Start with the outcome
Describe what should exist when the work is finished. Include the audience when it changes the result.
A practical guide to better conversations with AI
Learn the essentials, answer a few focused questions, and leave with a complete prompt you can paste into ChatGPT.
Your answers stay on this device. Nothing is uploaded.
The learning path
Describe what should exist when the work is finished. Include the audience when it changes the result.
Share facts, history, and constraints that could materially change the answer.
Name the files, measurements, screenshots, dates, and sources ChatGPT should use.
Specify the format, detail, tone, length, and decision the response should support.
For ambiguous work, let ChatGPT ask only the questions that would change its approach.
Keep the good parts and request precise changes instead of restarting the conversation.
Ask for source checks, calculation checks, assumptions, and unresolved uncertainty.
Carry forward decisions, constraints, current status, files, and the next concrete step.
Context builder
Spec-driven development
Build a project constitution and a testable feature specification, then hand the Markdown to a coding agent.
Have the agent map the current architecture, behaviors, tests, constraints, and risky areas. Turn confirmed reality into the first constitution before specifying changes.
When the same standards work across projects, save the steps, checks, and output format as a reusable skill. Keep project-specific facts in each project’s constitution.
Review the plan and evidence. Small slices, clear acceptance criteria, and explicit validation reduce drift; they do not remove the need for engineering judgment.
Prompt library
Choose a template, replace the brackets, and copy it into ChatGPT.
Tips and strategies
The best context is the information that could change the result.
Label what you observed, what you suspect, and what remains unknown. This reduces false certainty.
Observed: [facts]\nSuspected: [hypothesis]\nUnknown: [gaps]Tell ChatGPT which file, person, standard, or current source takes priority if information conflicts.
Treat the approved specification as authoritative. Flag conflicts instead of choosing silently.One good example can communicate tone and structure better than a long explanation. Say what to copy from it.
Match the attached report's section order, but use the new project's facts.Clarification is valuable when an answer would change the work—not as a ritual before every task.
Ask up to three questions only if the answers materially affect your recommendation.Point to the exact weakness, protect what worked, and request a targeted revision.
Keep the analysis and evidence. Make the opening more direct and move the recommendation first.Before important work is finished, ask for a concrete check tied to how you will use it.
Before finishing, verify every action has an owner and due date; flag anything unsupported.