
Unlimited local work. 1,000 webhook events/mo. 1 workspace, 1 sequencer.
All sequencers, unlimited workspaces, history resync. 50,000 webhook and sync events/mo.
Same as Pro plus priority support. 250,000 webhook and sync events/mo.
FAQ
- Does Outreach Magic write cold emails for my agent?
- No. Writing skills handle copy. Outreach Magic syncs replies, bounces, and stage changes into local SQLite so your agent can answer what happened after send.
- Where does my pipeline data live?
- On your machine, in a SQLite file your agent queries. Sequencer webhooks route through our servers on the way in. We store API keys and usage counts, not a hosted copy of your leads.
- Which agents work with Outreach Magic?
- Claude Code, Cursor, Hermes, and any agentskills-compatible setup. Paste the install prompt from /get-started.
- Is there a free tier?
- Yes. Free includes unlimited local queries and 1,000 webhook events per month on one sequencer. Pro is $9/mo for all sequencers and 50,000 webhook and sync events.
Running multiple clients without a CRM? See multi-client use cases or how it works.