CalPocalypse 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.

# CalPocalypse 9000

> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/calpocalypse-9000-meeting-scheduler-agent). Roasted, scored, ready to scaffold.

## What you are building

**Problem:** meeting scheduler agent

**Verdict:** ALREADY EXISTS — _"Congratulations, you've reinvented Calendly. Your parents must be so proud."_

**Summary:** An AI agent that autonomously finds, proposes, and books meeting times by reading calendars, inferring preferences, and handling the back-and-forth negotiation between participants.

## Agent-readiness score

Overall: **71/100** (band B)

| Dimension | Score | Why |
|---|---|---|
| Memory required | 24/25 | 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 | 23/25 | Established eval pattern — golden datasets and public benchmarks already exist. |

> Ready to scaffold today. CalPocalypse 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 "CalPocalypse 9000" and refuses tasks outside the stated scope.
- Given the canonical problem ("meeting scheduler agent"), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from Calendly?", the agent gives a concrete differentiator, not a marketing line.
- When asked about Google'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: `Cal.com (fork)`, `Claude API`, `Google Calendar API`, `Next.js`, `Supabase`
- Solo build estimate: 3-4 weeks for MVP, 6 months to be embarrassed by Reclaim's feature list

## Kill prediction

Google could obsolete this in 12-18 months. Google Duet AI inside Google Calendar will handle natural language scheduling natively — 'Schedule a meeting with my team next week when everyone's free' — no third-party tool needed, already rolling out

**Survival strategy:** Go vertical. Own one industry (recruiting, therapy, legal) so deeply that Google's generic solution feels like a butter knife at a surgery

## Hand-off

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