--- title: "Run and monitor" description: "How to run a workflow, watch it execute, pause and resume, stop a runaway, and recover from a crash." slug: guides/building-workflows/run-and-monitor section: guides subsection: building-workflows canonical_url: https://cerevisor.com/docs/guides/building-workflows/run-and-monitor last_verified: 2026-05-18 last_verified_version: "1.2.0" updated_at: 2026-05-18T15:08:18.053416+00:00 --- ## Running a workflow Three ways: - **Click the Run button** in the top-right of the canvas. - **Press Ctrl/Cmd+R**. - **Click an individual agent's play icon** to run just that agent (sandbox mode: runs in isolation). When you click Run, Cerevisor opens the **Execution Modal** showing a pre-run summary: - Total agents. - Wave count. - Estimated cost (per provider). - Permissions the run will need. - Skill availability check (preflight). If anything's wrong, missing provider, gated feature, incompatible skill: the modal blocks the run with an actionable error. If everything checks out, click **Run** in the modal to start. Click **Cancel** to dismiss. ## The Execution Modal Once a run starts, the modal shows live status. Top section: overall progress and run cost. Below that: one card per agent, grouped by wave. Each card shows: - Status badge: **Waiting / Running / Completed / Failed / Skipped**. - Streaming output preview (the agent's response as it's generated). - Tool calls in flight, with the tool name and arguments. - Wall-clock time so far. - The agent's resolved provider + model. Click any agent card to expand it for full output and full tool-call history. The modal also shows: - **Current wave** indicator at the top. - **Run cost so far** (per provider). - **Permission prompts** as banner toasts when an agent needs your sign-off. ## Stop, pause, resume Three buttons in the modal: | Button | Behavior | |---|---| | **Stop** | Hard stop. All running agents are cancelled; the run ends. Use for true emergencies. | | **Pause** | After each agent's current tool call finishes, the orchestrator pauses. Resume picks up where you left off. | | **Resume** | Continue from a paused state. | The Execution Modal can be closed with Escape: the run continues in the background. To reopen, click the status indicator in the status bar. ## Permission prompts When an agent calls a destructive tool (typically `bash`, `write_file`, `edit_file`), the **Permission Modal** opens. Options: | Button | Scope | |---|---| | **Allow once** | This single call. | | **Allow always for this run** | Every call of this tool for the rest of the run. | | **Allow always for this tool** | Permanently — writes to `WorkflowPermissions`. | | **Deny** | Returns an error to the agent. | Permission prompts pause only the agent that asked, other agents in the same wave continue running. ## Approval gates If a connection has flow type **Approval Gate**, the workflow pauses when it reaches the gate. The **Approval Gate Modal** shows: - The upstream agent's output preview. - The approval prompt you wrote on the connection. - The downstream agent that's waiting. Click **Approve** to proceed or **Reject** to halt the run. ## Ask-user prompts If an agent calls the `ask_user` tool, the **User Question Modal** opens. It shows the question and either a list of choice buttons or a free-form text input. The agent pauses until you respond. Other agents (in the same or other waves) continue running. ## Run cost The status bar shows running cost. The Execution Modal breaks it down per provider, per agent. Costs come from the provider's reported usage: - Anthropic: reported tokens × per-model pricing. - OpenAI-compatible: reported tokens × pricing if your provider returns it (Ollama returns no cost; local = always $0). - Codex CLI: always $0 (subscription billing). - Cursor Agent: always $0 (subscription billing). After a run, the full cost breakdown is saved to the audit log. ## Audit log Every run writes an NDJSON file to `~/.cerevisor/audit-logs/.ndjson`. The log contains: - Every event the orchestrator emitted. - Every tool call (name, arguments, result). - Every permission decision. - Every model call (provider, model, tokens, cost). - Errors with stack traces. You can open these files in any text editor. They're the truth of what happened. ## Replaying a workflow A `.cerevisor` file is the workflow definition. Re-opening it and pressing Run re-runs from scratch. If you want to re-run with a single agent's output replaced (e.g. "use last run's research, regenerate the writing"), there's no first-class "rerun from agent X" yet, workaround: copy the research output to a markdown file, attach it as an input to the writer, and run just the writer. ## Crash recovery If Cerevisor crashes or is force-closed mid-run: - On next launch, Cerevisor detects the unfinished session via its checkpoint. - The **Incomplete Session Modal** opens. - You can **Resume** (continues from the last checkpoint) or **Discard** (deletes the session). Resume is opportunistic; it works for most workflow shapes, but very recently-started agents may need to redo work. The modal shows session metadata so you can decide. ## Background runs You don't have to keep the Execution Modal open. Close it (Esc) and the run continues. The status bar shows a live indicator with the current wave. Reopen the modal any time to see live state. ## Cloud runs (Cursor only) If you set the workflow's run mode to **cloud** and use the Cursor Agent provider, the run executes on Cursor's cloud VMs. Cloud runs survive Cerevisor restarts. Manage them via the **Cloud Sessions** modal (title bar icon). See [Cursor cloud runs](../advanced/cursor-cloud-runs.md).