Home › Prompt examples › Coding AI prompts: 23 copy-ready examples
Coding AI prompts: 23 copy-ready examples
23 prompts from 7 coding guides, ready to copy into any AI chat assistant.
Replace the [brackets] with your details. Every prompt comes from one of our full guides, which also covers which tool to use, the steps and the risks. Want a prompt for something else? Use the prompt builder.
Tasks on this page
- AI prompts to explain unfamiliar code 5
- AI prompts to write unit tests 3
- AI prompts to fix a failing build 3
- AI prompts to refactor code across files 3
- AI prompts to review a pull request 3
- AI prompts to turn an issue into a pull request 3
- AI prompts to generate a regex or SQL query 3
AI prompts to explain unfamiliar code
When to use: Walk through what a function or file does, line by line. Full guide: Explain unfamiliar code
Explain this [language] code to someone who knows basic programming but not this codebase: [paste]. Cover: what it's for, inputs and outputs, side effects (files, network, database), edge cases, and anything that looks like a bug. Refer to line numbers.
Walk through this code with the input [example input], step by step, showing the value of each variable as it changes. Tell me the final output and any point where it could crash.
I've opened a new project. Read the main entry point and folder structure, then give me a one-page map: what each folder does, where requests or data come in, and the 5 files I should read first.
This [language] code gives [actual result] but I expected [expected result] for input [input]. Here is the code and the error or output: [paste]. List the 3 most likely causes in order, how to test each one, and the smallest fix. Don't rewrite unrelated code.
Write [pytest/Jest/...] tests for this function covering: a normal case, an empty or missing input, a boundary value, and the edge cases you found. Explain what each test proves.
AI prompts to write unit tests
When to use: Generate tests for existing code and run them in an agent. Full guide: Write unit tests
Write [framework] unit tests for this function. Expected behaviour: [rules]. Cover normal input, edge cases ([list]) and errors. One-line comment per test explaining what it protects. [paste code]
Here are the function and its current tests. List behaviours and edge cases the tests don't cover, ranked by risk. Don't write code yet.
Review these tests: which ones would still pass if the function were broken? Which mock too much? Suggest fixes.
AI prompts to fix a failing build
When to use: Agent reads errors, edits code and re-runs until green. Full guide: Fix a failing build
Here is the failing build log and the command to reproduce it. Explain the root cause in plain English and propose a fix before editing anything. [log]
Fix the failing build on this branch. Rules: don't delete, skip or weaken tests; don't modify CI files; keep dependency changes minimal and explain each. Rerun [command] after each change.
Summarise every change you made, why, and anything that could affect production or other teams.
AI prompts to refactor code across files
When to use: Rename or restructure code across a repository with review. Full guide: Refactor across files
I want to [rename X to Y / split module Z / change signature of F]. List every file and reference you'd change, including config, templates and docs. Don't edit yet.
Apply the plan on this branch. Behaviour must not change; public API [names] stays the same. Run [test command] after the change and report results.
Search the repository for remaining references to [old name], including strings, comments, docs and config. List them and say which are safe to change.
AI prompts to review a pull request
When to use: Get AI review comments on pull requests. Full guide: Automated PR review
Review this pull request diff. Focus on bugs, security issues and missing tests. For each comment give the file and line, why it matters and a suggested fix. Skip style nits. [diff]
Draft review guidelines for an AI reviewer on our [language/framework] repository: what to flag, what to ignore, severity levels. Keep it under 200 words.
Summarise this pull request for a human reviewer: what changed, risky areas, and the 3 files to read first.
AI prompts to turn an issue into a pull request
When to use: Assign an issue to a cloud agent that branches, codes and opens a PR. Full guide: Issue to pull request
Assign issue #17 to the cloud agent with instructions to add tests.
Assign issue #17 to the cloud agent with instructions to add tests. I'm new to this: explain each step in plain words and ask me for anything you need before starting.
Assign issue #17 to the cloud agent with instructions to add tests. When you finish, list any assumptions you made, anything you're unsure about, and what I should double-check before using the result.
AI prompts to generate a regex or SQL query
When to use: Describe what you need and get a tested pattern or query. Full guide: Generate a regex or SQL query
Write a [regex flavour / SQL dialect] that [describe the goal]. These should match: [examples]. These should NOT match: [examples]. Explain each part in one line.
Explain this [regex / SQL query] line by line in plain English, then tell me which inputs it would get wrong: [paste]
Here is my [pattern / query] and the result on my sample. List 10 tricky inputs or data situations (empty values, accents, time zones, duplicates) it might mishandle, and give a fixed version.
More prompt examples
All prompt examples · Writing & editing · Research · IT ops & DevOps · Customer support · Data analysis · Automation & agents · Image & video · Personal productivity · Education & learning · Marketing · Sales · HR & recruiting · Finance & accounting · Legal & compliance · Healthcare admin · Cybersecurity · Product & design · Personal life & home · Travel · Content creation · Small business
See also: Best AI tools for coding