Learning Center
Plain explanations of how to build and verify software with coding agents.
9 topics, 113 articles, 190 glossary terms
Verification
How to check that software written by coding agents works, from "done" claims and gamed tests to evidence from running the code.
- Start here: How to test AI-generated code
- Why do coding agents say "done" when the code doesn't work?
- What is runtime verification?
- Why do coding agents delete or weaken tests?
- What is a false pass (false green test)?
AI coding
How coding agents work and how teams build with them, from vibe coding and written specs to MCP and saved session history.
- Start here: What is a coding agent?
- What is vibe coding?
- What is spec-driven development?
- What is the Model Context Protocol (MCP)?
- What is AI coding session history?
Software testing
The types and levels of software testing, from unit tests to end-to-end journeys, and what changes when a coding agent writes the tests.
- Start here: What is software testing?
- What is unit testing?
- What is end-to-end testing?
- What is test-driven development (TDD)?
- What is the difference between mocks, stubs, and fakes?
Test quality
How to tell whether tests catch real bugs, from test oracles and code coverage to mutation testing and property-based testing.
- Start here: What is code coverage?
- What is a test oracle?
- What is mutation testing?
- What is the difference between mutation score and code coverage?
- What is property-based testing?
CI/CD
How pipelines build, test, and release each change, where checks run from pre-commit hooks to CI, and how coding agents change the load.
- Start here: What is CI/CD?
- What is the difference between pre-commit, pre-push, and CI checks?
- What is a pre-commit hook?
- What are agent hooks (Stop hooks)?
- Why is CI becoming the bottleneck for AI-written code?
Debugging
How to find, reproduce, and fix bugs, including flaky tests, race conditions, and regressions, and how to confirm that a fix worked.
- Start here: What is debugging?
- What are reproduction steps in a bug report?
- What is a flaky test?
- How to tell a flaky test from a real bug
- How to verify a bug fix
Test environments
Where software runs while it is tested, from agent sandboxes and test isolation to staging environments, and how prompt injection reaches agents.
- Start here: What is a sandbox for AI agents?
- What is test isolation (hermetic tests)?
- What is a staging environment?
- What is prompt injection in coding agents?
- What is an ephemeral environment?
CLI and web apps
How command-line tools and web apps behave at runtime and how to test them, from exit codes and output streams to headless browsers.
- Start here: How to test a command-line application
- What are exit codes?
- What is the difference between stdout and stderr?
- What is a headless browser?
- How to verify a CLI that a coding agent built
Code review
How human and AI code review work, what reading a diff can and cannot catch, static analysis, and how to review code written by agents.
- Start here: What is code review?
- What is AI code review?
- How to review a pull request written by a coding agent
- What is the difference between static and dynamic analysis?
- What is the code review bottleneck?
Glossary
190 terms used across the Learning Center, each defined in a sentence or two, A to Z.
How RunStory fits. These articles explain the practices. RunStory, from the same team, runs the software your coding agent commits and sends back what fails, with evidence. See how RunStory works