Llm – Sidequesting

tl;dr: This post describes my first current very rough approach to agentic development. This approach is heavy on docs, folder structure, and copious tools and scripts for verification feedback. My current approach is codified by the Winetech Standard Repo, which is a barebones skeleton of the structure and built-in agent ready documentation to get started on a new project. Actual Take-Aways Use ADRs Prune memories, AGENTS.md, and other context-filling documents regularly Provide a space to put observations found during their tasks so don’t get distracted and information doesn’t get lost Keep as much inside the repo as possible, to provide agents with the context on demand that they need Provide tools and scripts that can give negative feedback to the agents so they can quickly course-correct on their own Give them a runtime of your application to test against in a live setting. Static analysis is not enough. Table of Contents tl;dr: Actual Take-Aways Prerequisites Models Harnesses Subscriptions Project Ownership Folder Structure adr/ investigations/ tickets/ backlog.md Verification and Feedback Repo Tools AGENTS.md and Memories AGENTS.md Memories Skills Pruning files when they get too big or outdated Working with the Agents Prompting Style Corrections Lean into their biases and expectations for tools and docs Hooks and notifications Parallelization Some Usage Patterns “Wrap up” Handoff Documents Rewrite To Be Forward Looking Team A vs Team B Recent Worked Examples Reducing Token Spend on Backtracking during Failed Test Runs Test Suite Optimization Automation and Accessibility Migrating a Failing Robotics Sample From Gazebo to MuJoCo Prerequisites People get different results from the different workflows, tools, models and harnesses they use, so I’d like to set out what my particular set up looks like at the outset, so you can adjust your own expectations. …