Every answer now comes with receipts. Verify Responses gives you full visibility into how your agent arrived at an answer, so teams can audit claims, review sources, and ship AI with confidence.
Trust built into every answer
AI is powerful, but in real businesses, “sounds right” isn’t good enough. Security, compliance, and legal teams need to know:
- Where did this answer come from?
- Can we audit it?
- How do we prove it’s not hallucinating?
These questions are exactly why many AI deployments get stuck in pilot mode. Verify Responses removes that blocker by making answers inspectable automatically.
Why it matters for security and compliance teams
When AI becomes part of customer support, internal operations, or decision-making, organizations need more than a response—they need evidence.
Your team sees the potential of AI. But your CISO, compliance officer, and legal team see risk.
- Where did that answer come from?
- Can we audit this?
- How do we know it’s not hallucinating?
These questions keep powerful AI tools stuck in pilot mode forever.
Verify Responses answers all of them automatically. It can help you:
- Prove traceability with logged sources and claim-by-claim verification
- Support auditability for compliance workflows
- Reduce risk by catching shaky answers before they reach customers
- Improve reliability by exposing where your knowledge base is incomplete
How we use it at CustomGPT.ai
We became our own first users (again). We enabled Verify Responses on our own support agents and reviewed what the system surfaced.
What we found surprised us:
The AI wasn’t always the problem. Our documentation was.
Users were asking questions our knowledge base didn’t fully cover. With incomplete information, the model did what models do—it tried to be helpful, and “helpful” sometimes meant guessing.
“Every inaccurate response is a signal,” says Marko Mitrović, Product Manager at CustomGPT.ai. “It’s telling you something. Either your AI needs tuning, your system needs fixing, or your content has gaps. You just have to listen.”
Once we could see the claims and sources, we quickly:
- fixed persona configurations,
- resolved system-level retrieval issues,
- and published new documentation to cover missing topics.
Want the full breakdown? Read our complete case study.
What you can do with Verify Responses
- Corporate compliance & audit trails – Give your CISO and compliance teams the documentation they need. Every claim is traceable. Every source is logged.
- Security reviews – Prove to stakeholders that your AI isn’t making things up. Verify responses before they reach customers.
- Find knowledge gaps – Discover what’s missing from your documentation. Low verified claims scores point directly to content you need to create.
- Debug AI behavior – Stop guessing why your agent gave a weird answer. See exactly which sources it used and where it went wrong.
- QA before deployment – Test your agent thoroughly. Run verification on every response during development, then spot-check in production.
Ready to turn this on? Read the step-by-step guide to enable Verify Responses. Once enabled, your team can review claims, sources, and scores per response.
What’s inside
Claim Verifier: Automatically extracts factual claims from a response and cross-references them against your source documents, so you can see what’s verified and what isn’t.
Verified Claims Score: A simple ratio: Verified claims divided by total claims. If your AI makes 10 statements and 8 trace back to your docs, it scores 80%.
Trust Score: A virtual committee of six AI-powered stakeholders reviews responses for potential risk:
- End User
- Security / IT
- Risk Compliance
- Legal Compliance
- Public Relations
- Executive Leadership
Customer Intelligence Integration : Filter conversations by verified claims score in your analytics dashboard to find problem responses fast and take action.
Learn more about how it works.
How to use Verify Responses
There are two ways to use Verify Responses:
1) Builder mode
Enable Verify Responses via Actions and verification runs automatically on every chat—ideal for building and testing.
2) Audit mode
Run verification manually on any conversation (including older ones). Results appear in seconds—great for spot checks and audits.
Pro tip: In production, keep it on if you need full auditability for your CISO or CIO. This also surfaces trust scores in Customer Intelligence analytics.
See all use cases and workflows
Connect With Us
Want to see how other businesses are using Verify Responses or share your own use cases? Join the CustomGPT.ai Slack Community today.
Frequently Asked Questions
Q: What is Verify Responses?
A: Verify Responses is a transparency feature that shows you exactly how your AI arrived at its answer. It extracts every factual claim from a response, checks each one against your source documents, and analyzes the response from six stakeholder perspectives. You get full visibility into what’s verified, what’s not, and where potential risks might exist.
Q: Why should I use Verify Responses?
