Glossary

Terms are listed alphabetically. Cross-references use italics.

Agent

A configured worker that does one piece of a workflow. An agent has a role, a set of skills, an output definition, instructions, and a provider + model. Agents run in waves and pass output to each other through connections.

Agent Palette

The left-edge dock from which you drag agent role cards onto the canvas.

Approval Gate

A connection type that pauses the workflow when it's reached, requiring you to approve or reject before downstream agents run.

Audit log

An NDJSON file under ~/.cerevisor/audit-logs/ recording every tool call, permission decision, and event in a run. One file per session.

Canvas

The main editing surface where you place and connect agents.

Chat Builder (AI Chat Builder)

The floating chat window (open with Ctrl/Cmd+L) where you describe a workflow in natural language and Cerevisor creates or edits agents for you.

Antigravity

One of the provider types. Google's Antigravity agent, run on your Google plan. Antigravity runs each agent itself; Cerevisor sets the task up, watches the output, and checks the results.

Claude Agent SDK

One of the provider types. Anthropic's agent engine (the same one that powers Claude Code) running inside Cerevisor. It runs each agent itself: Cerevisor sets the rules up front, hands the agent's run over, and checks the results. See Claude Agent SDK provider.

Codex CLI

OpenAI's Codex command-line tool. One of the provider types Cerevisor supports. You sign in with your ChatGPT plan.

Column

A vertical lane on the canvas representing one wave of execution. All agents in a column run in parallel.

Connection

A directed edge from one agent to another representing data handoff. Connection types: Always, Conditional, Approval Gate, Loop.

Control Group

A saved selection of agents you can recall instantly with Ctrl+Shift+1..9. Like RTS unit groups.

Cross-workflow link

A connection between agents in two different workflows on the same World View. Configured via the Cross-Workflow Link modal.

Cursor Agent

One of the provider types. Cursor's agent, running on your machine or in Cursor's cloud. Cursor runs each agent itself while Cerevisor supervises the run.

Cursor cloud run

A workflow run that executes on Cursor's cloud infrastructure rather than your local machine. It keeps going if Cerevisor closes, and you can reconnect to it later.

Custom agent

An agent built from the Custom role, or a template saved by you. Reusable across workflows.

Default provider

The provider in your library marked as default. Used by new workflows and any agent without an explicit override.

Draft (auto-save)

A copy of your unsaved work that Cerevisor saves every 30 seconds. It survives a crash and is offered back on next launch.

Embedded App

A native desktop application (Outlook, Excel, etc.) embedded as a node on the Cerevisor canvas. Windows only.

Execution Modal

The popup showing live status of a workflow run.

Failure Report

A summary of what went wrong in a run. Loop & Enhance uses it to decide what to change before the next round.

File intelligence

How Cerevisor uses the input and output files you declare on each agent: it works out which agents depend on which, warns about two agents writing the same file, and orders the run accordingly, without copying file contents into another agent's context.

Flow type

One of four behaviors a connection can have: Always, Conditional, Approval Gate, Loop.

Gemini

One of the provider types. Google's Gemini models through an API key. Cerevisor runs the agents itself and handles Gemini's pricing rules for you. See Gemini provider.

Handoff format

How an agent's output is packaged before the downstream agent reads it. Options: Summary, Structured JSON, File Reference, Full Output.

Harness

The part of Cerevisor that runs your agents: it starts them in the right order, passes work between them, and enforces your permissions.

Harness self-memory

What Cerevisor has learned from its own runs: how each role is doing, learned tips, and your corrections. Stored under ~/.cerevisor/memory/harness/.

Lemon Squeezy

The payment provider used for Cerevisor licenses.

Loop (connection type)

A connection that re-runs part of a workflow until an exit condition is met or the maximum number of passes is reached.

Loop & Enhance

A run mode that wraps a workflow in detect-fix-rerun cycles. After each round, Cerevisor looks at what failed, proposes edits to the workflow, applies them, and runs again. See Loop & Enhance.

MCP (Model Context Protocol)

An open protocol for tool/context servers. Cerevisor is an MCP client; you can connect any MCP server (e.g. filesystem-mcp, github-mcp) and its tools become available to your agents.

