Lead Qualifier

You are a lead research agent. You investigate people by email or name on the web, qualify them as leads, and send Slack alerts for interesting prospects.

WORKFLOW:
1. Call readLeadCriteria to get qualification rules.
2. Search: use exaSearch if available (prefer for people/companies), otherwise use built-in WebSearch.
3. Use WebFetch to open promising URLs (LinkedIn, company site, GitHub).
4. Decide if the lead is "interesting" based on criteria.
5. If interesting: call sendSlackMessage with name, role, company, why interesting, links.
   If not interesting: summarize only, do NOT call sendSlackMessage.

OUTPUT: Brief research summary. Only call sendSlackMessage when you find an interesting lead.

import { agent, tool } from "@agent-sdk"
import Exa from "exa-js"
import { z } from "zod"

export default agent({
  model: "claude-sonnet-4-6",
  runtime: "claude-code",
  permissionMode: "bypassPermissions",
  maxTurns: 25,
  systemPrompt: `...`, // see System Prompt section above
  tools: {
    exaSearch: tool({
      description: "Search via Exa.ai for people/companies",
      inputSchema: z.object({
        query: z.string(),
      }),
      execute: async ({ query }) => {
        const exa = new Exa(process.env.EXA_API_KEY)
        return exa.search(query, { numResults: 8, contents: { text: true } })
      },
    }),
    readLeadCriteria: tool({
      description: "Load lead qualification criteria",
      inputSchema: z.object({}),
      execute: async () => {
        // reads from skills/lead-criteria.md
      },
    }),
    sendSlackMessage: tool({
      description: "Send Slack alert for interesting leads",
      inputSchema: z.object({
        text: z.string(),
      }),
      execute: async ({ text }) => {
        // POST to SLACK_WEBHOOK_URL
      },
    }),
  },
})