#llms

Strands + AgentCore — a year-end agent-stack inventory

“Pick the framework that matches your team's experience, not the one with the loudest blog posts.”

Bedrock AgentCore at Summit NY — what it actually changes

“AgentCore is what Bedrock Agents should have been from the start. That doesn't make it the wrong answer now.”

An open-source eval starter kit for product managers

“Vibes are a feature flag without a kill switch.”

Knowledge Bases for Bedrock in production — the gotchas list

“Managed RAG is 80% of the work. The other 20% is most of the production headaches.”

Three things from re:Invent that actually change my roadmap

“AWS announces two hundred things. You change your roadmap based on three.”

Building a multi-tenant LLM platform, 0 → 1

“The rubric outranked the org chart. That's the only way a call like that ever survives.”

Bedrock Agents, half a year in — the parts I actually use

“Agents are router code with model-shaped opinions. Useful, but not magic — and that's exactly why I kept some of it.”

First week with Bedrock: a PM's read on the September GA

“Bedrock isn't a model — it's the absence of a vendor lock-in argument.”

Prompt regression — the rough first version of our test set

“We're testing prompts the same way we test code. We just haven't earned the vocabulary yet.”