Field notes.
Founder notes and worked examples on building the data plane for AI agents.
- 8 min readopen-source · business-models
Open core was a licensing strategy. It needs to become an architectural one.
The enterprise tier was defensible because building it yourself was expensive. That clause just changed. Gating capabilities is a weaker strategy than it used to be; gating operations is a stronger one.
Read - 6 min readagents · data-infrastructure
The lakehouse organized data for analysts. Nobody has organized it for agents.
Every data layer ever built assumed a human decides the shape of the data ahead of time and a human reads the result. Production agents violate both assumptions — and the next data layer will be authored, in part, by the agents that read from it.
Read - 8 min readagents · context-engineering
Agents in production: what looks like a reasoning failure is usually a context failure
Your agent isn't hallucinating — it's reasoning correctly over the wrong inputs. What looks like a reasoning failure is usually a context failure, and context failures are fixable with engineering, today.
Read - agents · sre · benchmark
One read path, four incidents
The extended SRE benchmark: the same agent, with and without a data plane underneath.
Read - agents · sre
NavFlow for AI SRE
Incident response is an input problem. What an agent can do when the whole read is one call — with measured results.
Read