You’re Not Thinking Big Enough: Rebuilding Food Systems with AI Agents — Cody Menefee, Firecrawl
Source
AI Engineer
Author
AI Engineer
Date
Key takeaways · AI-distilled
Cody Menefee says only about 3% of cattle finish on pasture largely because of labor: good rotational grazing means moving the herd, fences, and water to a new one-day paddock every day.
GPS collars with virtual fences can move animals, but he argues they solve the fence, not the decision: grass regrows differently after drought, rain, or trampling, so someone still has to go look.
His proposal puts a LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition → in the loop, fed animal locations, drought conditions, and grass height (for example from a cheap trail cam aimed at a measuring stick), to suggest the next paddock for a human to confirm.
He lists three blockers: a grazing knowledge base (he is scraping farmer YouTube and papers into Open Pasture), a vision layer for biomass and biodiversity, and collar makers that lock out outside software.
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
Why it matters
A concrete, unusual application of agentic AI to regenerative grazing decisions, naming specific technical blockers like no legal drone autonomy and locked-down GPS collar APIs, which builders in physical-world domains will recognize.
videoFrom Ingestion to Agents: How AI Teams Build on Document Intelligence — Adit Abraham, Reducto
videoFrom VLM/VLA's to Embodied Agents — Armen Aghajanyan, Perceptron AI
videoSkill issue: stop deploying vision language models, use them with Skills — Merve Noyan, Hugging Face
videoFrom Scratch to SOTA: Training a 3B State-Space Vision Model — Krishna Prasad Srinivasan, Sarvam
