25 Jul 2026 · 7 min read

Consulting and Craft · Hands On

Extracting Lease Terms with Bedrock

An envisioning session parked this one with a single note: no gold answers. Pulling structured terms out of lease PDFs is a clean extraction job, but you can't ship what you can't measure, and there was nothing to measure against. So the build starts where the parking note pointed, building the gold set, and only then wires up the model: structured output, field-level confidence, and a human confirming anything the model isn't sure of before it touches the system of record.

Read article 24 Jul 2026 · 15 min read

Exam Room · Advanced GenAI

Hybrid Search and Reranking for Bedrock RAG

A support assistant on Bedrock retrieves by pure semantic search and keeps whiffing on exact-term queries: product codes, error codes, part numbers, acronyms, proper names. The embedding of 'ERR-4021' sits close to a hundred other error codes, so a plausible-but-wrong chunk outranks the one document that actually names it. The fix is two levers, hybrid retrieval and a reranker, and knowing which one the precision problem actually needs.

Read article 24 Jul 2026 · 1 min read

Flash Cards · Responsible AI

Flash Card: The Eight Responsible-AI Dimensions

AWS names its responsible-AI dimensions. Roughly, what are they?

Read article 24 Jul 2026 · 16 min read

Exam Room · Advanced GenAI

Evaluating a RAG Pipeline End to End

A citations-required assistant over internal documents answers most questions well and a few of them wrong, and the team cannot tell why. Was the right passage never retrieved, or was it retrieved and then ignored? Those are two different failures with two different fixes, and an evaluation that reports one score for the whole pipeline hides which one you have. This walks through separating the retrieval half from the generation half so the regression harness points at the part that actually broke.

Read article 23 Jul 2026 · 31 min read

The Workshop

The Workshop: Retrospectives

A pattern for creating a structured, safe space to inspect how the team is working and decide one or two things to change, so that continuous improvement stops being a poster on the wall and starts being a thing that actually happens.

Read article 23 Jul 2026 · 1 min read

Flash Cards · Governance

Flash Card: Turning Logs Into an Audit

The reviewer wants a control-mapped report and a statement of what the model is approved for. Two artifacts?

Read article 23 Jul 2026 · 13 min read

The Greenbox Story · Faster Together

API Contracts: Two Squads, One Direction

Perth and Melbourne have their own backlogs, their own sprint rhythms, and their own priorities. They keep surprising each other with dependencies nobody saw coming.

Read article 22 Jul 2026 · 15 min read

Exam Room · Advanced GenAI

Keeping PII Out of LLM Prompts and Logs

A claims assistant that has to answer questions about a customer's claim while keeping the customer's name, address, policy number, and medical details out of training data, out of logs, and out of anything a subpoena could touch later. PII redaction isn't one knob, it's four or five, in different places, each covering a different leak path. Comprehend, Bedrock Guardrails, custom redaction, and the prompt itself each handle a different shape of the problem.

Read article 22 Jul 2026 · 1 min read

Flash Cards · Governance

Flash Card: Who Changed It vs What It Said

Who turned off the PII filter, and when? Which log, and why not invocation logging?

Read article