Fractional AI Engineering Blog

Write

Applied AI Digest: Volume 3

Apr 15, 20263 min read

I wrote a profiling tool for agents

Apr 9, 20262 min read

The Prompt That Writes Itself

Prompt engineering is iteration. You read what failed, tweak the prompt, run it again, repeat. It's a tedious, but inextricable, part of building with LLMs. GEPA (Genetic-Pareto) takes that loop off y

May 15, 20264 min read

Applied AI Digest: Volume 2

Apr 1, 20264 min read

Stop designing chatbots

Mar 30, 20265 min read

Artifact-driven AI creation

How artifact-based thinking makes AI-assisted creation precise and cumulative

Mar 27, 20268 min read

Using MCPs with evals

When I joined Fractional AI, one of the first lessons I learned was that evaluations drive every major decision in our projects, from first prototype through post-launch improvement. In our initial cu

Mar 19, 20263 min read

Applied AI Digest: Volume 1

Top links and resources from Fractional AI, curated for AI engineers.

Mar 18, 20263 min read

The "quick fix" that works: runtime patching in Python

Motivation We wanted to generate demo videos with the python library Supervision but they wouldn't play in Chrome. There was a one-line fix buried inside the library -- but the public API gave us no w

Feb 25, 20264 min read

If I could turn back time

Have you ever exclaimed after a few hours engaged in some fruitless activity, "Well, that's X hours of my life I'll never get back"? Or, when in a reflective mood, "I wish I knew this when I was 16!"?

Feb 19, 20263 min read

Your evals have a Rotten Tomatoes problem

You push a change to a prompt and your eval score drops from 0.91 to 0.84. Something got worse, but the score doesn’t tell you what. So you start re-running the pipeline, tweaking your inputs, pouring

Feb 12, 20268 min read

Command Palette

Latest articles