Writing
Technical writing & engineering notes.
Articles, architecture notes, project logs, and engineering reflections. Filter by type, search by keyword, or browse by tag.
Assembled Primitives vs. a Platform
I built a voice agent out of cloud primitives, and it worked. It has since been replaced by a purpose-built voice platform, and I think that was the right call.
What Deserves Attention Today
My homelab produces one verdict each morning: something needs you, or nothing does. Getting the second half honest was much harder than the first.
A Planner That Will Not Onboard Anything
The tool that decides how to onboard a new service into my homelab has no ability to onboard a service. That separation is the design, not a limitation.
Documentation That Publishes Itself, After I Say Yes
My homelab writes its own wiki pages. Every one of them still passes through a pull request I merge by hand, and publishing happens only from main.
A Sandbox for Demos You Throw Away
One box runs every client demo I have live. The pattern is unremarkable; the interesting part was my monitoring reporting four healthy demos as missing.
Teaching a System to Say “I Don’t Know”
The most useful thing my homelab brain does is refuse to answer. Grounded-or-blocked: every claim cites the fact that produced it, or it never reaches me.
A Second Brain That Refuses to Guess
Answering an operational question was costing a local model a 30-50K token dump. I built a compiled memory layer that does it in 2-5K, and blocks itself when it cannot cite a source.
The Network Is the Layer I Documented Last
My homelab has an IPAM, metrics from every access point, and a config file for the network that is entirely placeholders — with a warning at the top admitting it.
Building Voice Integrations on Top of Async Chatbots
What breaks when you front an async chatbot with Amazon Connect + Lex, and how to keep latency, barge-in, and context handoff sane.
What I Learned Designing Omnichannel Backend Integrations
Shared intent schema, eventually-consistent conversation state, and why the channel should be the last thing your backend knows about.
How I Think About Secure Backend Integrations
A working mental model for auth, secrets, scopes, and blast radius — built from scars, not books.
Architecture Note: When to pick SQS FIFO over a DB queue
A decision framework I use when the team reaches for a Postgres-backed queue by default.