An evaluation process that stopped to announce it had started
An evaluation stopped to announce that it had started. Restarting it exposed a concurrency failure in the project’s database architecture.
Lynn Cole / Laboratory
Laboratory
Experiments, research notes, mad science, and things in progress.
Lightshow: an artboard of slices
A local artboard prototype where slices connect page layers and states, and can target or affect other slices.
Hardening the coding agent across models and integrations
Hardening a coding agent means fixing integration seams, recertifying models and making the same workflow hold across providers.
A powerful local model and a very hot Spark
A powerful local Qwen model meets a DGX Spark that runs uncomfortably hot. This is my experience with the original unit and its replacement.
Why I added an operator-reassurance layer
A long-running agent that works silently can look frozen. Progress narration became a necessary part of the product, even when the underlying work was going well.
Product hardening is finding the seams
Product hardening means finding the seams between features, models and workflows, while reducing the task-switching cost for the human.
A coding-agent hardening checklist
A coding-agent hardening checklist: model support, hooks, scheduling, tooling, skills and observability, with the remaining integration work still in flight.
Moving project state outside the blast radius
Shadow repositories protected project state, until the project’s tooling tried to use them. Moving that state outside the project changed the failure boundary.
When QA develops its own theory of the workflow
QA refused to stop using terminal commands it no longer had permission to run. The planner negotiated; the agent filed another bug.
Changing the runtime layer and rebuilding the interface
Changing the model runtime led to a scheduler rewrite, document ingestion and interface work—and added another five days to the project.
Reading layered context-control surfaces in Claude Code
A review of Claude Code’s layered context-control machinery: prompts, hidden reminders, tool serialization and parallel permission decisions.
A corporate-lobby simulation for agent evaluations
A corporate-lobby simulation could test agents against grudges, deliveries, banking, invoices and the drama that makes businesses difficult.