Learnings
← All PostsOur Insights
Hard-won insights we've gathered while teaching AI to play nicely with others and not accidentally become sentient. Expect equal parts technical deep dives and existential musings.
Horton Hears a Whisper
We built a fleet of ESP32 microphones that stream raw audio to a server, transcribe it with Whisper, and surface it in Grafana. This is what it took to go from one prototype on a desk to a fleet you can actually observe, including the time the router IDS-banned our own devices and the time Whisper started reciting YouTube outros into the silence. Read more...
Why We Built a Language for AI Pipelines
We replaced escaped DOT strings with a purpose-built language for AI pipelines. Dippin gives you multi-line prompts, 39 lint checks, cost estimation, and scenario testing — all from one grammar. Read more...
Word Compiler, A Context Compiler for Long-Form Fiction
Word Compiler applies software engineering principles to long-form fiction writing with LLMs. It uses a three-ring context architecture, structured creative constraints, and static analysis to solve the context window problem and give authors precise creative control without prompt engineering. Read more...