# InboxTriage 9000

> https://whycantwehaveanagentforthis.com/result/inboxtriage-9000-agent-triages-shared

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

## verdict

tier: ALREADY EXISTS, YOU'RE LATE
difficulty: 4/10
savage_line: Congrats, you just re-invented Intercom with extra steps and a worse UI.

## ship_it_anyway

differentiator: Build the billing-escalation audit trail, not just the escalation — a timestamped, exportable log proving a human reviewed every billing ticket, sold to finance teams for compliance.
riskiest_assumption: That teams will trust an AI draft enough to send it without heavy editing — if edit rates exceed 70%, you're an expensive spellchecker, not an agent.
honest_cost: ~$15K and 4 months to something defensible. Do NOT build this if you've never worked in support — you will ship something that infuriates the people it's supposed to help.

## agent_readiness

overall: 70/100 (band B)
memory_required: 22/25
tool_count: 11/25
policy_surface: 14/25
eval_coverage: 23/25

## owasp_codes

- MCP-2: Cross-server prompt injection
- MCP-3: Excessive agency
- MCP-5: Insecure tool composition

## install_options

bootstrap: https://whycantwehaveanagentforthis.com/api/bootstrap/68373674-e3a/raw
policy_yaml: https://whycantwehaveanagentforthis.com/api/agent-readiness/68373674-e3a?format=yaml
badge_svg: https://whycantwehaveanagentforthis.com/api/badge/68373674-e3a/svg

## next_step

scope_with_human: https://cal.com/sattyamjjain
note: Scope this agent live with a human — 20 min, free, no signup