enterprise

AI cannot help an enterprise that cannot describe itself, and governance failure surfaces faster than optimisation failure.

The companies that win with AI agents aren't deploying the most agents — they're redesigning their organisations to work with them.

I benchmarked 10 memory backends and multiple embedding models on actual agent memory retrieval. The results challenge common assumptions about what matters.

Agent memory isn't knowledge management. It's performance infrastructure — and the gap between a stateless agent and one that accumulates context is measurable.

Enterprise AI keeps promising to capture institutional knowledge. The most valuable kind resists capture by design.

The things that matter most in production are the things that get benchmarked least

The missing layer in enterprise AI isn't smarter models — it's structured memory that humans can actually review.

Most enterprises are optimising the wrong variable. The gap between 5% and 40% agent adoption won't be closed by better models.

The shift from agents you summon to agents that watch. Enterprise AI workflows are becoming continuous loops — and the failure modes are different.

Not better function calling — decoupling. When tools expose MCP servers, any agent can compose any system freely. The heterogeneity problem becomes a configuration problem.

The hardest phase of AI architecture isn't building the stack. It's the moment after the stack is built and eighteen teams start making independent decisions on top of it.

Ask for bugs and you'll get bugs — whether they exist or not. Sycophancy is a design feature, and the fix isn't better prompting.

Most enterprise AI agent pilots in financial services fail at the same point: the second tool call. The problem isn't the framework.