Skip to content
Reusable runbooks

Workflow templates

Workflow templates start from Threada primitives: intents, workflow definitions, evidence, policies, actions, release state, and the five governed surfaces. Installable packs remain optional presets when a team wants a packaged starting point.

Primitive presets

Templates compose primitives

Start from sources, WorkItems, evidence, policies, approvals, actions, evals, and release state in Studio. Optional packs such as IT access, vendor security, procurement, and HR lifecycle bundle those primitives into installable presets, but they are not required before the primitive workspace is useful.

Browse templates Docs

Downloadable workflow assets

Starter records and rubrics for teams evaluating governed AI work automation. They are examples, not customer data.

Policy template

Approval policy JSON

A starter policy set for review-first workflows: citation requirements, risk-based approvals, reviewer roles, and kill switches.

{
  "policy_set_id": "ps_vendor_security_review_template",
  "defaults": {
    "citation_required": true,
    "abstain_when_evidence_missing": true
  },
  "approval_rules": [
    { "rule_id": "rule_external_security_request", "requires_approval": true }
  ]
}
generation_mode: template_sample · provenance_citation: docs/spec/product.md#design-principles · Template sample; not tenant data · Replace example IDs, domains, roles, and thresholds before use.
Download policy template
Release check

Evaluation gate rubric

A simple fixture-driven rubric for testing extraction, grounding, approval routing, action safety, and receipt completeness before release.

gate_id,gate_name,expected_behavior,pass_threshold
extract-001,Extract required fields,"required fields are present",0.95
ground-001,Citation grounding,"answer cites current sources",0.98
audit-001,Receipt completeness,"event links actor, WorkItem, evidence, and policy",1.00
generation_mode: template_sample · provenance_citation: docs/spec/product.md#design-principles · Template sample; not tenant data · Replace example IDs, domains, roles, and thresholds before use.
Download eval rubric
Cost model

Build-vs-buy CSV

A component-level worksheet for estimating the parts of governed AI automation that teams often undercount.

component,build_scope,hidden_operating_cost,threada_surface
Retrieval and citations,"chunking, embeddings, hybrid search","source freshness, regression tests",Evidence
Approval gates,"review routing, policy precedence","auditor questions, role drift",Actions
Audit exports,"event envelope, retention, exports","incident reconstruction",Run log
generation_mode: template_sample · provenance_citation: docs/spec/product.md#design-principles · Template sample; not tenant data · Replace example IDs, domains, roles, and thresholds before use.
Download cost model
Sample output

WorkItem JSON

A concrete record showing the request, extracted fields, confidence, risk flags, evidence links, policy version, SLA, and queue state.

{
  "work_item_id": "wi_3f9a2b7c1d",
  "intent": "vendor_security_review",
  "confidence_score": 0.92,
  "risk_flags": ["external_requester"],
  "policy_set_version": 3,
  "status": "WORK_ITEM_STATUS_IN_REVIEW"
}
generation_mode: illustrative_sample · provenance_citation: docs/spec/product.md#design-principles · Synthetic marketing sample; not tenant data · Replace example IDs, domains, roles, and thresholds before use.
Download WorkItem JSON