Technology Radar, practical analyses and project updates.
- Analysis
Before comparing agents, check the benchmark version
Terminal-Bench 2.1 repaired 28 of 89 tasks. Compare agents on the same version.
Analysis
- Lab
The tool was allowed. The recipient was not.
A two-case fixture for catching recipient substitution before an agent sends anything.
Lab
- Radar
Speed is only part of the story. Reliability becomes a metric.
Terminal-Bench 2.1, KOSMOS kernels, robot failure prediction and sensor security.
Technology Radar
- Update
From analysis to a working template
The collection grew to 14 materials. It added handoff notes, targeted reading, tool responses, caching, acceptance checks and stop conditions. The recipes use synthetic examples; they do not report measured savings.
Project updates
- Update
Five primary sources and what they support
The collection added OpenAI documentation on caching and evaluation, alongside work on tool responses and Anthropic materials. The date I reviewed a source is separate from its publication date; an unknown date stays unknown.
Project updates
- Update
The first knowledge collection
Six materials cover context, tools, retries, parallel work, cost accounting and comparisons. Each entry explains when to use the technique and where its limits are.
Project updates