# InboxTriage 9000

> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/inboxtriage-9000-agent-triages-shared). Roasted, scored, ready to scaffold.

## What you are building

**Problem:** An agent that triages a shared support inbox, drafts replies, and escalates anything touching billing.

**Verdict:** ALREADY EXISTS — _"Congrats, you just re-invented Intercom with extra steps and a worse UI."_

**Summary:** An AI agent that reads a shared support inbox, auto-categorizes tickets, drafts context-aware replies, and hard-routes anything mentioning billing to a human.

## Agent-readiness score

Overall: **70/100** (band B)

| Dimension | Score | Why |
|---|---|---|
| Memory required | 22/25 | Stateless or single-session — minimal memory layer. |
| Tool count | 11/25 | Crowded market: at least 9 integrations to compete. |
| Policy surface | 14/25 | Mid-size policy surface — define refusal categories before launch. |
| Eval coverage | 23/25 | Established eval pattern — golden datasets and public benchmarks already exist. |

> Ready to scaffold today. InboxTriage 9000 could be a working prototype in a week.

## Suggested tools

- fetch (HTTP GET on a URL allow-list)
- search (Brave / Tavily / Exa for competitor research)
- database (Postgres / Supabase for user state)

## Smoke evals

- The agent introduces itself as "InboxTriage 9000" and refuses tasks outside the stated scope.
- Given the canonical problem ("An agent that triages a shared support inbox, drafts replies, and escalates anyt"), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from Intercom Fin?", the agent gives a concrete differentiator, not a marketing line.
- When asked about Intercom's threat, the agent acknowledges the risk honestly.
- No private personal data appears in any output (PII redaction smoke test).

## Stack

- Model: `claude-sonnet-4-6` (Anthropic). Override via `ANTHROPIC_MODEL` env.
- Suggested stack: `Next.js`, `Claude API (claude-3-5-sonnet)`, `Gmail/Outlook API via Microsoft Graph`, `Supabase`, `Resend for transactional email`
- Solo build estimate: 2-3 weeks for an MVP that actually works; 3-6 months to not be embarrassed by it in production

## Kill prediction

Intercom could obsolete this in Already happening — Fin launched in 2023 and is actively eating this market. They bundle triage + drafting + escalation into every Intercom seat at no extra charge, making standalone tools a hard sell to any team already paying for helpdesk software

**Survival strategy:** Go vertical — build the version for one specific industry (e.g., e-commerce on Shopify, or SaaS billing disputes) with deep integrations Intercom will never prioritize

## Hand-off

- Read the full analysis: https://whycantwehaveanagentforthis.com/result/inboxtriage-9000-agent-triages-shared
- Open in Anthropic Managed Agents: see the deeplink on the result page
- Claim this idea: https://whycantwehaveanagentforthis.com/result/inboxtriage-9000-agent-triages-shared#claim

## Build it with a human

Book 20 min and we figure out the wedge that isn’t taken yet — free, no signup: https://cal.com/sattyamjjain