The latest articles on PromptZone - AI Prompts, Guides and Tools for Builders by Jennifer Jasmine (@caninecalc). https://www.promptzone.com/caninecalc https://promptzone-community.s3.amazonaws.com/uploads/user/profile_image/40247/5d26bf72-a4e4-4a3b-b9e6-9daf3e92889f.png https://www.promptzone.com/caninecalc en Jennifer Jasmine Tue, 20 Oct 2026 00:09:14 +0000 https://www.promptzone.com/caninecalc/how-i-use-ai-prompts-to-ship-free-pet-care-calculators-37gb https://www.promptzone.com/caninecalc/how-i-use-ai-prompts-to-ship-free-pet-care-calculators-37gb <p>I run a small project called CanineCalc that publishes free dog calculators and research-backed care guides — puppy weight and size estimators, calorie and feeding calculators, a crate size finder, and more.</p> <p>Most of the tooling gets prototyped with a repeatable prompt workflow before I write production code. Here is the version I keep coming back to:</p> <h2 id="1-spec-first-code-second"> 1. Spec first, code second </h2> <p>My opening prompt never asks for code. It asks the model to write a plain-English spec: inputs, outputs, edge cases, and the formulas the calculator needs. Reviewing that spec first catches most of the mistakes that would otherwise hide inside generated code.</p> <h2 id="2-make-the-model-state-its-assumptions"> 2. Make the model state its assumptions </h2> <p>Pet care is full of rules of thumb that change by breed, age, and activity level. I prompt the model to list every assumption it bakes into a formula and to flag anything it is uncertain about. The flagged items become the parts I research and pin down myself, which keeps the final tool honest.</p> <h2 id="3-generate-the-unhappy-path"> 3. Generate the unhappy path </h2> <p>The most useful prompt in the sequence asks for edge cases: empty inputs, extreme values, mixed units. I keep that list next to the calculator and turn it into validation rules and test cases.</p> <h2 id="4-iterate-in-the-open"> 4. Iterate in the open </h2> <p>Once the calculator ships, real users find the inputs I never imagined. Each round of feedback becomes a new prompt: describe the confusing case, ask for the cleanest way to handle it, and update the tool. The loop is slow but it compounds.</p> <p>One example of the result is a <a href="https://caninecalc.com/dog-calorie-calculator/" rel="nofollow ugc noopener noreferrer">free dog calorie calculator</a> — it estimates daily calories from a dog's weight and activity level, and every assumption it uses is spelled out on the page.</p> <p>The takeaway: prompts are cheap and published tools are forever. Write the spec with the model, verify the assumptions yourself, and ship the calculator.</p> ai tutorial