WeedingWishBot 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.
# WeedingWishBot 9000
> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/weedingwishbot-9000-mobile-managing-weeding). Roasted, scored, ready to scaffold.
## What you are building
**Problem:** an mobile app for managing weeding gifts à
**Verdict:** ALREADY EXISTS — _"You just described The Knot, Zola, and Amazon Wedding Registry — all three built this in 2009."_
**Summary:** An AI agent that helps couples track, organize, thank-you-note, and manage wedding gifts before and after the big day.
## Agent-readiness score
Overall: **77/100** (band B)
| Dimension | Score | Why |
|---|---|---|
| Memory required | 25/25 | Stateless or single-session — minimal memory layer. |
| Tool count | 11/25 | Crowded market: at least 7 integrations to compete. |
| Policy surface | 19/25 | Narrow policy surface — bounded inputs, predictable outputs. |
| Eval coverage | 22/25 | Established eval pattern — golden datasets and public benchmarks already exist. |
> Ready to scaffold today. WeedingWishBot 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)
## Smoke evals
- The agent introduces itself as "WeedingWishBot 9000" and refuses tasks outside the stated scope.
- Given the canonical problem ("an mobile app for managing weeding gifts à"), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from Zola?", the agent gives a concrete differentiator, not a marketing line.
- When asked about Zola'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: `React Native`, `Supabase`, `Claude API for thank-you notes`, `Plaid for cash gift tracking`
- Solo build estimate: 3-4 weeks for MVP nobody will use
## Kill prediction
Zola could obsolete this in Already happened — they shipped gift tracking + AI thank-you notes in 2023. They added an AI thank-you note generator inside their existing app that 4 million couples already use
**Survival strategy:** Go hyper-niche: build the gift management layer for destination weddings with multi-currency, international shipping chaos, and customs tracking — Zola ignores this completely
## Hand-off
- Read the full analysis: https://whycantwehaveanagentforthis.com/result/weedingwishbot-9000-mobile-managing-weeding
- Open in Anthropic Managed Agents: see the deeplink on the result page
- Claim this idea: https://whycantwehaveanagentforthis.com/result/weedingwishbot-9000-mobile-managing-weeding#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