Read the automation before it runs
Every workflow is generated as code your engineers can inspect, diff, and approve.
-
Reviewable code
Workflows are inspectable, diffable, and version-controlled. Nothing opaque ever ships.
-
Approval gates
Humans approve before anything runs. Gates are first-class, not an add-on module.
-
Deterministic execution
The same input produces the same output. Agentic reasoning is scoped to steps that benefit from judgment.
Prove what happened, step by step
Every run is logged, replayable, and checked, so audits answer themselves.
-
Replayable runs
Any run can be replayed step by step with the inputs and outputs it saw.
-
Evals on every step
Each step carries evals that detect breakage when an upstream system changes.
-
Failures arrive as diffs
A broken step surfaces as a proposed patch your team reviews, not a silent error in production.
Keep production data out of the model
Models write the workflow. Your systems talk to reviewed code, not to a model.
-
Code, not model calls
Production data flows through the deterministic code your engineers approved.
-
Scoped access
Each workflow reaches only the systems and fields its steps declare.
-
Documented handling
Subprocessors, encryption, and retention commitments are published in the Trust Center.
Security questions, answered
Is Ballet SOC 2 compliant?
Ballet is part of Brainfish and covered by Brainfish’s SOC 2 Type II compliance. Reports and policies are available through the Trust Center at https://trust.brainfi.sh/.
Can I review what an automation does before it runs?
Yes. Every workflow is generated as version-controlled code. Engineers review and approve the diff before anything runs in production.
Are workflow runs auditable?
Yes. Every run is logged and replayable step by step, and evals on every step detect breakage before it reaches production.
Does my production data go through an AI model?
No. Models generate the workflow code. The workflow itself executes as deterministic code your engineers approved, so production data flows through reviewed code rather than a model call.
Move AI from personal wins to company returns
Nothing goes company-wide until it can be reviewed, gated and replayed. Bring one that needs all three.