
A Reproducible ComfyUI Workflow for Editorial Images
How to turn a node graph into a versioned image-production recipe with controlled inputs, traceable dependencies and reviewable outputs.
3 min read
Deep dives into agents, memory, retrieval, evaluation and the context assembled around every model call.


How to turn a node graph into a versioned image-production recipe with controlled inputs, traceable dependencies and reviewable outputs.
3 min read

A repeatable evaluation protocol for comparing image generators without turning the result into a subjective prompt contest.
4 min read

A shot-level protocol for comparing video generators on continuity, controllability, failure recovery and production cost.
4 min read

An architecture for adding generated dialogue to a game without giving up deterministic state, responsive interaction or narrative control.
4 min read

A rigorous guide to agent memory as a governed state subsystem: what is stored, how it is updated and retrieved, and how to evaluate it safely.
11 min read
Why the context you assemble matters more than the prompt you write, and practical techniques to keep it relevant and within budget.
3 min read
A practical guide to building a small Model Context Protocol server in TypeScript, from the first tool to testing it in a real client.
2 min read
How to compare two models on your own tasks with a small dataset, simple graders and a report you can actually read.
2 min read