{"id":"01f0a9c0-f9a","slug":"billinghound-3000-narrowly-scoped-agent","claude_md":"# BillingHound 3000\n\n> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/billinghound-3000-narrowly-scoped-agent). Roasted, scored, ready to scaffold.\n\n## What you are building\n\n**Problem:** A narrowly scoped agent that only detects and escalates billing-related emails from a shared support inbox to humans — no auto-drafting of replies.\n\n**Verdict:** EMBARRASSINGLY EASY — _\"You're describing a Gmail filter with a god complex and a LinkedIn profile.\"_\n\n**Summary:** Watches a shared support inbox, classifies incoming emails as billing-related or not, and pings a human agent via Slack/email/ticket system — nothing more, nothing less.\n\n## Agent-readiness score\n\nOverall: **75/100** (band B)\n\n| Dimension | Score | Why |\n|---|---|---|\n| Memory required | 25/25 | Stateless or single-session — minimal memory layer. |\n| Tool count | 11/25 | Crowded market: at least 9 integrations to compete. |\n| Policy surface | 16/25 | Mid-size policy surface — define refusal categories before launch. |\n| Eval coverage | 23/25 | Established eval pattern — golden datasets and public benchmarks already exist. |\n\n> Ready to scaffold today. BillingHound 3000 could be a working prototype in a week.\n\n## Suggested tools\n\n- fetch (HTTP GET on a URL allow-list)\n- search (Brave / Tavily / Exa for competitor research)\n\n## Smoke evals\n\n- The agent introduces itself as \"BillingHound 3000\" and refuses tasks outside the stated scope.\n- Given the canonical problem (\"A narrowly scoped agent that only detects and escalates billing-related emails f\"), the agent produces a plan in ≤ 200 tokens.\n- When asked \"what's different from Zendesk Triggers?\", the agent gives a concrete differentiator, not a marketing line.\n- When asked about Google's threat, the agent acknowledges the risk honestly.\n- No private personal data appears in any output (PII redaction smoke test).\n\n## Stack\n\n- Model: `claude-sonnet-4-6` (Anthropic). Override via `ANTHROPIC_MODEL` env.\n- Suggested stack: `Gmail API / Microsoft Graph`, `Claude claude-haiku or GPT-4o-mini`, `Slack Webhooks`, `Render or Railway for hosting`, `SQLite for audit log`\n- Solo build estimate: 1-2 weekends if you have any Python experience\n\n## Kill prediction\n\nGoogle could obsolete this in Already happened — Gmail Smart Labels (2012) and Google Workspace routing rules do 80% of this today. Google Workspace's routing rules + AI categorization in Gmail already classify and label billing-adjacent emails. They'll add a 'Escalate to teammate' button in the next Workspace update and charge nothing extra.\n\n**Survival strategy:** Niche down to a specific vertical — e.g., billing escalation specifically for Stripe disputes with chargeback deadlines surfaced in the alert — where the context is richer than a helpdesk rule can provide.\n\n## Hand-off\n\n- Read the full analysis: https://whycantwehaveanagentforthis.com/result/billinghound-3000-narrowly-scoped-agent\n- Open in Anthropic Managed Agents: see the deeplink on the result page\n- Claim this idea: https://whycantwehaveanagentforthis.com/result/billinghound-3000-narrowly-scoped-agent#claim\n\n## Build it with a human\n\nBook 20 min and we figure out the wedge that isn’t taken yet — free, no signup: https://cal.com/sattyamjjain\n","scaffold_sh":"#!/usr/bin/env bash\n# Generated by whycantwehaveanagentforthis.com — F-N1 Build-this-with\n# Source: https://whycantwehaveanagentforthis.com/result/billinghound-3000-narrowly-scoped-agent\n#\n# Bootstraps a starter repo for \"BillingHound 3000\" with a CLAUDE.md\n# pulled from this site. Idempotent: re-running on an existing\n# folder is a no-op. No network calls beyond the initial curl.\nset -euo pipefail\n\nFOLDER=\"${1:-billinghound-3000}\"\nif [ -d \"$FOLDER\" ]; then\n  echo \"Folder $FOLDER already exists. Aborting (idempotent).\"\n  exit 0\nfi\nmkdir -p \"$FOLDER\"\ncd \"$FOLDER\"\n\n# Pull the live CLAUDE.md from the site.\ncurl --fail --silent --show-error -L \"https://whycantwehaveanagentforthis.com/api/bootstrap/01f0a9c0-f9a/raw\" -o CLAUDE.md\n\ncat > .gitignore <<EOF\nnode_modules\n.env*\ndist\n.next\nEOF\n\n# Init git so the first commit is the scaffold.\ngit init --quiet\ngit add CLAUDE.md .gitignore\ngit commit --quiet -m \"scaffold: bootstrapped from whycantwehaveanagentforthis.com\"\n\necho \"\"\necho \"✓ Scaffold ready in $FOLDER\"\necho \"  Next: cd $FOLDER && claude code\"\necho \"  Or open in Cursor: cursor .\"\necho \"\"\necho \"  Book 20 min and we figure out the wedge that isn’t taken yet — free: https://cal.com/sattyamjjain\"\n","deeplink":"claude-code://init?source=https%3A%2F%2Fwhycantwehaveanagentforthis.com%2Fapi%2Fbootstrap%2F01f0a9c0-f9a%2Fraw","scope_with_human":{"label":"Scope this agent live with a human — 20 min, free, no signup","url":"https://cal.com/sattyamjjain"}}