Beyond the definition
Articles & reading paths
Read deeper explanations of context, coding-agent turns, and task failures, or follow a curated route through the glossary.
Companion articles
- Context window versus memory: what actually persists?
Separate what a model can use now from what an application saves, retrieves, compacts, or leaves in your files.
- Anatomy of a coding-agent turn
Follow a coding request from context assembly through tool calls, execution, verification, and a final response.
- Why an agent can call a tool successfully and still fail the task
Distinguish transport, execution, evidence, and task success, then reproduce a successful edit that fails its acceptance check.
Choose a reading path
- Your first coding agent
Learn what controls the work, how tools act, and what evidence to ask for before accepting a coding change.
- Understanding context
Trace how information becomes model input, survives a session, and returns after compaction or a handoff.
- Debugging agent failures
Work backward from an unmet requirement to the tool result, environment, and evidence that led to it.
Definitions stay concise in the glossary. These pages connect the ideas through comparisons and examples. Conversations are illustrative, not recorded runs. Review dates identify substantive editorial reviews; references identify the primary sources behind technical claims.