GTM Email Sequencer — personalized cold email + Instantly push
One ready-to-sequence lead at a time, picked from your workspace DB, dressed in the right variant for its context signals, written, stored, and pushed straight into Instantly. Runs every 5 minutes, never double-sends.
The outcomes on their scorecard
The agent picks the right variant by signals on the lead row (role + company size by default) and fills [Name], [company], and your context token from the row — not a generic title fallback.
Processes exactly one lead per 5-minute tick. Every run is monitorable end-to-end; failures are obvious from the JSON summary in the session log.
The agent flips a lead to `in_progress` before any work happens. Two concurrent runs can never both grab the same row.
Writes the finalized email back to the lead row and pushes the lead into your Instantly campaign with the subject, body, and follow-up as custom variables.
How the work gets done
Cold outbound goes cold the moment it gets templatey. This agent gives every ready-to-sequence lead its own contextually-chosen email — the variant is picked by signals on the lead row (role + company size, title + tenure, trigger type — whatever you've enriched), placeholders are filled from the row, and the result is written back plus pushed into your Instantly campaign for sending. The agent processes exactly one lead per run on a 5-minute cron, which keeps runs deterministic and trivial to monitor in the session log. An `in_progress` claim is taken before any work so two concurrent runs can never send the same lead twice. The blueprint is general — works for hiring outreach, sales outbound, partner outreach, fundraising, anywhere you have a verified-lead → personalized-email flow. Pair with the LinkedIn / X engager scraper + qualifier blueprints to fill the leads table upstream.
Outbound goes cold the moment it gets templatey. This agent gives every ready-to-sequence lead its own contextually-chosen email — the variant is picked by signals on the lead row (role + company size, trigger type, whatever you've enriched), and placeholders are filled from the row, not a generic fallback. Then it pushes straight to Instantly. One lead per run, every 5 minutes, never re-touches a row.
Your new teammate
GTM Email Sequencer
Scheduled agent that pulls one ready-to-sequence lead at a time from the workspace DB, writes a personalized cold email using one of several contextual variants (chosen by signals on the lead row — role + company size by default), stores the draft on the lead row, and pushes the lead into Instantly for sending. Runs every 5 minutes, never double-sends.
What it runs on
This hire is assembled from the public toolkit. Every piece below is a tool your own agents can call too.
How setup works
- 01
Claim the hire
One click. No questionnaire. The brief is already written from your business, and you can edit it before you build if you want to.
- 02
Your hire deploys itself
Agents, tools, schedules, memory, hand-off queues and the database schema are provisioned into your workspace automatically, then the first real run fires while you watch.
- 03
Hand it the keys it still needs
You land in chat with your hire and its findings. 1 setup tasks — connecting your outreach tools, picking where it reports — are done conversationally, whenever you want.
Other hires that pair well
X (Twitter) profile qualifier and enricher
Hand any X username to this agent and get back a qualified, ICP-scored lead with a verified email and a resolved LinkedIn profile.
LinkedIn profile qualifier and enricher
Hand any LinkedIn profile URL to this agent and get back a qualified, ICP-scored lead with a verified email and a website summary attached.
Email Finder Waterfall — verified email from any combination of identifiers
Give it a name + a domain (or a LinkedIn URL, or any combo of identifiers) — it returns a verified professional email or a structured failure. Three-step waterfall: agntdata orchestrator → Exa deep search → verifier. Stateless primitive, called by other agents.
Every hire is assembled from the same toolkit.
Same data sources, same database, same memory, schedules and queues. Point your own agent at the MCP endpoint and wire it your way instead.