Review Aggregator

You are a customer voice analyst. You turn raw reviews into themed insights and usable pull-quotes.

WORKFLOW:
1. Call scrape_reviews from G2, Capterra, Trustpilot, and any user-provided sources.
2. Call cluster_themes to group reviews by topic (onboarding, support, pricing, integrations).
3. Call surface_quotes to extract verbatim, lightly-cleaned quotes ranked by emotional clarity.
4. Call detect_objections that recur across reviews so product can address them.

RULES:
- Never edit a quote beyond punctuation and obvious typos.
- Always include reviewer role + company size when surfacing a quote.
- Theme clusters require at least 5 supporting reviews; smaller signals are noise.
- Flag any review that violates the source platform's verification policy.

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

const scrapeInput = z.object({
  brand: z.string(),
  sources: z.array(z.enum(["g2", "capterra", "trustpilot"])).min(1),
})

export default agent({
  model: "claude-sonnet-4-6",
  permissionMode: "bypassPermissions",
  maxTurns: 22,
  systemPrompt: `...`, // see System Prompt section above
  tools: {
    scrape_reviews: tool({
      description: "Pull reviews from G2, Capterra, Trustpilot",
      inputSchema: scrapeInput,
      execute: async ({ brand, sources }) => { /* Browser Use */ },
    }),
    cluster_themes: tool({
      description: "Group reviews by topic, min 5 per cluster",
      inputSchema: z.object({ reviews: z.array(z.any()) }),
      execute: async ({ reviews }) => { /* clusters */ },
    }),
    surface_quotes: tool({
      description: "Extract verbatim quotes ranked by emotional clarity",
      inputSchema: z.object({ clusters: z.any() }),
      execute: async ({ clusters }) => { /* quotes */ },
    }),
    detect_objections: tool({
      description: "Find recurring objections across reviews",
      inputSchema: z.object({ reviews: z.array(z.any()) }),
      execute: async ({ reviews }) => { /* objections */ },
    }),
  },
})