https://hexproof.dev/datagrams/Recent content in Datagrams on hexproofHugoen-ushttps://hexproof.dev/datagrams/fossil-record-harness-engineering/Wed, 08 Apr 2026 00:00:00 +0000https://hexproof.dev/datagrams/fossil-record-harness-engineering/<p>Every AI coding tool solves the same fundamental problem: fitting the right information into a fixed-size context window so an LLM can write correct code. Claude Code (v2.1.88, source maps), <a href="https://github.com/Aider-AI/aider">Aider</a> (v0.86.3, Apache 2.0), Cursor (leaked prompts, v1.0-2.0), Windsurf (leaked prompts, Waves 1-11), and GitHub <a href="https://github.com/microsoft/vscode-copilot-chat">Copilot</a> (vscode-copilot-chat v0.43.0, MIT) solve it five completely different ways.</p> <p><a href="https://x.com/tobi/status/1935533422589399127">Tobi Lutke</a> named the discipline &ldquo;context engineering&rdquo; &ndash; &ldquo;the art of providing all the context for the task to be plausibly solvable by the LLM.&rdquo; <a href="https://mitchellh.com/writing/my-ai-adoption-journey">Mitchell Hashimoto</a> pushed further to &ldquo;harness engineering&rdquo; &ndash; &ldquo;anytime you find an agent makes a mistake, you take the time to engineer a solution such that the agent never makes that mistake again.&rdquo; Each architecture is a fossil record of the constraint its team built around. Claude Code: cost. Aider: model portability. Cursor: edit speed. Windsurf: autonomy. Copilot: model plurality. What follows is how each team engineered their harness, examined through source code, leaked prompts, and open-source repositories.</p>