LEAD GENERATION
Draft a personalized outreach email for each qualified stargazer
For high-fit stargazers, research their work and write a tailored cold email referencing their actual repos and stack, then save it as a Gmail draft for a rep to review and send.
How it runs
The automated pipeline, trigger to output.
- TriggerGitHub star event on repoGitHub
- ActionPull stargazer repos, languages, activityGitHub
- ActionResearch company hook via ExaExa
- ActionCompose personalized emailOpenAI
- LogicSkip if no email or below fit bar
- OutputSave Gmail draft for rep reviewGmail
What it does
Generates a ready-to-edit, personalized outreach email for each qualified stargazer. It reads the person's public repos, languages, and recent activity, researches their company, and drafts an email that references something specific about them — no generic templates. The draft lands in Gmail for human review before sending.
When to use it
You want personalized outreach at volume but refuse to send fully automated cold emails. This keeps a human in the loop while removing the research-and-write grind that makes reps skip personalization.
How it works
- 1A GitHub webhook fires when someone stars your repo.
- 2The flow pulls the stargazer's pinned repos, primary languages, and recent commits.
- 3Exa researches the company for a relevant hook (product, recent news, hiring).
- 4An agent step composes a personalized email that cites a concrete detail from their work.
- 5A logic gate skips anyone missing a resolvable email or below the fit bar.
- 6The finished email is saved as a Gmail draft, assigned to the right rep.
Set it up
What you configure once, before turning it on.
- 1Connect GitHubRepos, issues, pull requests, actions.
- 2Connect ExaNeural search across the web.
- 3Connect OpenAIModels, embeddings, files.
- 4Connect GmailRead, draft, send, label.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Lead Generation workflows
Instantly triage uploaded badge CSVs and notify the SDR lead
Accepts a badge-scan CSV via webhook, validates and dedupes it on the spot, checks each attendee against HubSpot.
Score Zoom webinar poll answers into a tiered outreach queue
When a Zoom webinar ends, pull each attendee's poll responses, compute an intent score, and write a tiered (Hot/Warm/Cold) outreach queue to Airtable for the sales team to work.
Classify open-text webinar poll answers with AI and enrich the lead record
For webinars that use free-text poll questions, an AI step reads each attendee's written answers, classifies intent and pain points into structured fields.
Fast-track hot webinar leads into HubSpot and ping the rep on Slack
After a webinar, identify attendees whose poll answers signal high purchase intent, create or update their HubSpot contact with a lead score.
Agent-driven Brave intent harvest with enrichment and Gmail draft outreach
A CEO-driven agent harvests intent signals from Brave, enriches each prospect via web research, writes a personalized cold email.
Manual Brave keyword sweep into an Airtable research board
On demand, sweeps a topic across Brave Search, clusters the results by buying stage with an LLM, and writes a deduplicated research board to Airtable with company, source URL.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.