A: If you need to trust your AI’s answers – whether for compliance, customer-facing use, or internal decisions – this feature gives you proof instead of assumptions. It helps you catch inaccuracies before your users do, identify gaps in your knowledge base, and provide audit trails for regulated industries.
Q: How is this different from just reading the AI’s response?
A: Reading a response tells you what the AI said. Verify Responses tells you why it said it – which specific documents it pulled from, which claims are actually backed by your sources, and which ones aren’t. It’s the difference between trusting and verifying.
Q: Will my end-users see the Verify Responses panel?
A: No. Verify Responses is a behind-the-scenes tool designed exclusively for you – the builder and administrator. Your end-users see a clean, standard chat interface. The feature exists to give you confidence that your chatbot is accurate and safe.
Q: Who is this feature designed for?
A: This feature is built for you, the builder and manager of the AI system. Think of it as your administrative dashboard for trust and safety. It provides the audit trail, fact-checking, and risk analysis you need to build, test, and manage a reliable AI assistant.
Q: How does the Verify Responses button work?
A: When you click the Claim button, the system reads the AI’s response, extracts every factual claim (like facts, dates, numbers, or policy details), and cross-references each one against your source documents. It then shows you exactly where it found supporting evidence – or flags claims that couldn’t be verified.
Q: What is the Verified claim score?
A: The Verified claim score is a simple calculation: verified claims divided by total claims found. If your AI makes 10 factual statements and 8 can be traced back to your source documents, your Verified claim score is 80%. This gives you a quick, quantifiable measure of how well-supported a response is.
Q: What does the Trust Building button do?
A: The Trust Building button runs your response through a simulated review by six virtual stakeholders: End User, Security/IT, Risk Compliance, Legal Compliance, Public Relations, and Executive Leadership. Each perspective analyzes the response for potential concerns – like legally risky phrasing, security issues, or reputation risks – that you might not have considered.
Q: What are the six stakeholder perspectives?
A: The six perspectives are:
- End User – Is this answer helpful and appropriate for customers?
- Security/IT – Are there data exposure or system security concerns?
- Risk Compliance – Does this create regulatory or financial exposure?
- Legal Compliance – Is there liability risk or legally ambiguous language?
- Public Relations – Could this cause negative public perception?
- Executive Leadership – Does this align with brand and strategic goals?
Q: What happens if a claim can’t be verified?
A: Claims without source support get flagged in the interface. This doesn’t necessarily mean the claim is wrong – it means it couldn’t be traced back to your uploaded documents. This is your signal to either add that information to your knowledge base or investigate further.
Q: Can the Verified Claim Score and Trust Score conflict with each other?
A: Yes, and that’s by design. A response can be factually accurate (high Verified Claim Score) but still raise concerns from a stakeholder perspective (lower Trust Score). For example, a statement might be true but use legally risky phrasing. The system highlights these conflicts so you can make informed decisions.
Q: How do I access Verify Responses?
A: You’ll find the Verify Responses button next to AI responses in your builder interface. The shield icon opens the Verify Responses panel. You can also view verification data in the Customer Intelligence tab.
Q: What are the two ways to use Verify Responses
A: There are two modes:
- Persistent mode – Enable Verify Responses via Actions and verification runs automatically on every chat. This is ideal for development, QA, and building your agent.
- On-demand mode – Run verification manually on any specific conversation, including past conversations. Results appear in seconds. This is ideal for production audits and spot-checks.
Q: When should I use persistent mode vs. on-demand mode?
A: Use persistent mode while building and testing your agent – you’ll get instant verification data on every response. When you deploy to production, switch to on-demand mode for spot-checking, to reduce cost. However, if you need full auditability for compliance (like for your CISO or CIO), keep it enabled in production. This also surfaces trust scores in your Customer Intelligence analytics.
Q: Will this slow down my chatbot responses?
A: No. Your standard chat response is generated at normal speed. The Verify Responses analysis is a separate process that runs either automatically (in persistent mode) or when you trigger it manually (on-demand). Your end-users won’t experience any delay.
Q: Can I run verification on old conversations?
A: Yes. You can run Verify Responses on-demand for any past conversation. Results appear in seconds.
Q: How does Verify Responses work with Customer Intelligence?
A: Verification data flows into your Customer Intelligence dashboard. You can filter conversations by verified claim score, stakeholder status, or other criteria to quickly identify responses that need attention. This makes it easy to find patterns, spot problem areas, and prioritize improvements.
