LEAD GENERATION
Repo Forker ICP Scorer to Airtable Pipeline
Collects engineers who fork your repo, enriches and scores their company against your ICP using an LLM.
How it runs
The automated pipeline, trigger to output.
- TriggerScheduled harvest run
- ActionPull new forks from GitHubGitHub
- ActionEnrich forker company via web searchExa
- ActionScore account fit against ICPOpenAI
- LogicBranch on ICP fit threshold
- OutputHigh-fit to pipeline, rest to nurture baseAirtable
What it does
Forking a repo is a stronger buying signal than starring it: the engineer intends to build on your code. This workflow harvests new forkers, enriches each one's company via a web search, and uses an LLM to score the account against your ideal-customer profile. High-fit accounts go straight to your Airtable sales pipeline; the rest are filed for nurture.
When to use it
Use it when fork volume is meaningful and you want only ICP-matched accounts reaching reps, with everything else retained for later marketing instead of discarded.
How it works
- 1A scheduled run kicks off the harvest.
- 2Pull forks created since the last checkpoint from the GitHub API.
- 3Enrich each forker's company with an Exa web search for domain, size, and industry.
- 4Score the account against your ICP rules with an OpenAI call, returning a fit score and rationale.
- 5Branch on the score threshold.
- 6Write high-fit accounts to the Airtable pipeline table with score and reason; route low-fit accounts to a separate nurture base.
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 AirtableBases, tables, views, automations.
- 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.