CalBot 1994 — 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.

# CalBot 1994

> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/calbot-1994-agent-autoreplies-emails). Roasted, scored, ready to scaffold.

## What you are building

**Problem:** an agent that auto-replies to emails with meeting scheduling

**Verdict:** ALREADY EXISTS — _"Congratulations, you just reinvented Calendly with extra steps and less funding."_

**Summary:** An AI agent that reads incoming emails, detects scheduling intent, and auto-replies with available times or a booking link — possibly confirming the meeting autonomously.

## Agent-readiness score

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

| Dimension | Score | Why |
|---|---|---|
| Memory required | 23/25 | 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. CalBot 1994 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 "CalBot 1994" and refuses tasks outside the stated scope.
- Given the canonical problem ("an agent that auto-replies to emails with meeting scheduling"), 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 OSS`, `Gmail API / Microsoft Graph API`, `Claude API`, `Next.js`, `Resend`
- Solo build estimate: 1-2 weekends to a working prototype; 3 months to something you're not embarrassed by

## Kill prediction

Google could obsolete this in Already happening — Gemini in Gmail is rolling out scheduling suggestions now. Google Workspace will natively parse scheduling emails and insert booking flows directly in Gmail, zero install required, free for 3 billion users

**Survival strategy:** Go painfully vertical — build this exclusively for one industry (e.g., medical practices, law firms) where Gmail's generic solution is too dumb and compliance matters

## Hand-off

- Read the full analysis: https://whycantwehaveanagentforthis.com/result/calbot-1994-agent-autoreplies-emails
- Open in Anthropic Managed Agents: see the deeplink on the result page
- Claim this idea: https://whycantwehaveanagentforthis.com/result/calbot-1994-agent-autoreplies-emails#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