Q: How do I find low-scoring conversations?
A: Go to Customer Intelligence in your dashboard and use the filters to sort by verified claim score. You can quickly identify which conversations scored below your threshold and need review.
Q: Can I use Customer Intelligence data to improve my knowledge base?
A: Absolutely. This is one of the most valuable use cases. Filter for low verified claim scores to identify where your knowledge base has gaps. Each flagged claim points directly to content you may need to create or improve.
Q: Which plans include Verify Responses?
A: Verify Responses is available on Premium and Enterprise plans.
Q: Does running Verify Responses cost extra?
A: The Verify Responses features are powerful tools that consume significant resources. For Premium and Enterprise users, enabling them will apply a cost modifier to your queries. This will be clearly communicated in your settings before you proceed.
Q: How can compliance and legal teams use this?
A: Verify Responses creates audit-ready documentation for every AI response. The Legal Compliance stakeholder flags liability risks, while verified claim scores provide verifiable source citations. For regulated industries where “the AI said so” isn’t a valid answer, this gives you the proof you need.
Q: How does this help with security reviews?
A: The Security/IT stakeholder analyzes every response for sensitive information handling and system security implications. You can prove to stakeholders that your AI isn’t exposing data or making things up.
Q: Can I use this to debug why my AI gave a strange answer?
A: Yes. Instead of guessing why your agent gave a weird response, you can see exactly which source documents it used and where it went wrong. This makes troubleshooting much faster.
Q: How can I use this for QA before deployment?
A: Enable testing mode during development so verification runs on every response. Test your agent with real questions, check verified claim score, and fix issues before your users encounter them. Then switch to on-demand mode for production.
Q: Can this help me find gaps in my documentation?
A: Yes – this is one of the most valuable discoveries you can make. When claims get flagged as unverified, it often means your knowledge base is incomplete. Low Verified Claim scores point directly to content you need to create.
Q: What’s considered a “good” Verified Claim Score?
A: This depends on your use case and risk tolerance. For high-stakes applications (legal advice, medical information, compliance), you likely want scores above 90%. For general customer support, 80%+ may be acceptable. Use your scores to set internal benchmarks and improve over time.
Q: What if my Verified Claim Score is low?
A: A low score is actually valuable information. It means you found problems before your customers did. Use the detailed breakdown to identify whether the issue is your persona configuration, the retrieval system, or gaps in your documentation – then fix it.
Q: Does a high Verified Claim Score mean the response is definitely correct?
A: A high Verified Claim Score means the claims in the response can be traced back to your source documents. It doesn’t guarantee the source documents themselves are correct or complete. The feature verifies alignment with your sources, not absolute truth.
Q: What if the AI’s answer is correct but gets a low score?
A: This usually means the information exists but isn’t in your uploaded documents. The AI may have inferred something reasonable, but it couldn’t be verified against your sources. Consider adding that information to your knowledge base.
Q: Is my data secure when using Verify Responses?
A: Yes. Analysis is performed securely within the CustomGPT.ai environment. Verification data is not shared with other users or external systems. Only the authenticated user can access explainability analysis for their queries.
Q: Is this feature compliant with regulations?
A: Verify Responses operates within CustomGPT.ai’s SOC-2 Type II and GDPR-compliant infrastructure.
Q: Can other users see my verification results?
A: No. Only you (the authenticated builder/administrator) can access the Verify Responses analysis for your agents and conversations.
Q: How often should I run verification?
A: During development and testing, run it on everything (persistent mode). In production, the frequency depends on your needs. High-stakes applications may warrant continuous verification; others may only need periodic spot-checks.
Q: What’s the best workflow for improving my AI using this feature?
A: Enable persistent mode while building
- Let real conversations happen
- Check verified claims score in Customer Intelligence
- Categorize problems (persona, system, or content gaps)
- Fix issues and retest
- Switch to on-demand mode for production
- Run periodic audits on production conversations
Q: Should I keep Verify Responses enabled in production?
A: It depends on your requirements. If you need governance and full auditability for compliance teams (CISO, CIO), keep it enabled – this also surfaces trust scores in Customer Intelligence analytics. If you’re primarily doing spot-checks, on-demand mode reduces overhead while still giving you access when needed.