Notes from the work

What we learned building the thing.

Engineering notes, architecture decisions and post-mortems from live work. Written by the people who shipped it.

3 posts in AI Engineering

AI EngineeringAug 6, 20268 min read
Why Agentic Lead Scoring Beats Cold Outreach for UK Buy-to-Let Mortgages
Buy-to-let is now a remortgage market — the borrowers are already out there, on fixed rates with end dates. Agentic scoring finds the ones reaching term and reaching for a decision, instead of dialling everyone.
Read the post
AI EngineeringAug 6, 20267 min read
Building a PII-Safe Agentic Architecture for BFSI on AWS Serverless
A reference architecture for running AI agents on banking data without leaking PII — guardrails at ingress, redact-before-reason, VPC-only model calls, and an audit trail that survives an RBI inspection.
Read the post
AI EngineeringJun 1, 202612 min read
Six Months of Production LLM Bills: A Cost-Optimisation Postmortem
We shipped a customer-facing AI feature in January and the first invoice was twelve times higher than the back-of-napkin estimate. Here's the six-month story of how we cut inference spend by 87% without touching the model — caching, routing, prompt economy, and the one decision that saved more than every clever trick combined. We shipped a customer-facing AI feature in January and the first invoice was twelve times higher than the back-of-napkin estimate. Here's the six-month story of how we cut inference spend by 87% without touching the model — caching, routing, prompt economy, and the one decision that saved more than every clever trick combined.
Read the post