Orqestria Download
← Back to Internal system builders

Skill · Version 1.0.0

AI workflow step integration

Embeds AI steps in workflows with validated outputs, durable checkpoints, scoped tools and evidence of external effects.

ai-tool-step-integration

Team members using this skill

See how it helps

When is it useful?

Use when model decisions feed business workflows or tool actions must survive retries safely.

What does it help you do?

  • Validates structured responses and routes invalid or uncertain results to explicit alternatives.
  • Stores completed outputs and usage so downstream retries can reuse prior results.
  • Restricts tool authority and verifies actual execution records before reporting success.

Try asking this

Add invoice classification to our workflow with schema validation, review routing and restart behavior that avoids unnecessary model calls. Feed in an invoice with no recognizable supplier. It should enter review with the original evidence, while restarting a completed classification reuses its saved result.

Detailed documentation

Read the skill’s original instructions, examples and checks in their authored language.

Details…Show less

AI & Tool Step Integration

Use this skill when embedding LLM prompts, structured extraction, classification, or autonomous tool-using AI agent steps inside deterministic workflows.

Never Trust Unverified AI Text as Proof of Side Effects

  1. Validate Structured Outputs Against a Strict Schema:
    • When an AI step drives downstream workflow branching or data mapping (e.g., routing a support ticket, extracting invoice fields, choosing a category), enforce a strict JSON Schema / structured output contract (response_format / tool schema).
    • If the model output fails schema validation, refuses, or returns low confidence below a configured threshold, route to an explicit fallback / human_review / error port rather than passing malformed data to downstream steps.
  2. Never Treat an LLM's Natural-Language Claim as Proof of Execution:
    • An AI step saying "I have refunded the customer and sent the confirmation email" is not proof that those actions occurred.
    • Verify actual tool call receipts / deterministic step execution records, or keep external state-mutating actions as explicit, auditable workflow steps outside the free-form prompt.

Durable Checkpointing & Cost/Token Bounds

  • Checkpoint Completed AI & Tool Steps:
    • Persist the resolved LLM output, token usage, model identifier, and tool call results at the step boundary so if a downstream step fails and retries, the workflow replays the recorded AI step output instead of re-billing and re-running the LLM non-deterministically.
  • Enforce Explicit Execution Budgets:
    • Configure hard limits on every AI step: maxTokens, maxToolCalls / maxIterations, timeoutMs, and allowed tool allowlists so an agent loop inside a workflow can never spin indefinitely.

Tenant Isolation, Permissions & Prompt-Injection Defense

  • Scoped Authority (effective_permissions = run_actor ∩ workflow_scope ∩ step_tool_allowlist):
    • AI steps and tool calls must execute strictly within the active tenantId and the initiating principal's authorized scope.
    • Gate high-impact or irreversible actions (payments, deletions, external broadcasts, permission changes) behind a deterministic workflow Approval step before the tool executes.
    • Delimit untrusted external input (emails, webhooks, uploaded documents) clearly and never allow untrusted prompt content to override workflow control-flow rules or tool target tenant IDs.

Checklist

  • Are AI step outputs validated against a strict schema before driving downstream workflow branches?
  • Are external side effects verified via deterministic tool/step execution receipts rather than LLM prose claims?
  • Are completed AI step outputs checkpointed so downstream retries do not re-invoke the LLM unnecessarily?
  • Are tool allowlists, token/iteration budgets, tenant isolation, and human approval gates enforced on AI steps?

Included files 1

  • SKILL.md