I wrote a profiling tool for agentsWhile building an agent for a client, we hit a scaling problem: a coordinator agent had 4-5 subagents each with 15-20 tool calls. Each tool result got appended to the context, then what started as a rApr 9, 2026·2 min read
Applied AI Digest: Volume 1Top links and resources from Fractional AI, curated for AI engineers. Mar 18, 2026·2 min read
The "Quick Fix" That Works: Runtime Patching in PythonMotivation 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 wFeb 25, 2026·4 min read
If I could turn back timeHave 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, 2026·3 min read
Your Evals Have a Rotten Tomatoes ProblemYou 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, pouringFeb 12, 2026·8 min read
The Virtues of Showing Your Work: Do LLM Explanations Actually Help?If you've spent any time prompting large language models, you've probably heard of Chain of Thought (CoT) reasoning—the technique of asking an LLM to "show its work" by generating intermediate reasoniFeb 5, 2026·5 min read