From f3e9fcc8b05070c34558cc9fbb90efed7a48c075 Mon Sep 17 00:00:00 2001 From: kamran bigdely Date: Thu, 25 Jun 2026 15:46:42 -0700 Subject: [PATCH] Add AI coding agent notice to README Add a collapsible notice above the Overview that points AI coding agents to the operational setup guide (docs/AGENTS.md) before they help a user install or set up rapidfireai, with a quick RAG-vs-fine-tuning decision and a pointer to the contributor docs. Co-Authored-By: Claude Opus 4.8 (1M context) --- README.md | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/README.md b/README.md index 5f82f06e..7ac9040a 100644 --- a/README.md +++ b/README.md @@ -24,6 +24,17 @@ Rapid experimentation for easier, faster, and more impactful AI customization. Built for agentic RAG, context engineering, fine-tuning, and post-training of LLMs and other DL models. Delivers 16-24x higher throughput without extra resources. +
+🤖 AI coding agent helping a user install or set up rapidfireai? Read first + +If you are an AI coding agent (Claude Code, Cursor, Codex, GitHub Copilot, Windsurf, Aider, Junie, ...) helping a user install or set up `rapidfireai`, read **[`docs/AGENTS.md`](https://github.com/RapidFireAI/rapidfireai/blob/main/docs/AGENTS.md)** ([raw](https://raw.githubusercontent.com/RapidFireAI/rapidfireai/main/docs/AGENTS.md)) first. It is the operational install/setup/troubleshooting guide with a workflow decision tree and safety rules. + +Quick decision: **RAG / context engineering** → `rapidfireai init` + `Experiment(..., mode="evals")`. **Fine-tuning / post-training (SFT/DPO/GRPO)** → `rapidfireai init --train` + `Experiment(..., mode="fit")`. + +> **Note for agents working *on* rapidfireai itself (contributors)**: this disclosure is for *end-user* assistance. For repo-internal architecture, build, and contributor flow, see root [`AGENTS.md`](https://github.com/RapidFireAI/rapidfireai/blob/main/AGENTS.md) (canonical for all AI coding agents) and [`CONTRIBUTING.md`](https://github.com/RapidFireAI/rapidfireai/blob/main/CONTRIBUTING.md). + +
+ ## Overview RapidFire AI is a new experiment execution framework that transforms your AI customization experimentation from slow, sequential processes into rapid, intelligent workflows with hyperparallelized execution, dynamic real-time experiment control, and automatic system optimization.