← All topics

#measurement

  1. What my AI logs can actually tell me

    Looking back through my workflow history showed how much activity I could count, and how much measurement I still needed.

  2. Stopping a context optimization

    A representative compaction test lost important state, so I stopped the experiment and returned to shorter work stages.

  3. Checking the age of the evidence

    A stale error changed a workflow diagnosis, and exposed why I need timestamps and attribution alongside usage numbers.

  4. Checking what my AI usage numbers mean

    An unexpected quota reset led me to examine pricing fallbacks, source freshness and the difference between estimates and spend.

  5. Measuring why local AI felt slow

    A slow greeting pushed me to separate model loading, instruction processing and queued work from response generation.