> ## Documentation Index > Fetch the complete documentation index at: https://synthlabs.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Run an agent > Launch a task or dataset with an explicit agent and scoring method, then inspect the result. Use `synth run start` to execute an agent on tasks. By default each task's own verifier assesses its result. You can replace that verifier with a judge profile, or collect unscored outputs. ## Before you start * [Install and sign in](/getting-started/install). * Select an uploaded [task](/concepts/tasks-and-versions) or [dataset](/concepts/datasets-and-suites) you can access. * Prepare a validated [agent profile](/concepts/profiles-and-candidates), or deliberately use the platform default. * Check the task's timeouts and resource requirements. A submission can incur compute costs; a dry run does not launch trials. Use your namespace in place of `acme`. Task and dataset references below are examples: replace them with exact versions returned by your own Registry commands. ## Run one task ```bash theme={null} synth run start \ --task acme/review-permissions@v1 \ --actor @reviewer.json \ --dry-run ``` Read what the dry run checked and what remains unresolved. A successful dry run does not prove that the model will execute or that the task's verifier is good. When the request matches your intent, submit the same command without `--dry-run`: ```bash theme={null} synth run start \ --task acme/review-permissions@v1 \ --actor @reviewer.json ``` Copy the returned run ID. `--task` reuses or creates a private one-task dataset for that task; the run still has a pinned task set. ## Run a dataset and repeat each task Save `eval-plan.json`: ```json theme={null} {"trials_per_task": 4} ``` ```bash theme={null} synth run start \ --dataset acme/review-evaluation@v1 \ --actor @reviewer.json \ --plan @eval-plan.json ``` A dataset with 20 entries and four trials per entry requests 80 trial slots. Repeated dataset members remain repeated entries. This is a work amount, not a promise that 80 sandboxes will run simultaneously. Without `--actor`, the platform selects its default actor and the receipt identifies that choice. Use an explicit profile when reproducibility matters. ## Choose the scoring method | Intent | Flags | Result | | - | - | - | | Use the task's assessment | Omit `--judge` and `--no-judge` | The task verifier scores each trial. | | Supply another assessor | `--judge @judge.json` or a pinned `agent://` reference | That judge replaces the task verifier. | | Collect outputs only | `--no-judge` | No verifier, judge or reward. | Omitting `--judge` does **not** disable scoring. Do not combine `--judge` and `--no-judge`. Training is a separate operation and cannot be unscored. ## Inspect the work ```bash theme={null} synth run show synth run events --follow --timeout 10m synth run result synth run trials ``` Stopping the local watch does not stop the remote run. A terminal execution state and task quality are different: read the output, score coverage and failure information before deciding what the result establishes. To stop remote work deliberately: ```bash theme={null} synth run cancel --yes ``` Cancellation is cooperative. Continue inspecting the run until it reports its terminal outcome and any cleanup limitation. Read [runs and evidence](/concepts/runs-and-evidence), then [compare setups](/guides/evaluate-and-compare) or [train the model](/guides/managed-training). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.