CASE 06
6 weeks
AI Sales Research Agent for B2B
Replaced three hours a day of manual prospect research with a structured agent.
- TypeScript
- Node
- LangGraph
- OpenAI
- HubSpot API
THE PROBLEM
SDRs were spending the first half of every day on prospect research — web, LinkedIn, public filings, prior touches in CRM — before they could write a single email.
WHAT WE DID
- 01
Multi-tool agent over web search, LinkedIn scraping, and HubSpot history.
- 02
Strict structured output: the agent returns a typed dossier (company summary, ICP fit score, recent triggers, talking points) that writes directly back to HubSpot.
- 03
Guardrails on cost and rate limits; any run over budget escalates to a cheaper model path.
- 04
Browser extension that lets SDRs kick off a run on any LinkedIn profile.
OUTCOME
SDRs work roughly five times the prospects per day. Email reply rates improved because the opens are actually tailored.