Data handling
Understand what information should and should not be used in Trigz workflows.
In this guide, you will learn how to:
- Understand when to use this feature
- Prepare the right inputs before setup
- Configure the workflow safely
- Test expected and edge cases
- Review related docs before launch
- Best for
- Workflow owners
- Before you start
- Prepare one clear workflow, a known owner, and the knowledge or system details needed for setup.
On this page
OverviewWhen to use thisPrerequisitesStep-by-stepExamplesBest practicesTroubleshootingRelated articlesBefore you start
- A Trigz account
- A workflow owner
- A first workflow or template
- Approved knowledge or sample data
- A test channel or safe test environment
Overview
Understand what information should and should not be used in Trigz workflows.
When to use this
- You are setting up a real workflow
- You need a repeatable configuration path
- You want clear fallback, testing, and ownership before launch
Step-by-step
1
Use approved knowledge
- Why this matters
- This step keeps the workflow clear, testable, and easier to improve after launch.
- How to do it
- Complete this setup step in Trigz, then confirm the expected behavior before continuing to step 2.
- Expected result
- You have a clearer workflow configuration and a safer launch path.
- UI location
- Docs -> Setup area
Use approved knowledgeUI placeholder
2
Avoid sensitive data
- Why this matters
- This step keeps the workflow clear, testable, and easier to improve after launch.
- How to do it
- Complete this setup step in Trigz, then confirm the expected behavior before continuing to step 3.
- Expected result
- You have a clearer workflow configuration and a safer launch path.
Avoid sensitive dataUI placeholder
3
Use minimum data needed
- Why this matters
- This step keeps the workflow clear, testable, and easier to improve after launch.
- How to do it
- Complete this setup step in Trigz, then confirm the expected behavior before continuing to step 4.
- Expected result
- You have a clearer workflow configuration and a safer launch path.
Use minimum data neededUI placeholder
4
Separate test and production data
- Why this matters
- This step keeps the workflow clear, testable, and easier to improve after launch.
- How to do it
- Complete this setup step in Trigz, then confirm the expected behavior before continuing to step 5.
- Expected result
- You have a clearer workflow configuration and a safer launch path.
Separate test and production dataUI placeholder
5
Define data owners
- Why this matters
- This step keeps the workflow clear, testable, and easier to improve after launch.
- How to do it
- Complete this setup step in Trigz, then confirm the expected behavior before continuing to step 6.
- Expected result
- You have a clearer workflow configuration and a safer launch path.
Define data ownersUI placeholder
Specific channels, integrations, API access, and production behavior may depend on plan, setup, and implementation review.
Do not paste passwords, API keys, credentials, or private customer data into public forms, prompts, or unsafe sources.
Example ways to use this
Knowledge review
- Scenario
- An internal guide is being added.
- Setup
- Remove secrets and unapproved data before upload.
- Outcome
- The workflow uses safer knowledge sources.
Best practices
Start with one workflowUse clean, approved knowledgeKeep instructions simple at firstTest both common and edge casesConfigure fallback before launchUse human handoff for sensitive requestsReview analytics after activationImprove knowledge based on unanswered questions
Common mistakes
| Mistake | Why it hurts | Better approach |
|---|---|---|
| Adding too much messy content | The agent may retrieve weak or conflicting answers. | Start with clean, approved sources. |
| Skipping fallback setup | Users may get poor answers or dead ends. | Configure fallback and handoff before launch. |
| Launching across every channel at once | Harder to monitor and improve. | Start with one channel. |
| Not assigning an owner | Handoffs may be ignored. | Assign a workflow owner. |
Troubleshooting
| Issue | Possible cause | What to check |
|---|---|---|
| Agent gives incomplete answers | Missing or weak knowledge source | Review connected documents and FAQs |
| Agent answers when it should hand off | Handoff rule not configured | Check fallback and escalation settings |
| Agent tone feels wrong | Instructions are too broad | Update tone and response guidance |
| Agent cannot answer common questions | Content is missing or not connected | Add or clean the knowledge source |
Was this article helpful?
Your feedback helps us improve our docs.
Still need help?
Use the Help Center, contact support, or book a demo if you need help mapping your first workflow.