Concepts

This page is the glossary for the Watcher vocabulary used across these docs, linking to the full concept page where one exists.

Term	Definition
Session	One recorded interaction with a coding agent, such as a single Claude Code or Codex conversation on a developer's machine. A session contains one or more trajectories. See Sessions and trajectories.
Trajectory	One linear path through a session's conversation: an unbroken chain of messages ending at one of the session's latest messages. Graders review trajectories. See Sessions and trajectories.
Grader	A versioned grading rubric: a prompt plus score dimensions that an LLM applies to a trajectory, producing a grade: one value per dimension, plus optional explanation and summary text. Watcher ships built-in graders, and you can create your own. See Graders.
Blocking review	Review of a tool call before it runs. The outcome allows the call, denies it, or escalates it to a human for approval. See Blocking and trailing review.
Trailing review	Server-side grading that follows ingested sessions: summaries while a session runs and after it settles, plus a deeper security review of highly scored sessions. See Blocking and trailing review.
Organization settings	Org-wide configuration managed by admins in the Analyzer, such as Slack notifications for flagged sessions. See Organization settings.
Admin audit log	An append-only file on a self-hosted deployment recording admin access to other users' session data, organization-level writes, and system-attributed retention scrubs, one JSON line per event. See Operations.
Analyzer	Watcher's web dashboard: where your team reviews sessions and their grades, works on graders, and where admins manage organization settings. See Analyzer.
Watcher API	The HTTP interface your deployment serves for programmatic access to sessions, trajectories, grades, and graders. See API.
Watcher client	The program installed on each developer machine. It hooks into coding agents (Claude Code, Codex) to record sessions, upload them to your Watcher deployment, and enforce blocking review. See Client for installing and using it.
Supported agents	The coding agents the Watcher client integrates with: Claude Code and Codex. Each agent's hooks record sessions and gate tool calls for blocking review in their own way. See Supported agents.
Enforcement mode	The machine-wide client setting that controls what blocking review does with its judgments: enforce, observe, or paused. Set in the machine's admin settings baseline, directly or via managed client settings. See Blocking and trailing review.
Managed client settings	An admin-authored overlay of Watcher client settings, edited in the Analyzer and delivered to developer machines by client pull (when distribution via Watcher is on) or by your MDM, with per-value locking. See Organization settings.
Settings profile	A named bundle of the Watcher client's review settings that is switched as a unit, such as the built-in Default and Human in the Loop profiles. See Client.
Red-team drill	A prompt an admin downloads from the Analyzer and sends to a developer, whose AI assistant uses it to turn enforcement on for that one machine, probe an agreed threat model, and restore the machine. See Organization settings.