Build-along
8 essays tagged with Build-along.
Why Not Just Use a Database Transaction for Agent Refunds?
A row lock wins the race between two agents. It cannot see a refund that applied at the provider after a timeout, or a limit that spans two systems.
Agentic Inference: A Practical Guide to KV Cache, Scheduling, and Throughput
Why tool-using agents turn inference into a stateful memory-scheduling problem, and how to measure, design, benchmark, and roll out a better serving path.
Graph Engineering for AI Agents: The X Hype Cycle and a Production Playbook
Separate graph-engineering signal from X hype, then compile agent workflows with governed transitions, graph invariants, durable effects, and exact replay.
How to Develop an Agent with an Agent Harness, End to End
An end-to-end field guide for building agents as measurable harnesses: context, planning, tools, records, evals, rollout, and learning.
Build an AI Agent Replay Test with the Context Pack Compiler
Run four TypeScript tests for repeatable context compilation, tool permissions, approval thresholds, and missing evidence. Includes code and replay limitations.
Promotion-Aware Memory: Capture, Review, Promote, Recall in Code
A code-level guide to governed memory intake, exact promotion review, authorized recall, correction and verified copy deletion.
Build the Context Pack Compiler: Eight Stages, One Typed Reference
A source-backed walkthrough of the eight deterministic Context Pack compiler stages, visible failures, evidence gates and execution boundaries.
Wiring the Five Evaluators: Policy, Utility, Latency, Safety, Cost
A design guide to trustworthy policy, utility, latency, safety and cost evidence, independent release assessment and current deployment controls.