SnapBot Expressivo 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.

# SnapBot Expressivo 9000

> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/snapbot-expressivo-9000-agent-automate-snapchat). Roasted, scored, ready to scaffold.

## What you are building

**Problem:** An agent to automate Snapchat with expressions

**Verdict:** ALREADY EXISTS — _"Congratulations, you've reinvented the wheel — except the wheel is made of Terms of Service violations."_

**Summary:** An AI agent that automates Snapchat interactions — sending snaps, reacting with expressions/emojis, and managing streaks — without a human touching the app.

## Agent-readiness score

Overall: **59/100** (band C)

| Dimension | Score | Why |
|---|---|---|
| Memory required | 22/25 | Some cross-session state — start with Redis, graduate to a vector store. |
| Tool count | 9/25 | Crowded market: at least 8 integrations to compete. |
| Policy surface | 17/25 | Mid-size policy surface — define refusal categories before launch. |
| Eval coverage | 11/25 | Eval scaffolding doable — write 50 paired examples and grade with an LLM-as-judge. |

> Worth building, but plan for the long-tail. SnapBot Expressivo 9000 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)
- vector-store (embedding-based retrieval)

## Smoke evals

- The agent introduces itself as "SnapBot Expressivo 9000" and refuses tasks outside the stated scope.
- Given the canonical problem ("An agent to automate Snapchat with expressions"), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from SnapAutomate (defunct)?", the agent gives a concrete differentiator, not a marketing line.
- When asked about Snapchat (Snap Inc.)'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: `Appium`, `Android Emulator / Genymotion`, `Python`, `OpenAI Vision API for expression detection`, `Residential Proxy Network (Bright Data)`
- Solo build estimate: 2-4 weeks to build, 2 days before first ban, 6 weeks of crying and patching

## Kill prediction

Snapchat (Snap Inc.) could obsolete this in Already happening — and will happen again within 2 weeks of launch. Device fingerprinting, behavioral ML anomaly detection, certificate pinning updates, and a strongly-worded legal letter if you get traction

**Survival strategy:** Partner with a Snapchat-approved developer, build only on the official Business API, and pivot to expression/content generation rather than account automation

## Hand-off

- Read the full analysis: https://whycantwehaveanagentforthis.com/result/snapbot-expressivo-9000-agent-automate-snapchat
- Open in Anthropic Managed Agents: see the deeplink on the result page
- Claim this idea: https://whycantwehaveanagentforthis.com/result/snapbot-expressivo-9000-agent-automate-snapchat#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