BillReaper 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.

# BillReaper 9000

> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/billreaper-9000-agent-autopays-bills). Roasted, scored, ready to scaffold.

## What you are building

**Problem:** An agent that auto-pays my bills

**Verdict:** ALREADY EXISTS — _"Congratulations, you just reinvented autopay, a feature your grandma has had since the Bush administration."_

**Summary:** An agent that monitors incoming bills and automatically initiates payments from linked bank accounts or cards before due dates.

## Agent-readiness score

Overall: **74/100** (band B)

| 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 | 18/25 | 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. BillReaper 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 "BillReaper 9000" and refuses tasks outside the stated scope.
- Given the canonical problem ("An agent that auto-pays my bills"), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from Autopay (Every Bank Ever)?", the agent gives a concrete differentiator, not a marketing line.
- When asked about Nobody — it's already dead on arrival'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: `Plaid API`, `Next.js`, `Stripe Treasury`, `PostgreSQL`
- Solo build estimate: 1 weekend — then 6 months of compliance paperwork

## Kill prediction

Nobody — it's already dead on arrival could obsolete this in Already happened — circa 2005. Banks, credit cards, and utilities built autopay natively into their platforms for free, removing any reason for a standalone product to exist

**Survival strategy:** Pivot hard to B2B accounts payable automation for SMBs — that's where the actual pain lives. Check out what Tipalti and Bill.com do and find the gap below their price floor.

## Hand-off

- Read the full analysis: https://whycantwehaveanagentforthis.com/result/billreaper-9000-agent-autopays-bills
- Open in Anthropic Managed Agents: see the deeplink on the result page
- Claim this idea: https://whycantwehaveanagentforthis.com/result/billreaper-9000-agent-autopays-bills#claim