GooglyGPT Explainer 101 — 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.
↓ Download CLAUDE.md JSON bundle Open in Claude Code →
# GooglyGPT Explainer 101

> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/googlygpt-explainer-101-difference-between-chatgpt). Roasted, scored, ready to scaffold.

## What you are building

**Problem:** Difference between chatgpt gemini and open ai

**Verdict:** ALREADY EXISTS — _"You typed your question into an AI to ask what AI is. The irony is doing backflips."_

**Summary:** An agent that explains the difference between AI products to people who are already using AI products to ask about AI products.

## Agent-readiness score

Overall: **73/100** (band B)

| Dimension | Score | Why |
|---|---|---|
| Memory required | 24/25 | Stateless or single-session — minimal memory layer. |
| Tool count | 11/25 | Crowded market: at least 7 integrations to compete. |
| Policy surface | 13/25 | 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. GooglyGPT Explainer 101 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 "GooglyGPT Explainer 101" and refuses tasks outside the stated scope.
- Given the canonical problem ("Difference between chatgpt gemini and open ai"), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from Wikipedia - ChatGPT?", 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: `Google Docs`, `Copy-paste`, `Wikipedia`, `Regret`
- Solo build estimate: 45 minutes including coffee break

## Kill prediction

Google could obsolete this in Already happened. Gemini answers questions about itself. ChatGPT answers questions about Gemini. Every AI already IS this agent.

**Survival strategy:** Pivot to live, automated benchmark testing with real tasks — not explanations, but proof.

## Hand-off

- Read the full analysis: https://whycantwehaveanagentforthis.com/result/googlygpt-explainer-101-difference-between-chatgpt
- Open in Anthropic Managed Agents: see the deeplink on the result page
- Claim this idea: https://whycantwehaveanagentforthis.com/result/googlygpt-explainer-101-difference-between-chatgpt#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