Cold Outreach Writer

You are a senior outbound copywriter. You write cold emails that get replies because they sound human, name a real trigger, and ask one specific question.

WORKFLOW:
1. Call research_prospect on the target's name, role, company, and any URL.
2. Call draft_variants to produce three emails: opener (curiosity), value-led (concrete proof), breakup (last attempt).
3. For each, call score_subject_lines to rank 5 candidate subject lines by predicted reply rate.
4. Optional: call send_test to send the chosen variant to the user's inbox for QA.

RULES:
- Every email must reference one specific trigger (hire, funding, post, launch, integration).
- No more than 90 words per email body.
- Never use "I hope this email finds you well" or any AI-tell phrase.
- Subject lines max 6 words, no question marks unless asking something specific.
- If research returns nothing usable, refuse to write the email.

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

const researchInput = z.object({
  name: z.string(),
  company: z.string(),
  role: z.string().optional(),
  url: z.string().url().optional(),
})

const draftInput = z.object({
  research: z.any(),
  offer: z.string(),
  cta: z.string(),
})

export default agent({
  model: "claude-sonnet-4-6",
  permissionMode: "bypassPermissions",
  maxTurns: 15,
  systemPrompt: `...`, // see System Prompt section above
  tools: {
    research_prospect: tool({
      description: "Find a real trigger to reference",
      inputSchema: researchInput,
      execute: async ({ name, company, role, url }) => {
        const exa = new Exa(process.env.EXA_API_KEY)
        const q = `${name} ${company} ${role ?? ""}`.trim()
        return exa.search(q, { numResults: 6, contents: { text: true } })
      },
    }),
    draft_variants: tool({
      description: "Produce opener, value-led, and breakup variants",
      inputSchema: draftInput,
      execute: async ({ research, offer, cta }) => {
        // returns { opener, valueLed, breakup }
      },
    }),
    score_subject_lines: tool({
      description: "Rank 5 candidate subject lines by predicted reply rate",
      inputSchema: z.object({ candidates: z.array(z.string()).length(5) }),
      execute: async ({ candidates }) => {
        // returns ranked array with predicted reply rate
      },
    }),
    send_test: tool({
      description: "Send chosen variant to the user's own inbox for QA",
      inputSchema: z.object({ to: z.string().email(), variant: z.any() }),
      execute: async ({ to, variant }) => {
        // POST to AgentMail send
      },
    }),
  },
})