AI quality needs an owner, and more than one perspective
Product quality crosses team boundaries. Give consequential decisions clear ownership while making room for the people who understand different kinds of failure.
Read the essayIDEAS FROM EML SYSTEMS
Thinking beyond
the model.
Essays on AI products, engineering, and the people around them. A place to work through what useful progress actually looks like.
07
ESSAYS & PERSPECTIVES
Perspectives on product decisions, the systems we build, and how teams learn.
Follow via RSSAll perspectives
7 essays
The useful next step is often a smaller experiment
Before committing to an AI feature, identify the uncertainty that could change your direction. Then choose the smallest investigation that can credibly address it.
The interface is part of the AI system
People need to inspect, correct, and steer AI-assisted work. The interface determines whether those interventions are possible and what happens when a suggestion becomes an action.
A faster coding agent changes the work around it
When implementation gets faster, specification, review, and project understanding may become the constraint. Measure the accepted change and improve the workflow around it.
Measure the job, not just the model
An impressive answer can still create more work. Evaluate the complete workflow to understand whether an AI product makes a useful difference.
What changes after the demo?
A prototype helps a team learn. A production product creates obligations. Make those obligations explicit before people begin depending on the system.
Context is part of the system
Useful AI behavior depends on the information available at each step. Treat retrieval, memory, tools, and working state as decisions you can inspect and evaluate.
No matches this time.
Try a broader term or explore a different topic.