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

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

What is the core idea behind "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. Generate cleanup PR descriptions referencing the original ticket.
3. Diff JSON/YAML configs across environments and call out semantic changes
4. python
Which term best describes a foundational idea in "Tests as Prompts — an Unexpected Superpower"?
1. assertion
2. test-driven development
3. red-green-refactor
4. pytest
A learner studying Tests as Prompts — an Unexpected Superpower would need to understand which concept?
1. test-driven development
2. red-green-refactor
3. assertion
4. pytest
Which of these is directly relevant to Tests as Prompts — an Unexpected Superpower?
1. test-driven development
2. assertion
3. pytest
4. red-green-refactor
Which of the following is a key point about Tests as Prompts — an Unexpected Superpower?
1. Write a test that fails (red)
2. Ask the AI to write the function to make it pass (green)
3. Check the code works and is readable
4. Ask the AI to clean it up without breaking tests (refactor)
Which of these does NOT belong in a discussion of Tests as Prompts — an Unexpected Superpower?
1. Generate cleanup PR descriptions referencing the original ticket.
2. Check the code works and is readable
3. Ask the AI to write the function to make it pass (green)
4. Write a test that fails (red)
What is the key insight about "The edge case checklist" in the context of Tests as Prompts — an Unexpected Superpower?
1. Generate cleanup PR descriptions referencing the original ticket.
2. Diff JSON/YAML configs across environments and call out semantic changes
3. Always ask: what about empty input, null, zero, negatives, duplicates, very large inputs, and unicode? Your tests should…
4. python
What is the key insight about "Do not let the AI write tests that test nothing" in the context of Tests as Prompts — an Unexpected Superpower?
1. Generate cleanup PR descriptions referencing the original ticket.
2. Diff JSON/YAML configs across environments and call out semantic changes
3. python
4. AI sometimes writes assertions that just re-state the code, like `assert result == result`.
Which statement accurately describes an aspect of Tests as Prompts — an Unexpected Superpower?
1. A test says: when I give the function this input, I expect exactly this output.
2. Generate cleanup PR descriptions referencing the original ticket.
3. Diff JSON/YAML configs across environments and call out semantic changes
4. python
What does working with Tests as Prompts — an Unexpected Superpower typically involve?
1. Generate cleanup PR descriptions referencing the original ticket.
2. 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 li…
3. Diff JSON/YAML configs across environments and call out semantic changes
4. python
Which of the following is true about Tests as Prompts — an Unexpected Superpower?
1. Generate cleanup PR descriptions referencing the original ticket.
2. Diff JSON/YAML configs across environments and call out semantic changes
3. 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, genera…
4. python
Which best describes the scope of "Tests as Prompts — an Unexpected Superpower"?
1. It is unrelated to ai-coding workflows
2. It applies only to the opposite beginner tier
3. It was deprecated in 2024 and no longer relevant
4. It focuses on Writing a test first is not just good engineering. It is the clearest possible prompt for an AI. Let
Which section heading best belongs in a lesson about Tests as Prompts — an Unexpected Superpower?
1. The red-green-refactor loop, with AI
2. Generate cleanup PR descriptions referencing the original ticket.
3. Diff JSON/YAML configs across environments and call out semantic changes
4. python
Which section heading best belongs in a lesson about Tests as Prompts — an Unexpected Superpower?
1. Generate cleanup PR descriptions referencing the original ticket.
2. A concrete example in Python
3. Diff JSON/YAML configs across environments and call out semantic changes
4. python
Which section heading best belongs in a lesson about Tests as Prompts — an Unexpected Superpower?
1. Generate cleanup PR descriptions referencing the original ticket.
2. Diff JSON/YAML configs across environments and call out semantic changes
3. Ask the AI to help write tests too
4. python

← 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

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

What is the core idea behind "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. Generate cleanup PR descriptions referencing the original ticket.
3. Diff JSON/YAML configs across environments and call out semantic changes
4. python
Which term best describes a foundational idea in "Tests as Prompts — an Unexpected Superpower"?
1. assertion
2. test-driven development
3. red-green-refactor
4. pytest
A learner studying Tests as Prompts — an Unexpected Superpower would need to understand which concept?
1. test-driven development
2. red-green-refactor
3. assertion
4. pytest
Which of these is directly relevant to Tests as Prompts — an Unexpected Superpower?
1. test-driven development
2. assertion
3. pytest
4. red-green-refactor
Which of the following is a key point about Tests as Prompts — an Unexpected Superpower?
1. Write a test that fails (red)
2. Ask the AI to write the function to make it pass (green)
3. Check the code works and is readable
4. Ask the AI to clean it up without breaking tests (refactor)
Which of these does NOT belong in a discussion of Tests as Prompts — an Unexpected Superpower?
1. Generate cleanup PR descriptions referencing the original ticket.
2. Check the code works and is readable
3. Ask the AI to write the function to make it pass (green)
4. Write a test that fails (red)
What is the key insight about "The edge case checklist" in the context of Tests as Prompts — an Unexpected Superpower?
1. Generate cleanup PR descriptions referencing the original ticket.
2. Diff JSON/YAML configs across environments and call out semantic changes
3. Always ask: what about empty input, null, zero, negatives, duplicates, very large inputs, and unicode? Your tests should…
4. python
What is the key insight about "Do not let the AI write tests that test nothing" in the context of Tests as Prompts — an Unexpected Superpower?
1. Generate cleanup PR descriptions referencing the original ticket.
2. Diff JSON/YAML configs across environments and call out semantic changes
3. python
4. AI sometimes writes assertions that just re-state the code, like `assert result == result`.
Which statement accurately describes an aspect of Tests as Prompts — an Unexpected Superpower?
1. A test says: when I give the function this input, I expect exactly this output.
2. Generate cleanup PR descriptions referencing the original ticket.
3. Diff JSON/YAML configs across environments and call out semantic changes
4. python
What does working with Tests as Prompts — an Unexpected Superpower typically involve?
1. Generate cleanup PR descriptions referencing the original ticket.
2. 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 li…
3. Diff JSON/YAML configs across environments and call out semantic changes
4. python
Which of the following is true about Tests as Prompts — an Unexpected Superpower?
1. Generate cleanup PR descriptions referencing the original ticket.
2. Diff JSON/YAML configs across environments and call out semantic changes
3. 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, genera…
4. python
Which best describes the scope of "Tests as Prompts — an Unexpected Superpower"?
1. It is unrelated to ai-coding workflows
2. It applies only to the opposite beginner tier
3. It was deprecated in 2024 and no longer relevant
4. It focuses on Writing a test first is not just good engineering. It is the clearest possible prompt for an AI. Let
Which section heading best belongs in a lesson about Tests as Prompts — an Unexpected Superpower?
1. The red-green-refactor loop, with AI
2. Generate cleanup PR descriptions referencing the original ticket.
3. Diff JSON/YAML configs across environments and call out semantic changes
4. python
Which section heading best belongs in a lesson about Tests as Prompts — an Unexpected Superpower?
1. Generate cleanup PR descriptions referencing the original ticket.
2. A concrete example in Python
3. Diff JSON/YAML configs across environments and call out semantic changes
4. python
Which section heading best belongs in a lesson about Tests as Prompts — an Unexpected Superpower?
1. Generate cleanup PR descriptions referencing the original ticket.
2. Diff JSON/YAML configs across environments and call out semantic changes
3. Ask the AI to help write tests too
4. python

← Back to interactive lesson