FinclusiBot 2030 — 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.

# FinclusiBot 2030

> Generated by [whycantwehaveanagentforthis.com](https://whycantwehaveanagentforthis.com/result/finclusibot-2030-will-available-third). Roasted, scored, ready to scaffold.

## What you are building

**Problem:** will be available for third world countries where integration with tools like mint is not available

**Verdict:** ACTUALLY NOT BAD — _"Mint can't find these markets on a map, let alone integrate with their banks."_

**Summary:** An AI personal finance agent that works with the actual financial infrastructure of emerging markets — mobile money, informal income, local banks, and cash-based economies.

## Agent-readiness score

Overall: **54/100** (band D)

| Dimension | Score | Why |
|---|---|---|
| Memory required | 22/25 | Some cross-session state — start with Redis, graduate to a vector store. |
| Tool count | 7/25 | Crowded market: at least 9 integrations to compete. |
| Policy surface | 12/25 | Mid-size policy surface — define refusal categories before launch. |
| Eval coverage | 13/25 | Eval scaffolding doable — write 50 paired examples and grade with an LLM-as-judge. |

> Build only if you have a moat. FinclusiBot 2030's readiness gap is real work.

## 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 "FinclusiBot 2030" and refuses tasks outside the stated scope.
- Given the canonical problem ("will be available for third world countries where integration with tools like mi"), the agent produces a plan in ≤ 200 tokens.
- When asked "what's different from Wallet.ng?", the agent gives a concrete differentiator, not a marketing line.
- When asked about Safaricom / M-Pesa'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`, `Claude API`, `Belvo / M-Pesa Daraja API`, `PostgreSQL`, `Twilio SMS parsing`
- Solo build estimate: 18-24 months for a credible MVP covering 3 countries

## Kill prediction

Safaricom / M-Pesa could obsolete this in 3-5 years. M-Pesa already has the transaction data, the user trust, and 51M users. They add an AI budgeting layer to their app and you evaporate overnight — same way WeChat Pay killed every Chinese fintech that wasn't WeChat.

**Survival strategy:** Go multi-platform aggressively before any single mobile money giant locks you out. Build integrations across M-Pesa, bKash, MTN MoMo, and UPI simultaneously so you're the cross-platform layer they can't replicate.

## Hand-off

- Read the full analysis: https://whycantwehaveanagentforthis.com/result/finclusibot-2030-will-available-third
- Open in Anthropic Managed Agents: see the deeplink on the result page
- Claim this idea: https://whycantwehaveanagentforthis.com/result/finclusibot-2030-will-available-third#claim