infrastructure
4 posts
Agent memory is only a moat if you can export it
Agent memory becomes a business asset when you control it, can export it, know when it gets deleted, and know it trains no model. Use four contract questions to tell whether a memory layer is building your company brain or the vendor's moat.
A DIY agent fleet costs you a week, not a token budget.
A DIY agent fleet costs more than tokens and seats because every agent needs someone to version, supervise, limit and measure it. For businesses without an engineering bench, the right build-vs-buy question is who owns that work and whether it's included in the platform.
Agentic graphs vs. loops: what actually breaks when agents run wide
Linear agents get slow when independent work is forced through one queue. Graphs help when the work is genuinely wide, as long as verification, isolation, and measurement are built into the structure.
Every AI agent needs a blast radius: the case for microVM isolation
Where an agent runs decides what it can damage when prompt injection lands. A walk through the four levels of isolation in common use, and why microVMs have become the production standard.