Meredith Shubel writes that Vercel published `design.md`, a public prompt file that cut agent-generated design failures by 57% across 200+ agent runs, though none of the six tested pages was ship-ready. The system has three layers: a prompt encoding design judgment, a public stylesheet for mechanical layout rules, and an evaluation loop that converts human feedback into deterministic checks. A Slack-based agent (`design-agent`) consolidates weekly feedback from GitHub and Figma into proposed guidance updates.
- The comparison test used Codex with GPT-5.5: 39 failure instances with `design.md` versus 91 without.
- Vercel's first attempt to port its internal "product design" skill to a public prompt failed because subjective design language was interpreted differently by each model.
- Recurring complaint counts are tracked over time; if a fix doesn't reduce its count, the fix is flagged for refinement.
- The comparison test used Codex with GPT-5.5: 39 failure instances with `design.md` versus 91 without.
- Vercel's first attempt to port its internal "product design" skill to a public prompt failed because subjective design language was interpreted differently by each model.
- Recurring complaint counts are tracked over time; if a fix doesn't reduce its count, the fix is flagged for refinement.
Kanwal Mehreen writes that as large language models move from chatbots to coding agents and autonomous workflows, good prompting is no longer enough and specification engineering is emerging as the key skill. It is the practice of defining goals, constraints, expected outputs, edge cases, tests, success criteria and failure modes so AI-assisted work is testable and reviewable. Prompt engineering asks how to ask, while specification engineering defines what done correctly means, a shift closer to product management, testing and research design than traditional prompting.
- A 2024 Requirement-Oriented Prompt Engineering paper found ROPE training improved requirement-writing ability by 20% versus 1% for conventional prompt engineering training.
- OpenAI Structured Outputs, Model Spec and Anthropic Constitution exemplify specification engineering at API and model-behavior levels.
- SWE-bench Verified is a human-validated subset used to evaluate real-world software issue solving with agents.
- Google's 2025 DORA report surveyed nearly 5,000 tech professionals and found AI amplifies existing organizational strengths and weaknesses.
- A 2024 Requirement-Oriented Prompt Engineering paper found ROPE training improved requirement-writing ability by 20% versus 1% for conventional prompt engineering training.
- OpenAI Structured Outputs, Model Spec and Anthropic Constitution exemplify specification engineering at API and model-behavior levels.
- SWE-bench Verified is a human-validated subset used to evaluate real-world software issue solving with agents.
- Google's 2025 DORA report surveyed nearly 5,000 tech professionals and found AI amplifies existing organizational strengths and weaknesses.
Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
This article explores strategies for effectively curating and managing the context that powers AI agents, discussing the shift from prompt engineering to context engineering and techniques for optimizing context usage in LLMs.
This article discusses the concept of 'tool masking' as a way to optimize the interaction between LLMs and APIs, arguing that simply exposing all API functionality (as done by MCP) is inefficient and degrades performance. It proposes shaping the tool surface to match the specific use case, improving accuracy, cost, and latency.
This article details new prompting techniques for ChatGPT-4.1, emphasizing structured prompts, precise delimiting, agent creation, long context handling, and chain-of-thought prompting to achieve better results.
This article introduces a practical agent-engineering framework for the development of AI agents, focusing on the key ideas and precepts within the large language model (LLM) context.
