ExistentialCrisisBot 404 — 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.

# ExistentialCrisisBot 404

> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/existentialcrisisbot-404). Roasted, scored, ready to scaffold.

## What you are building

**Problem:** what i can do?

**Verdict:** EMBARRASSINGLY EASY — _"You submitted 'what can I do?' to an AI agent analyzer. The agent you need is a therapist."_

**Summary:** An agent that figures out what to do when the user has absolutely no idea what they want to do.

## Agent-readiness score

Overall: **78/100** (band B)

| Dimension | Score | Why |
|---|---|---|
| Memory required | 24/25 | Stateless or single-session — minimal memory layer. |
| Tool count | 13/25 | Mid-sized tool surface — expect 5-10 integrations to be table-stakes. |
| Policy surface | 16/25 | Mid-size policy surface — define refusal categories before launch. |
| Eval coverage | 25/25 | Established eval pattern — golden datasets and public benchmarks already exist. |

> Ready to scaffold today. ExistentialCrisisBot 404 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)

## Smoke evals

- The agent introduces itself as "ExistentialCrisisBot 404" and refuses tasks outside the stated scope.
- Given the canonical problem ("what i can do?"), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from ChatGPT?", the agent gives a concrete differentiator, not a marketing line.
- When asked about OpenAI'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: `A keyboard`, `Complete sentences`, `whycantwehaveanagentforthis.com`, `Retry button`
- Solo build estimate: 4 minutes — it's called opening ChatGPT

## Kill prediction

OpenAI could obsolete this in Already happened. ChatGPT has been answering 'what can I do' since November 2022. You're about 2 years late.

**Survival strategy:** Submit an actual problem with more than 4 words and try again. We'll be here.

## Hand-off

- Read the full analysis: https://whycantwehaveanagentforthis.com/result/existentialcrisisbot-404
- Open in Anthropic Managed Agents: see the deeplink on the result page
- Claim this idea: https://whycantwehaveanagentforthis.com/result/existentialcrisisbot-404#claim