# Inbound lead research and qualification agent

Every inbound form fill gets a deep-research pass on the person and company, a structured qualification verdict, and a drafted reply. A human approves in Slack with one click before anything is sent.

**Why it matters:** Vercel had 10 people triaging website leads. Their top performer said the research step was the part they never wanted to do again. After the agent, one person handles that work and the other nine moved to more complex sales work.

- Trigger: Website contact / demo form
- Tools: Vercel AI SDK, Next.js, Slack, Salesforce, HubSpot, OpenAI, Exa
- Time saved (rough estimate): 10–25 hours/week
- Typical agency build cost (rough estimate): $8k–$25k

## Steps
1. Research agent: company site, news, LinkedIn, funding
2. Qualify with a fixed schema (generateObject)
3. Draft personalised follow-up email
4. Slack card: approve / edit / reject
5. On approval: send email, write CRM

## Pitfalls
- Shadow your best SDR first and copy their actual checklist into the research prompt; generic prompts give generic research.
- Keep the qualification output a strict schema, not prose, so routing rules stay deterministic.
- Log every rejection reason from the Slack step and feed it back into the prompt monthly.

## Sources
- [Vercel: what we learned building agents at Vercel](https://vercel.com/blog/what-we-learned-building-agents-at-vercel)
- [Vercel Labs: open-source lead-agent template (GitHub)](https://github.com/vercel-labs/lead-agent)

---
Source: https://cofounderbase.com/workflows/lead-research-qualification-agent/?utm_source=md&utm_medium=ai · Cofounderbase, a directory of agencies that build AI internal tools and automations. Data comes from each agency's own website and official partner directories; rankings are not sold.
