Build intelligent workflows.
With real code.
Steering is a workflow automation platform where every step runs real JavaScript — with Claude AI built in for data enrichment, classification, and decision-making.
AI built in,
not bolted on.
Placeholder — describe how Claude is available in every step with await ai.prompt() for direct answers and await ai.askWithTools() to let the AI query your own workflows for live data.
Full visibility.
Zero guesswork.
Placeholder — describe how every run captures inputs, outputs, console logs, and timing per step so nothing is ever a black box.
Built for teams.
Secure by design.
Placeholder — describe tenant isolation, encrypted secrets, API key auth, and role-based access for enterprise teams.
Why Steering
Real JavaScript execution
Every step runs your code in a secure isolated VM. No proprietary syntax, no drag-and-drop — just JavaScript that does exactly what you intend.
AI data enrichment
Call `await ai.prompt()` for direct AI responses, or `await ai.askWithTools()` to let Claude query your own workflows for live data — enrich records, classify inputs, and make decisions with real context.
Conditional branching
Route between steps based on success, error, or custom conditions you define. Handle failures gracefully without workarounds.
Flexible triggers
Fire workflows via REST API (sync or fire-and-forget), on a cron schedule, or in response to external events.
100% observability
Every run is logged with full input/output data, console output, and timing per step. See exactly what moved through your integrations.
Shared state & secrets
Persist data across steps with context and storage. Access encrypted secrets securely — all tenant-scoped and isolated.
AI data enrichment
Call Claude directly from any step script. Use ai.prompt() for direct answers, or ai.askWithTools() to let Claude call your own workflows as tools — querying live data before it responds.
// Fetch a support ticket, then classify it with Claude const ticket = await fetch( `${secrets.API_BASE}/tickets/${input.id}` ).then(r => r.json()) const urgency = await ai.prompt( `Classify this ticket urgency: low / medium / high / critical ${ticket.body}`, { maxTokens: 20 } ) $output({ ticket, urgency: urgency.trim() })
Claude built in
Every tenant gets `ai.prompt()` and `ai.askWithTools()` in every step script. No API wiring, no SDK setup — it just works. Use `askWithTools()` to let Claude call your own workflows as tools to fetch live data.
Service Registry
Register your APIs with base URLs, documentation, and usage notes. The AI assistant learns your stack before writing a single line.
AI code generation
Describe what a step should do. The Step Helper writes the JavaScript, pre-wired with your services, secrets, and data flow globals.
100% observability
Every byte that moves through your workflows is captured and inspectable — from the data entering each step, to API calls made to external systems, to the final output. Real operational insight, not just pass/fail status.
Step inputs and outputs
Inspect the exact data that entered and left every step in every run. No black boxes — every transformation is visible.
Integration data flows
See the payloads sent to and received from every external system your workflows touch. Spot integration failures instantly.
Console output per step
Every `console.log()` in your step scripts is captured against the run. Debug runtime behaviour without guessing.
Runtime metrics
Execution time is recorded per step and per run. Identify slow integrations and optimise with real data, not estimates.
How it works
Connect your services
Register APIs in the Service Registry with base URLs, documentation links, and usage notes. Add encrypted secrets. The AI assistant learns your stack.
Build steps with AI
Describe what a step should do. The AI writes JavaScript pre-wired with your services, secrets, and workflow data globals.
Trigger, monitor, iterate
Run workflows via API or schedule. Inspect every execution — inputs, outputs, console, and timing — in one focused view.