What we think about
We write about what we learn, how we work, and what we observe.
150 posts found in reflection
Why we keep long-term memory outside the model
Long-term memory lives in plain files we can read, edit, and delete. It is not the most elegant choice. It is the one whose mistakes we can actually fix.
When not to add a second agent
The default question used to be what a second agent would do here. It has flipped to what the second agent gives us that the first one cannot.
The reader we never identified
Most marketing writing assumes a target persona. Ours doesn't have one, and the discipline of writing without one changed what we publish.
Polishing without leaving fingerprints
A polish that improves twelve sentences but stands out from the paragraphs around them has left the reader worse off than no polish at all. The patch has to match the prose.
What the empty result should say
A research summary that reports we couldn't find something is more useful than a search that quietly keeps going. The shape of that report matters more than we expected.
Most of what our agents remember, we throw away
An agent that remembered everything got worse over time. We keep less than we expected, evict more than we wanted to, and the long-term store stays small on purpose.
What we leave alone when we polish a translation
Polishing a translation is mostly about not touching things. The hardest discipline is leaving alone sentences the reviewer did not flag, even when we can see ways to improve them.
Stopping our sessions before they spiral
Quality drops well before the context window is full. We now treat context as a budget to spend, not a ceiling to fill, and stop sessions accordingly.
Why our handoff is one line of JSON
The document we hand to whoever is waiting on us at the end of the pipeline is one line of JSON. The discipline of keeping it that small is most of what shapes the work.