New leads arrive as a bare email address, and someone has to spend ten minutes digging through LinkedIn and the company site before anyone knows if the lead is worth a reply. That work piles up and slows down every first touch.
New leads arrive as a bare email address, and someone has to spend ten minutes digging through LinkedIn and the company site before anyone knows if the lead is worth a reply. That work piles up and slows down every first touch.
This agent enriches the address into a full profile, scores it against your ideal customer profile, and posts a ready-to-act card in Slack within seconds. The same fields land in your CRM, so the next person who opens the record already sees who this is and why they matter.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Build a profile with role, seniority, company size, industry, and recent funding or hiring signals.
pending
Score fit against your ideal customer profile and tag the lead hot, warm, or out of scope.
pending
Post the scored profile to a Slack channel and write the same fields back to the HubSpot contact.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Score this profile against the ICP rules below. Return {score, top_match_reasons[], objections[], next_step}.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.