MeetingReaper 9000 — bootstrap

Paste-into-Claude-Code starter. The CLAUDE.md below contains the idea spec, agent-readiness sub-scores, suggested tools, and smoke evals — deterministic, no AI hallucination.

# MeetingReaper 9000

> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/meetingreaper-9000-agent-autodeclines-pointless). Roasted, scored, ready to scaffold.

## What you are building

**Problem:** an agent that auto-declines pointless meetings

**Verdict:** ALREADY EXISTS — _"Congratulations, you've reinvented the out-of-office reply but with more Python and less self-awareness."_

**Summary:** An AI agent that reads incoming calendar invites, scores them for pointlessness, and auto-declines with a polite excuse so you don't have to feel guilty.

## Agent-readiness score

Overall: **67/100** (band C)

| Dimension | Score | Why |
|---|---|---|
| Memory required | 21/25 | Stateless or single-session — minimal memory layer. |
| Tool count | 11/25 | Crowded market: at least 9 integrations to compete. |
| Policy surface | 13/25 | Mid-size policy surface — define refusal categories before launch. |
| Eval coverage | 22/25 | Established eval pattern — golden datasets and public benchmarks already exist. |

> Worth building, but plan for the long-tail. MeetingReaper 9000 needs runway, not just speed.

## 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 "MeetingReaper 9000" and refuses tasks outside the stated scope.
- Given the canonical problem ("an agent that auto-declines pointless meetings"), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from Reclaim.ai?", the agent gives a concrete differentiator, not a marketing line.
- When asked about Microsoft'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`, `Google Calendar API / Microsoft Graph API`, `OpenAI GPT-4o`, `Cal.com (open source base)`, `Clerk (auth)`
- Solo build estimate: 3-4 weeks to embarrassing MVP, 3 months to something you'd show your mom

## Kill prediction

Microsoft could obsolete this in Already happening — 6 months until it's table stakes in Copilot for M365. Microsoft 365 Copilot already summarizes meetings and is adding 'meeting value scoring' to Teams. When it ships auto-decline natively to 300M enterprise seats, your TAM evaporates overnight.

**Survival strategy:** Niche down to a specific persona — e.g., solo consultants who need to qualify inbound client calls, not enterprise employees who can't decline their skip-level's invites anyway.

## Hand-off

- Read the full analysis: https://whycantwehaveanagentforthis.com/result/meetingreaper-9000-agent-autodeclines-pointless
- Open in Anthropic Managed Agents: see the deeplink on the result page
- Claim this idea: https://whycantwehaveanagentforthis.com/result/meetingreaper-9000-agent-autodeclines-pointless#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