Tests as Prompts — an Unexpected Superpower

Writing a test first is not just good engineering. It is the clearest possible prompt for an AI. Let's use tests to make AI code reliable.

35 min · Reviewed 2026

A Test Is an Executable Prompt

A test says: when I give the function this input, I expect exactly this output. That is the most precise way to describe behavior that exists. If you paste a failing test and ask the AI to make it pass, you get amazingly focused results.

The red-green-refactor loop, with AI

Write a test that fails (red)
Ask the AI to write the function to make it pass (green)
Check the code works and is readable
Ask the AI to clean it up without breaking tests (refactor)

A concrete example in Python

# Step 1: write the tests first def test_add_positive(): assert add(2, 3) == 5 def test_add_negative(): assert add(-1, -1) == -2 def test_add_zero(): assert add(0, 42) == 42 # Step 2: paste the tests into your AI chat and say: # "Write the `add` function so all three tests pass." # Step 3: the AI almost always produces: def add(a, b): return a + b # Step 4: run pytest. If green, ship it.Writing the tests first gives the AI an unambiguous target. No room for misinterpretation.

Ask the AI to help write tests too

You do not need to write every test by hand. Give the AI the function signature, ask for test cases including edge cases, then review the list. You will often find a case you had not considered — that is the point.

Fast frameworks to know

Language	Framework	Command
Python	pytest	pytest
TypeScript	Vitest	npx vitest
JavaScript	Jest	npm test
Go	testing (built-in)	go test ./
Rust	cargo test	cargo test

Tests are the only prompt that runs.
— A TDD-loving engineer

The big idea: a test is a prompt the machine can verify. Writing tests first turns every AI coding session into a tight loop: target, generate, check, done.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-coding-tests-as-prompts-builders

What is the main idea of "Tests as Prompts — an Unexpected Superpower"?
1. Writing a test first is not just good engineering. It is the clearest possible prompt for an AI. Let's use tests to make AI code reliable.
2. Use AI as the final authority for the whole decision
3. Avoid checking the answer once it sounds polished
4. Focus only on speed instead of judgment
Which concept is most central to "Tests as Prompts — an Unexpected Superpower"?
1. assertions
2. test-driven development
3. red-green-refactor
4. specification
Which use of AI fits this topic best?
1. Let the AI decide what matters without your review
2. Use the answer before checking whether it fits the situation
3. Write a test that fails (red)
4. Use the first answer without checking it
What should a careful learner remember about "Review before you run"?
1. AI code is a first draft. Read through it, understand each line, and test on sample inputs before merging into real projects.
2. Skip the context so the tool can guess faster
3. Treat the output as private even after sharing it online
4. Use the answer without checking the source
You want to use AI after this lesson. What is the safest next step?
1. Act immediately because the AI answer is written clearly
2. Use the AI answer as a draft, then check it against a reliable source.
3. Hide uncertainty so the final answer looks cleaner
4. Use private or sensitive details before checking permission
How should AI output about test-driven development be treated?
1. As proof that no other source is needed
2. As a replacement for context, consent, or expert review
3. As a draft or helper output that still needs human judgment and verification
4. As something that becomes correct when it sounds confident
Name one way to verify an AI answer about test-driven development.
Which action would help you apply "Tests as Prompts — an Unexpected Superpower" responsibly?
1. Use the tool to avoid thinking through the tradeoff
2. Keep going even if the output conflicts with a trusted source
3. Use the first answer without checking it
4. Ask the AI to write the function to make it pass (green)

← Back to interactive lesson

Tendril · Builders · AI-Assisted Coding

Tests as Prompts — an Unexpected Superpower

Writing a test first is not just good engineering. It is the clearest possible prompt for an AI. Let's use tests to make AI code reliable.

35 min · Reviewed 2026

A Test Is an Executable Prompt

The red-green-refactor loop, with AI

Write a test that fails (red)
Ask the AI to write the function to make it pass (green)
Check the code works and is readable
Ask the AI to clean it up without breaking tests (refactor)

A concrete example in Python

# Step 1: write the tests first def test_add_positive(): assert add(2, 3) == 5 def test_add_negative(): assert add(-1, -1) == -2 def test_add_zero(): assert add(0, 42) == 42 # Step 2: paste the tests into your AI chat and say: # "Write the `add` function so all three tests pass." # Step 3: the AI almost always produces: def add(a, b): return a + b # Step 4: run pytest. If green, ship it.Writing the tests first gives the AI an unambiguous target. No room for misinterpretation.

Ask the AI to help write tests too

Fast frameworks to know

Language	Framework	Command
Python	pytest	pytest
TypeScript	Vitest	npx vitest
JavaScript	Jest	npm test
Go	testing (built-in)	go test ./
Rust	cargo test	cargo test

Tests are the only prompt that runs.
— A TDD-loving engineer

The big idea: a test is a prompt the machine can verify. Writing tests first turns every AI coding session into a tight loop: target, generate, check, done.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-coding-tests-as-prompts-builders

What is the main idea of "Tests as Prompts — an Unexpected Superpower"?
1. Writing a test first is not just good engineering. It is the clearest possible prompt for an AI. Let's use tests to make AI code reliable.
2. Use AI as the final authority for the whole decision
3. Avoid checking the answer once it sounds polished
4. Focus only on speed instead of judgment
Which concept is most central to "Tests as Prompts — an Unexpected Superpower"?
1. assertions
2. test-driven development
3. red-green-refactor
4. specification
Which use of AI fits this topic best?
1. Let the AI decide what matters without your review
2. Use the answer before checking whether it fits the situation
3. Write a test that fails (red)
4. Use the first answer without checking it
What should a careful learner remember about "Review before you run"?
1. AI code is a first draft. Read through it, understand each line, and test on sample inputs before merging into real projects.
2. Skip the context so the tool can guess faster
3. Treat the output as private even after sharing it online
4. Use the answer without checking the source
You want to use AI after this lesson. What is the safest next step?
1. Act immediately because the AI answer is written clearly
2. Use the AI answer as a draft, then check it against a reliable source.
3. Hide uncertainty so the final answer looks cleaner
4. Use private or sensitive details before checking permission
How should AI output about test-driven development be treated?
1. As proof that no other source is needed
2. As a replacement for context, consent, or expert review
3. As a draft or helper output that still needs human judgment and verification
4. As something that becomes correct when it sounds confident
Name one way to verify an AI answer about test-driven development.
Which action would help you apply "Tests as Prompts — an Unexpected Superpower" responsibly?
1. Use the tool to avoid thinking through the tradeoff
2. Keep going even if the output conflicts with a trusted source
3. Use the first answer without checking it
4. Ask the AI to write the function to make it pass (green)

← Back to interactive lesson