Every run, logged for governance.
Each workflow run is recorded end to end — completed and failed steps, per-step state, timestamps, inputs, and outputs. Human approvals are captured in the trail, so you can prove what happened and why.
Who did what, when, and why.
Enterprise-ready
Built for scale, governance, and reliability.
Composable
Works with the rest of the agentic platform out of the box.
Observable
Every run is logged, retrievable, and auditable via the Workflow Runs API.
Traceable
Per-step state and timestamps show exactly what ran, when, and how it ended.
Accountable
Human-in-the-Loop approvals are recorded as part of the run.
Exportable
Retrieve any run by ID; step outputs are downloadable where available.
Every run is a complete, retrievable record.
When a workflow runs, the platform logs the run with its inputs, overall state, and start and end timestamps. Retrieve any run by ID through the Workflow Runs API to monitor progress or reconstruct exactly what happened.
Steps, states, timestamps, and approvals.
Each run separates completed_steps from failed_steps. Every step carries its own state and timing, so nothing about an execution is left implicit.
Failures and aborts are first-class, not silent.
Completed steps record their output; failed or aborted steps record state and an error message. A user-intentional stop is marked USER_ABORTED so you can filter it apart from a genuine FAILED — clean signal for monitoring dashboards.
Governance you can hand to an auditor.
Prove what ran
Reconstruct any execution from its logged inputs, steps, and outputs.
Accountable approvals
Human-in-the-Loop checkpoints record who approved what before it proceeded.
Monitor at scale
Poll runs by ID to track progress and catch failures as they happen.
Distinguish intent
USER_ABORTED vs FAILED tells deliberate stops apart from real errors.
A governed publishing pipeline, fully logged.
The run logs each step's state and timestamps; the Human-in-the-Loop approval is recorded before publish, so the trail proves a person signed off.
How every run becomes evidence.
Configure
Build it visually in Studio and add a Human-in-the-Loop checkpoint where sign-off matters.
Run
Trigger the workflow; it executes asynchronously while each step is logged with state and timestamps.
Approve
The run pauses at the checkpoint until a reviewer approves — and that approval is recorded.
Audit
Retrieve the run by ID to review completed and failed steps, inputs, and outputs.
What teams ask before they commit.
What is an audit trail in an AI workflow platform?
An audit trail is the complete, retrievable record of what an automated workflow did: which steps ran, in what state, when, with which inputs and outputs, and who approved what. In Draft & Goal, every workflow run is logged end to end so teams can prove what happened and why.
What does Draft & Goal log for each workflow run?
Each run records its inputs, overall state, and start and end timestamps, and separates completed steps from failed ones. Every step carries its own state and timing, completed steps record their output, and failed or aborted steps record a state and an error message, so nothing about an execution stays implicit.
Can I retrieve a past workflow run for an audit?
Yes. Any run can be retrieved by ID through the Draft & Goal Workflow Runs API, returning the run record with its inputs, state, timestamps, and completed and failed steps. Step outputs are downloadable where available, so you can reconstruct exactly what an execution did and hand the evidence to an auditor.
Are human approvals recorded in the audit trail?
Yes. When a Draft & Goal workflow reaches a Human-in-the-Loop checkpoint, the run pauses until a reviewer approves, and that approval is recorded as part of the run. For a governed publishing pipeline, the trail proves a person signed off on the copy before anything was published.
How does Draft & Goal tell real failures apart from deliberate stops?
A user-intentional stop is marked USER_ABORTED, while a genuine error is marked FAILED with its error message preserved in the run record. That distinction gives monitoring dashboards a clean signal, so teams can track true failures at scale without deliberate aborts polluting the data.
Show us the workflow.
We'll show you the 10x.
Bring the marketing workflow that eats your week. We'll build it live, with your data and your models, in 30 minutes.