Author validation rules in plain English. No code, no deployment, no IT ticket. Rules take effect immediately.
Update rules in minutes, not sprint cycles. No deployment pipeline, no test class requirements for rule changes.
Built-in safety checks, version comparison, and rollback. Test before you activate — never go live blind.
Business analysts and operations teams own their rules. IT manages the platform; business manages the logic.
"Customer account required and duplicate review"
JSON rule structure stored as a data record — no Apex
Verify results, then flip a switch — no deploy needed
Rules run automatically on every record submission
Policies are the rules. Decisions are the outcomes. Understanding both is the foundation of everything in the workbench.
Shared rules that apply to a process or set of accounts. Managed by a small team of rule authors. Visible to all users with the right permission set.
Personal approval workflow rules tied to an individual. Only visible to the owner and admins. Can be enabled for any user.
Policies must move through each state in order. Active policies can be rolled back to Draft if issues arise.
Rule applies only to specific accounts you select. Best for account-specific business logic.
Rule applies to a class of accounts (e.g., all GPOs, all IDNs). Good for broad policy.
Rule applies universally. Use sparingly — check blast radius before activating.
Rule changes require Apex code, test classes, and deployment cycles.
Rules stored as data records, evaluated by a static engine. No code changes.
The workbench has three main panels arranged left-to-right. Use the view toggle buttons at the top to show/hide panels.
New Validation button, search & filters (object, process, event, active), auto-numbered policy list with sequence, priority, state, and active status.
Generate + Validate, Coach Prompt, Guided Flow, Smart Defaults, Activate Safely, Explain Policy. Below: configuration fields for target object, thresholds, account scope.
Prompt Assist for auto-generating test payloads, adhoc JSON testing, expected decision matching, simulation against real records, execution trace.
Click New Validation in the Policy List panel. A blank policy is created with default settings: Sequence 100, Priority 50, Target Object: Partner Registration, Block Threshold: 85, Review Threshold: 60.
Select Validation Policy (shared business rule) or Approval (individual-owned) from the Policy Type dropdown. Choose "Validation" for rules the team manages. Choose "Approval" for personal workflow rules.
In the "Describe What You Want" field, type your rule in plain English.
"Customer account required and duplicate review" "Block if opportunity name is blank or account has no billing address" "Flag for review if discount percentage exceeds 20% and deal size is under $50K"
Click the green Generate + Validate button. The system parses your business language into executable rule logic, creates execution steps with conditions and fallback modes, and sets AI Confidence, Risk, and Impact Scope indicators.
In the Validation Editor, set: Account Policy Use Case (Bill Back, Chargeback, Product Restriction, etc.), Account Scope (Named Accounts, Segment, or All Accounts), and optionally assign specific named accounts and add Business Guidance notes.
Click Save Policy Draft at the bottom of the editor. The policy is now saved as a Draft version. Next step: test it before activation.
Always test your rules before activating. The workbench provides two testing methods.
Quick validation against a single JSON payload.
{"Customer_Account__c": null,
"Opportunity_Name__c": ""}
Run your rule against real records from the target object.
Each test run produces a step-by-step trace showing how the engine evaluated your rule:
Runs automated readiness checks: steps present and properly sequenced, no conflicts with other active policies, test coverage exists, sample runtime performance is acceptable. If all checks pass, the policy goes live. If any fail, you'll see specific error messages.
Turns off the policy entirely. The rule stops evaluating immediately. Fastest option.
Switches back to the previously active version. The old rule logic takes effect instantly.
If you activated multiple policies together, restore the entire set from a saved snapshot.
Versions can also be Rejected (goes back to Draft for rework)
Use Version Diff in Advanced View to compare any two versions side-by-side. Select left/right versions and click Run Diff.
| Section | Key | Left (Old) | Right (New) | Status |
|---|---|---|---|---|
| Thresholds | Block | 85 | 90 | Changed |
| Thresholds | Review | 60 | 60 | Same |
| Steps | Step 30 | — | Check billing addr | Added |
| Steps | Step 20 | Check phone | — | Removed |
Monitor coverage, review feedback, check cross-model validation, and manage policies at scale.
Shows how many accounts would be affected if a policy is activated. "Applies to ALL 143 accounts" = high blast radius — review carefully.
After a policy runs, reviewers can rate outcomes as Helpful, Unhelpful, or Wrong. Feedback helps tune policies over time.
Optionally validate your rule against multiple AI models. Shows consensus, agreement %, and hallucination risk.
View/edit individual steps: sequence, type (Validation/Approval/Enrichment/Action), fallback mode, condition IR, active toggle
Identifies intra-policy contradictions (steps that conflict) and inter-policy conflicts (competing rules on the same field)
Shows which fields are evaluated by which steps across all active policies. Understand coverage and overlap.
Export policies as JSON for backup, migration, or sharing between orgs. Import to restore or transfer.
Save reusable test cases with expected outcomes. Run full test packs to verify behaviors after changes.
Re-generate rules with refinement instructions. Use templates (Last 10, Potential, Review) for common patterns.
Two permission sets control access. Users manage their own approval policies; Admins manage everything.
| Capability | User (PV User) | Admin (PV Admin) |
|---|---|---|
| Validation Policies (shared) | ||
| View validation policies | ✓ | ✓ |
| Create / edit / delete validation policies | ✗ | ✓ |
| Activate / deactivate validation policies | ✗ | ✓ |
| Approval Policies (individual) | ||
| View own approval policies | ✓ | ✓ |
| View all users' approval policies | ✗ | ✓ |
| Create / edit own approval policies | ✓ | ✓ |
| Testing & Feedback | ||
| Run adhoc tests | ✓ | ✓ |
| Submit feedback on outcomes | ✓ | ✓ |
| Run simulations | ✗ | ✓ |
| Run cross-model checks | ✗ | ✓ |
| Governance | ||
| View Governance Dashboard | ✗ | ✓ |
| Export / import policies | ✗ | ✓ |
| Policy set snapshot & rollback | ✗ | ✓ |
Three complete examples showing how to create, test, and activate policies for common business needs.
Customer account required and duplicate review
Customer_Account__c is blank → Score: 90 (Block)Opportunity_Name__c matches an existing record → Score: 75 (Review)
{"Customer_Account__c": null,
"Opportunity_Name__c": ""}{"Customer_Account__c": "001xx000003DGbY",
"Opportunity_Name__c": "Acme Deal"}Flag for review if discount percentage exceeds 15 percent
Find and select the policy in the policy list
"Customer account required. Allow if account name is provided even without lookup ID."
Creates Version 2 with the updated rule logic
Advanced View → Version Diff → Left: V1, Right: V2 → Run Diff
Step 10 condition changed from isBlank to isBlank AND nameIsBlank
Compare results vs V1: "5 records that were blocked would now be allowed"
Satisfied with the change → Activate. If issues arise next day → Rollback to V1 instantly