GlowUp.exe — 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 →
# GlowUp.exe

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

## What you are building

**Problem:** Ugly so ugly

**Verdict:** EMBARRASSINGLY EASY — _"Bro submitted 'being ugly' as a business problem. The audacity is actually kind of beautiful."_

**Summary:** An AI agent that analyzes your appearance, suggests actionable style/grooming improvements, and optionally applies beauty filters — basically a brutally honest personal stylist that lives in your phone.

## Agent-readiness score

Overall: **69/100** (band C)

| Dimension | Score | Why |
|---|---|---|
| Memory required | 23/25 | Stateless or single-session — minimal memory layer. |
| Tool count | 11/25 | Crowded market: at least 8 integrations to compete. |
| Policy surface | 12/25 | Mid-size policy surface — define refusal categories before launch. |
| Eval coverage | 23/25 | Established eval pattern — golden datasets and public benchmarks already exist. |

> Worth building, but plan for the long-tail. GlowUp.exe needs runway, not just speed.

## 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 "GlowUp.exe" and refuses tasks outside the stated scope.
- Given the canonical problem ("Ugly so ugly"), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from FaceApp?", the agent gives a concrete differentiator, not a marketing line.
- When asked about Snapchat'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`, `Replicate API (for image models)`, `InsightFace`, `Claude API`, `Stripe`
- Solo build estimate: 2-3 weeks for an MVP that works, 3 months before you're not embarrassed by it

## Kill prediction

Snapchat could obsolete this in Already happened — check your Snap camera. Snapchat's AR lenses and beauty filters are free, used by 375M daily users, and updated weekly by an army of engineers. They already won this war.

**Survival strategy:** Ignore filters entirely. Go full brutal-honesty coaching: 'Here's your haircut, skincare routine, and outfit changes — ranked by ROI on attractiveness.' Make it the Mean Girls app people secretly want.

## Hand-off

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