Your AI agent forgets why. Give it a decision record A developer released Design Decision Method, an MIT-licensed Agent Skill that adds a structured "decision record" step to AI-assisted interface work so coding agents retain the reasoning behind design choices rather than only the resulting code. The method, which follows the open Agent Skills format and installs into Claude Code, Cursor, Gemini CLI and Codex, asks agents to log each costly-to-reverse decision with its frequency, familiarity, error cost, device, chosen pattern and rationale, plus an honest validation status such as proposed, heuristic review or manual test. The author notes the approach is untested and that whether it saves time has not been measured. You spend a session getting an order form right. One page, not three steps. A review summary before submit. Delivery date where people actually look for it. Then a new prompt regenerates the form, and the agent goes back to a three-step wizard, because nothing told it why you chose otherwise. The agent kept the code. It did not keep the reasons. Design Decision Method handles this with step 4 of its workflow: the decision record. For a choice that would be costly to undo, the method asks you or your agent to record: It also asks you to judge effort in a specific way: compare the effort to read, remember, enter, navigate, and recover, rather than counting clicks or visible elements. A three-step flow has fewer fields per screen. That does not make it less effort if people have to go back to check what they entered on step one. Two more rules keep the record honest: Say you run a small print shop at example.com, and you ask your agent to build the order form. This is an illustration of how the procedure applies, not a case study or a measured result. The decision row looks like this: | Decision | Frequency | Familiarity | Error cost | Device | Pattern chosen | Reason | |---|---|---|---|---|---|---| | Order form layout | Occasional, once per order | Mostly first-time customers | Medium: a wrong size or quantity means a reprint | Phone first | One page, grouped sections, review summary before submit | Customers need to see size, quantity, and price together to catch mistakes. Splitting them across steps adds recall effort at the point of decision. | If a source you cite recommends a different pattern for this form, that is where an adaptation line goes, in the same three-part form. The record also carries a short validation status, because step 6 of the method asks for an honest evidence label on each result: proposed, heuristic review, automated check, manual test, or user research. For this form it might read: Untested stays untested. The record says so instead of implying the form works. Next week you ask the agent to add a "rush delivery" option. The following prompt starts from that record. The agent can see the form is one page for a reason, and that the reason is error cost, not taste. It adds the option inside the existing structure instead of reinventing the flow. A person still checks the result. The method does not measure how many prompts that removes, and whether it saves time has not been measured. The decision record is proportional. A small change gets a few lines. The repo's design record template is a scaffold, not mandatory overhead. Save the record with the work as docs/design/