AffordAbled - AI finance for transactions, IOUs, splits, and settlements.

Personal finance tools often require users to navigate forms and separate screens for routine tasks. Shared expenses and informal debts can also be difficult to track alongside personal transactions. I wanted to explore whether a conversational interface could make these workflows easier while keeping financial records structured, user-scoped, and verifiable.

I independently designed and built AffordAbled as a full-stack application using React, TypeScript, FastAPI, and PostgreSQL. Its LangGraph chat workflow coordinates specialist agents and finance tools for transactions, accounts, spending queries, shared expenses, IOUs, and settlements. Guardrails and saved-result checks help ensure the assistant reports completed actions accurately. Chat turns use background processing and server-sent events, with polling as a fallback. Simple balance questions can take a direct database path without additional model calls.

AffordAbled demonstrates a conversational alternative to manually navigating finance forms for supported tasks. A local evaluation of 10 balance queries measured median end-to-end chat latency (p50) at 6.27 seconds, with server-side turn time around 5.77 seconds. A later 3-request run measured 4.29 seconds, but used different conditions and is not directly comparable. These preliminary local results are not production measurements. No timed comparison with manual entry or another finance app has been conducted.