Thinking out loud on hard problems
- Designing a Security-Findings Aggregator with DDD and Kafka
One system that uses domain-driven, event-driven and message-driven design plus REST, with a 10,000-finding simulation showing what the outbox and inbox fix.
- SageMaker Workshop: Why 89% Accuracy Meant Almost Nothing
I worked through AWS's SageMaker AI Workshop. My first model beat a do-nothing baseline by half a point. Here's what that taught me about shipping ML.
- Long-Running On-Call Agent: Every Choice, Measured
An on-call agent forces four choices: who reasons, who decides, what it sees, what survives a crash. What I picked, measured, and the AWS option for each.
- Chaperone: A Flight Recorder for AI Agents on AWS
How I built Chaperone in four days with Claude Code and the AWS MCP Server: CloudTrail turned into a reviewable record of what a coding agent did in AWS.
- Your Agent Doesn't Need to Generate Text to Decide. It Needs a Classifier.
Two new model classes skip text generation for agent decisions — routing, risk scoring, best-of-N selection. Why a typed answer beats a paragraph.
- The Multi-Agent Coordination Tax: Mesh vs. Mediator
Agent-to-agent messaging grows quadratically with team size. Why mesh multi-agent systems get expensive, and the mediator pattern microservices already proved.
- SLI/SLO Observability, Built By Hand Before Any Vendor Touches It
A vendor-neutral SLI/SLO pipeline from scratch with OTel, Prometheus, Sloth, Alertmanager and Grafana: three real bugs and a working burn-rate alert.
- MCP Is Giving Up Statefulness — and That's the Point
MCP's July 28 revision removes session state, sampling, roots and logging. Why a protocol built for laptops had to go stateless to run in data centers.
- Self-Hosting Chatterbox on Apple Silicon: The Build Log, and the Bigger Bet Underneath It
A build log for self-hosting Resemble AI's Chatterbox voice-cloning model on Apple Silicon: the judgment calls the docs skip, and why the pattern matters.
- The Agent That Forgets Everything: Cross-Session Memory Without Breaking the Audit Trail
Part 6: what happens when the context window closes. Cross-session memory for a compliance agent with Mem0 and pgvector, and why it's the hardest part.
34 posts