# isnan lab — Small experiments. Useful outcomes.

> isnan lab: every experiment I run, with the question behind it, what came out, and what is still open. Small experiments. Useful outcomes.

- Author: Falah Isnan (https://falah-isnan.com/)

## Experiments

- [RAG vs Markdown wiki](https://lab.falah-isnan.com/experiments/rag-vs-markdown-wiki): The same knowledge base built twice: a RAG index, and a Markdown LLM Wiki linked by hand. Neither method won outright. Interim result: RAG leads on token efficiency and speed, and that lead widens as the knowledge base grows. The Markdown LLM Wiki leads on maintainability and predictability. For a low-to-mid knowledge base that you wrote yourself, the Markdown approach was the more effective of the two: the relationships are explicit, so what the model will read is something you can anticipate.
- [AI Behavioral Runtime](https://lab.falah-isnan.com/experiments/ai-behavioral-runtime): Steering a model's reasoning along principles defined in advance. It lifts the benchmark, and every step pays for it. Interim result: Steering works. Forcing a model to reason along defined principles lifted the benchmark without touching native reasoning, which is the result the experiment was after. It is not free: the steering is paid on every step, and anything the principles never described is exactly as unsolved as it was before.
- [Workflow Runtime](https://lab.falah-isnan.com/experiments/workflow-runtime): Letting the model author its own workflow and spawn agents for it. Often it works; often it spends tokens and hours on work nobody needed. Interim result: A workflow that has been designed and tested beats pointing the model at every problem and letting it author its own. Dynamic workflows are not written off — but before that path is worth taking, Workflow Runtime has to bound the work an agent may do and make it explicit when the process must stop.

## Elsewhere

- [Falah Isnan](https://falah-isnan.com/): Falah Isnan builds systems, products, and interfaces. Selected work, how I think, and how to get in touch.
- [isnan tools](https://tools.falah-isnan.com/): Free, public tools by Falah Isnan. Practical utilities for recurring problems.
- [GitHub](https://github.com/mohfalahisnan)