Blog
2026
On optimizing AI costs
pre requisites for minimising llm costs and getting better outputs
Sep 13Prompt caching & context optimization for harnesses
Extremely scalable solutions to context bloat and hitting prompt caches.
Jul 29Multi agent harness architecture
fixing context pollution, orchestrating a boss model with a swarm of subagents, and implementing a lazy tool surface.
Jul 25Reliable email labelling
The hidden product work behind reliable email labelling.
Jun 9Practical work suggestions from integration activity
Challenges and hurdles on extracting actionable work from across integrations.
Jun 9