01
Essay · Agent architecture
Building an Agent That Improves Its Own Harness
Turn repeated failures into tested changes, then use the evidence to improve the next experiment.
Essays & collections6 essays · 5 collections
Writing
Architecture, experiments, and useful distinctions from building autonomous agents, context systems, and reproducible evaluation.
02
Collection · 3 parts
How to Write and Score an Agent Eval
From a plausible wrong answer to a defensible release decision: nine chapters on writing tests, calculating scores, and checking whether success repeats.
03
Essay · Agent interfaces
Implementing Progressive Disclosure for Agent Tools
Build one discoverable CLI for MCP, SQL, and REST, with precise schemas, scoped execution, and honest result receipts.
04
Essay · Agent architecture
Before You Build Another Agent
Build a strong generalist. Make expertise discoverable. Delegate only when the task earns it.
05
Collection · 5 chapters
The Quality Flywheel
How failures become experiments, better decisions, and knowledge that survives the next release.
06
Collection · 10 chapters
Classifiers: When Labels Become Decisions
Ten chapters on designing categories, choosing evidence, measuring errors, and deciding when a label deserves to influence what happens next.
07
Collection · 5 chapters
How Intelligence Finds Its Way
Five essays on the worlds intelligence can read, the questions it asks, the experience it carries, and the actions it can afford to try.
08
Essay · Evaluation & replay infrastructure
Checkpoint Replay for Long-Horizon Agent Evaluation
Evaluate a 24-hour soak at recorded checkpoints. Restore the evidence and agent state available at each moment, then test the decisions.
09
Essay · Context & data infrastructure
Local Context for Autonomous Agents
Put telemetry, logs, and topology beside the agent. Use PromQL and files to keep retrieval reliable and model context focused.
10
Collection · 9 chapters
Trustworthy Autonomy
Nine principles for systems that deserve the authority we give them. A field guide to evidence, boundaries, and learning from consequences.
11
Essay · Autonomous agents
Engineering Autonomous Agents
An agent’s capabilities depend on its data, execution loop, state, and feedback. Design them as one system.