Insights on AI agents, infrastructure, and building the future of autonomous software.
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 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.
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.
Levain workspaces now ship with a default assistant built on the Hermes agent framework because Hermes can keep memory, read a knowledge base, and write reusable skills. That means the assistant can learn how your business works instead of asking you to explain billing, approvals, or customer handoffs every Monday.
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.
Agents don't improve on their own. A structured iteration loop (measure, test, refine) is what separates a v1 that stagnates from one that gets meaningfully better over time.