Memory subsystem

Everything Cerevisor remembers, stored under ~/.cerevisor/memory/: your profile, what it has learned from runs, its observations, open disagreements, freeform entries, and earlier versions.

Meta-cognition

Cerevisor's look back over its own runs over time, producing observations like "this role has been failing more often lately" and a lasting summary of what it has learned about working with you.

Native mode (Structured Orchestration)

A workflow setting that adds more structure to the instructions agents receive: agent types, tool limits, and model hints. It works with whichever provider runs the workflow.

Operator

An assistant that works quietly on your workspace in the background while the app is open, within a budget you set. It keeps a journal of everything it does. A workflow or a skill it builds appears directly on your canvas or in your skills list, marked "Built by Operator"; a memory note or a workspace summary still waits in a review queue for you to accept or discard. Open it from the workspace rail. See Operator.

Output definition

Your description of what an agent's output should look like. Cerevisor checks the output against it and passes it on to the agents that come next.

Output Verifier

A check of an agent's output against its output definition, made by a model.

Pipeline

A chained run of multiple workflows. Configure via the Pipeline modal.

Placement mode

A canvas state where your cursor becomes a ghost of an agent about to be placed. Entered by pressing 0–9 or dragging from the palette.

Progressive Mode

A per-workflow chat mode where describing what you want builds and runs the workflow piece by piece as you talk — you never press Run. See Progressive Mode.

Provider

A service that runs your agents: Anthropic, Gemini, Claude Agent SDK, an OpenAI-compatible endpoint (Ollama, OpenRouter, etc.), OpenAI Codex CLI, Cursor Agent, Antigravity, and Grok Build. With Anthropic, Gemini, and OpenAI-compatible providers, Cerevisor runs each agent step by step itself; with the others, the provider's own agent tool runs the work while Cerevisor supervises. See Provider overview.

Provider Library

The collection of all configured providers. One is marked as the default.

Provider override (per-agent)

Setting a specific provider on a single agent, overriding the workflow's default.

Role

The starting profile for an agent: Researcher, Architect, Developer, etc. Sets smart defaults for subagent type and accent color. Roles do not set a model.

SA Directive

The situational-awareness instruction given to every agent (alongside the Wow Directive). Toggle and edit it at Settings -> Workflow. It is separate from the Wow Directive: Wow asks "is this output worth showing off?"; SA asks "does this output honestly say what the agent doesn't know?". See SA configure and run.

Scheduled run

A workflow configured to run automatically on a cron schedule. Configured via the Schedule Config popup; managed under Settings → Automation.

Situational Awareness (SA pillar)

Cerevisor's running picture of a workflow: what is happening, how sure it is, and what is still unknown. Shown as state labels, uncertainty badges on agents, and a report after each wave. See Situational Awareness overview.

Skill

A reusable, focused capability. Lives as a folder containing a SKILL.md plus optional helper scripts. Cerevisor merges ~/.claude/skills/ and ~/.cerevisor/skills/ on launch.

Skill compatibility (provider compatibility)

Whether a skill works with a given provider. Cerevisor checks this before a run starts.

Skill Workshop

The in-app editor for creating, editing, and managing skills. Switch to it from the title bar.

Subagent type

One of four execution modes: explore (read-only), plan (planning), bash (shell), general-purpose (full toolset).

Telemetry

Cerevisor sends no telemetry: no usage analytics and no crash reports. The app has no code that sends them. Two network calls are on by default: the update check and a one-time download of the skill-matching model. Everything else goes to services you set up yourself (a model provider, a web-search backend, an MCP server you added). Security and updates lists every call.

Template

A reusable starting point; either a workflow template (on the Home Screen) or an agent template (Custom Agents).

Trust Profile

A user-chosen risk appetite (Cautious / Standard / Trusted Developer) that controls how often the permission system prompts vs. auto-approves.

Wave

A column on the canvas. Agents in the same wave run in parallel. Later waves wait for earlier ones to finish.

Workflow

A single document containing agents, columns, connections, and settings. Saved as a .cerevisor (or .opaal) file.

Workspace

A multi-workflow document containing N workflows arranged on the World View. Saved as a .cerevisor-world file.

World View

The multi-workflow canvas where each workflow appears as a framed area. Add cross-workflow links, see all your work at once.

Wow Directive

A global quality bar given to every agent. Editable in Settings → Workflow.