SMB spends 2 days and $250 building an AI quoting tool that saves 20 hrs/week
MatthewChang · x · 2026-10-03
A small business owner spent 2 days and $250 in API credits building an AI quoting tool trained on his own data. It's projected to save 20 hours per week, run for under $20/month, and improve over time as it trains on company data — and it sent out its first automated quote an hour after launch. He acknowledges critics will call it "slop" but points to the tangible results.
More from coding & agent
- FT: US tech outages blamed on rush to fix bugs found by AI — nordicinst · 2026-11-19
- Claude Code overtakes Cursor and Copilot in job-post mentions ahead of Anthropic IPO — antgoldbloom · 2026-11-19
- Dev submits PR adding periodic checkpoints to GKE sandboxes so agents don't lose progress — yoimnotkesku · 2026-11-19
- AWS adds private CA support to Bedrock AgentCore Identity for connecting agents to self-hosted IdPs — AWS ML Blog · 2026-11-19
- Orchestrator's Cloud Agents graduate from beta to general availability — julianweisser · 2026-11-19
- Zero users, 33 pages shipped: dev crowdsources audit for AI-agent trust schema — TheHamzaShahbaz · 2026-11-19