Abandoned Cart Recovery
SystemE-commerce
Classify how a shopper replied to a recovery prompt, draft a personalized win-back email that addresses their reason, and QA it for tone and links before it goes out.
3 agents · 5 steps
Playbooks
A playbook chains multiple AI assistants with branches and safety checks. Use X-VG-Flow instead of X-VG-Agent when you want a workflow — never send both headers.
💡 Quick start: Browse 51 active playbooks in the catalog below.
Headers
X-VG-Flow: your-playbook-slug— runs a published playbookX-VG-Agent: your-agent-slug— single-agent mode (unchanged)- Both headers →
400 mutually_exclusive_headers
Billing
Each production or Live test run uses 1 workflow execution plus validations for every assistant step (and reasks). Builder Simulate is free — zero executions and zero validations. Publishing a playbook does not consume executions.
Simulate vs Live vs API
- Simulate — dashboard preview; walks branches locally
- Live run — full proxy test from the dashboard (counts as 1 execution)
- Production API — same billing as Live run
Create and publish playbooks in the dashboard. See also the first playbook tutorial or the quickstart for single-agent setup.
Playbook Marketplace
Browse 51 production-ready playbooks. Fork any to your organization and start building.
Complete Catalog
All public playbooks — system & community
51 playbooks
3 steps | p50 1.38 ms | 3 validations
Ad Copy Brand Safety Gate
SystemContent
Generate marketing ad copy from a brief, run deterministic QA on placeholders, links, and forbidden phrases, and reject variants that fail brand safety checks.
2 agents · 4 steps
Agentic Tool-Call Validator
SystemSecurity
Let an agent propose tool or function calls, validate names against a configured whitelist, and route blocked calls to human review before execution.
3 agents · 5 steps
BEC Payment Review
SystemFinance
Review urgent payment instructions, validate wire details, block or escalate to CFO.
4 agents · 6 steps
Campaign Idea Validation
SystemContent
Score a marketing campaign idea for fit and risk. Approved ideas are expanded into a structured creative brief; weak or risky ideas are returned with a reason instead.
2 agents · 4 steps
Code Change Guard
SystemSoftware
Generate a patch, run security checks, route unsafe changes to human review.
3 agents · 5 steps
Complaint Triage
SystemSupport
Triage incoming complaints by severity, escalate urgent cases, and draft a standard reply for routine issues.
3 agents · 5 steps
Customer Review Tagging Gate
SystemData
Classify a single review or NPS comment into structured JSON with sentiment and a primary topic from a fixed taxonomy. Invalid enum values are blocked deterministically — not silently mapped to the nearest tag. Run once per comment; batch ingestion loops on your side.
2 agents · 4 steps
Data Enrichment
SystemData
Turn messy contact input into normalized CRM fields, then add audit metadata for downstream systems.
3 agents · 4 steps
Expense Approval
SystemFinance
Extract expense details, enforce policy rules, approve or reject with reason.
3 agents · 5 steps
Extract Then Decide
SystemOperations
Pull structured data from a document, confirm with the user when safe, or send a short failure message when extraction fails checks.
3 agents · 5 steps
Extract with Repair Loop
SystemData
Extract fields from input, validate required fields, route to a repair step when checks fail, then loop back to extraction (up to 3 visits).
3 agents · 5 steps
Feature Request Triage
SystemSoftware
Score an incoming feature request for fit. Approved ones are checked for API/contract impact before being marked as planned; everything else gets a clear, polite reply explaining the decision.
3 agents · 5 steps
Financial Advisory Guard
SystemFinance
Generate a customer-facing financial answer, run compliance guardrails on guarantees and disclaimers, and route blocked output to human review instead of sending.
3 agents · 5 steps
GitHub Issue Auto-Responder
SystemSoftware
Turn raw issue text into structured bug reports with required reproduction steps and logs, auto-reply when fields are missing, and draft triage responses when intake passes.
3 agents · 5 steps
HR Onboarding Intake
SystemHR
Extract new-hire details from an intake form, enforce a strict schema so nothing required is missing, and send a personalized welcome only when the record is complete - incomplete records route to a human.
3 agents · 5 steps
HR Policy Answer
SystemHR
Answer HR policy questions with citations and GDPR guard before sending.
2 agents · 3 steps
Incident Response Assist
SystemSoftware
Pull the key error patterns out of a noisy log dump, propose a safe remediation, and automatically hand off to an on-call human when the fix can't be validated as safe.
3 agents · 5 steps
Insurance FNOL Intake
SystemInsurance
Extract first notice of loss, guard coverage language, escalate to adjuster when needed.
4 agents · 6 steps
Invoice Processing
SystemFinance
Extract fields from an invoice, run a fraud-pattern check, then send an approval or rejection message.
4 agents · 6 steps
Page 1 of 3 · 51 total
curl
curl -s "https://api.valguard.ai/v1/chat/completions" \
-H "Authorization: Bearer $VG_API_KEY" \
-H "X-VG-Flow: support-automation" \
-H "Content-Type: application/json" \
-d '{"model":"openai/gpt-4o-mini","messages":[{"role":"user","content":"Hello"}]}'SDKs
Use withPlaybook() / with_playbook() / WithPlaybook() on the ValGuard client — see package READMEs under packages/sdk-*.
Error codes
mutually_exclusive_headers— both X-VG-Agent and X-VG-Flow sentplaybook_not_published— draft playbook; publish before API callsorchestration_executions_exhausted— monthly workflow quota used up (402)