SunBurnedSportsGenius 305 — 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.

# SunBurnedSportsGenius 305

> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/sunburnedsportsgenius-305-south-florida-sports). Roasted, scored, ready to scaffold.

## What you are building

**Problem:** South Florida Sports Trivia

**Verdict:** EMBARRASSINGLY EASY — _"You want to build a trivia bot for a market where half the fans moved here from somewhere else and don't care."_

**Summary:** An AI-powered trivia agent covering the Heat, Dolphins, Marlins, Panthers, Inter Miami, and historical South Florida sports moments, with adaptive difficulty and real-time stat verification.

## Agent-readiness score

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

| Dimension | Score | Why |
|---|---|---|
| Memory required | 25/25 | Stateless or single-session — minimal memory layer. |
| Tool count | 11/25 | Crowded market: at least 8 integrations to compete. |
| Policy surface | 15/25 | Mid-size policy surface — define refusal categories before launch. |
| Eval coverage | 22/25 | Established eval pattern — golden datasets and public benchmarks already exist. |

> Ready to scaffold today. SunBurnedSportsGenius 305 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 "SunBurnedSportsGenius 305" and refuses tasks outside the stated scope.
- Given the canonical problem ("South Florida Sports Trivia"), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from Trivia Crack?", the agent gives a concrete differentiator, not a marketing line.
- When asked about ESPN'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`, `OpenAI GPT-4o`, `TheSportsDB API`, `Supabase`, `Vercel`
- Solo build estimate: 1-2 weekends for MVP, 6 weeks for something you're not embarrassed to show

## Kill prediction

ESPN could obsolete this in 12-18 months. ESPN already owns the sports fan attention layer and will drop an AI trivia feature into their app as a retention mechanic, instantly making your standalone product redundant for 40M existing users

**Survival strategy:** Go hyper-local B2B — sell white-labeled trivia experiences directly to the Heat, Dolphins, and Hard Rock Stadium for in-venue fan engagement. Become the vendor, not the app.

## Hand-off

- Read the full analysis: https://whycantwehaveanagentforthis.com/result/sunburnedsportsgenius-305-south-florida-sports
- Open in Anthropic Managed Agents: see the deeplink on the result page
- Claim this idea: https://whycantwehaveanagentforthis.com/result/sunburnedsportsgenius-305-south-florida-sports#claim