{"slug": "experimenting-with-intent-cells-for-rerunnable-llm-workflows", "title": "Experimenting with intent cells for rerunnable LLM workflows", "summary": "A developer is experimenting with a syntax called Intent-Cell Coding (ICC DSL) for creating rerunnable LLM workflows, where each step is an \"intent cell\" that combines readable task text with execution details. The approach aims to address reproducibility challenges by recording exact input versions, hashes, and upstream artifact references, sparking discussion on best practices for maintaining state in LLM demos and workflows.", "body_md": "I am experimenting with a small syntax/workflow idea for multi-step LLM work.\n\nThe 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:\n\nChat is good for exploration, but it is a weak record. Scripts are reproducible, but often too rigid for work that starts exploratory.\n\nThe 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.\n\nA cell keeps readable task text together with execution details:\n\n```\nc1 Collect\n> auto\n@file -markdown context.md\n\nc2 Review\n> fast\n%from c1\n@file -json review.json\n\nc3 Final\n> best\n%from c1\n%from c2\n@file -markdown final.md\n```\n\nThe 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.\n\nI am curious how people here think about reproducibility for LLM demos and workflows.\n\nDo you usually keep this state in notebooks, app logs, model/dataset cards, traces, config files, or generated run manifests?", "url": "https://wpnews.pro/news/experimenting-with-intent-cells-for-rerunnable-llm-workflows", "canonical_source": "https://discuss.huggingface.co/t/experimenting-with-intent-cells-for-rerunnable-llm-workflows/177909#post_1", "published_at": "2026-07-16 20:30:14+00:00", "updated_at": "2026-07-16 20:38:43.271812+00:00", "lang": "en", "topics": ["large-language-models", "developer-tools", "artificial-intelligence"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/experimenting-with-intent-cells-for-rerunnable-llm-workflows", "markdown": "https://wpnews.pro/news/experimenting-with-intent-cells-for-rerunnable-llm-workflows.md", "text": "https://wpnews.pro/news/experimenting-with-intent-cells-for-rerunnable-llm-workflows.txt", "jsonld": "https://wpnews.pro/news/experimenting-with-intent-cells-for-rerunnable-llm-workflows.jsonld"}}