# Experimenting with intent cells for rerunnable LLM workflows

> Source: <https://discuss.huggingface.co/t/experimenting-with-intent-cells-for-rerunnable-llm-workflows/177909#post_1>
> Published: 2026-07-16 20:30:14+00:00

I am experimenting with a small syntax/workflow idea for multi-step LLM work.

The problem I keep running into is that the useful part of an LLM workflow is not just the prompt. It is the trail around it:

Chat is good for exploration, but it is a weak record. Scripts are reproducible, but often too rigid for work that starts exploratory.

The shape I am testing is a local-first notebook where each step is an “intent cell”. I am calling the syntax ICC DSL, for Intent-Cell Coding.

A cell keeps readable task text together with execution details:

```
c1 Collect
> auto
@file -markdown context.md

c2 Review
> fast
%from c1
@file -json review.json

c3 Final
> best
%from c1
%from c2
@file -markdown final.md
```

The part I am thinking hardest about is file/context identity. A rerun is not really comparable unless the system records exact input versions, hashes, snapshots, retrieval results, or upstream artifact refs.

I am curious how people here think about reproducibility for LLM demos and workflows.

Do you usually keep this state in notebooks, app logs, model/dataset cards, traces, config files, or generated run manifests?