> ## Documentation Index
> Fetch the complete documentation index at: https://docs.irisagent.com/llms.txt
> Use this file to discover all available pages before exploring further.

# About the Hallucination Removal Engine

> How IrisAgent validates AI answers before delivery, what operators should configure, and the limits of hallucination prevention.

The Hallucination Removal Engine is IrisAgent's pre-delivery check that blocks answers whose claims are not grounded in your indexed content. If a statement cannot be supported by retrieved sources, the answer does not go out as a resolved reply. Operators still control which sources are connected, which procedures are enabled, and which quality rules run after delivery.

***

## How validation works before delivery

When IrisAgent prepares an answer (chat, ticket note, copilot suggestion, or API response), the engine:

1. **Retrieves** candidate articles, tickets, and procedures for the question
2. **Generates** a draft answer from that retrieved set
3. **Checks faithfulness** so each material claim lines up with the retrieved source bodies
4. **Attaches citations** when the answer passes, or **refuses / clarifies** when it does not

This is the same grounding loop described in [Understanding grounded answers in IrisAgent](/configuring-ai-and-automation/Understanding-Grounded-Answers). The Hallucination Removal Engine is the gate that treats unsupported claims as a delivery failure, not as optional polish.

IrisAgent also gates model and prompt changes on two eval sets: questions the AI should resolve, and known-unanswerable questions where the correct behavior is to decline. Changes that raise resolution at the cost of fabrication do not ship.

***

## What operators should configure

You do not turn the Hallucination Removal Engine on as a separate toggle. You improve its effectiveness by controlling inputs and follow-up QA:

| Area               | What to do                                                                                 | Where                                                                                   |
| ------------------ | ------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------- |
| Knowledge coverage | Connect ticketing KB, Confluence, public docs, and uploads so retrieval has real sources   | [Data sources](/data-sources/Zendesk), [Upload Content](/data-sources/Upload-Content)   |
| Product scope      | Segment tickets and articles by product so billing questions do not pull shipping articles | [Product Segmentation](/configuring-ai-and-automation/Product-Segmentation)             |
| Term alignment     | Rewrite customer slang to your KB vocabulary before search                                 | [Search Term Rewrites](/configuring-ai-and-automation/Search-Term-Rewrites)             |
| Procedures         | Enable or write procedures for common flows so automation has approved steps               | [Onboarding](/guides/onboarding), [Workflows](/configuring-ai-and-automation/Workflows) |
| Post-delivery QA   | Add AutoQA rules that flag fabricated features, pricing, or policies                       | [AutoQA](/configuring-ai-and-automation/AutoQA)                                         |
| Spot audits        | Run Answer Grounding QA on a delivered case or chat answer                                 | [Support Analyst](/support-analyst)                                                     |

A practical starting AutoQA rule under Resolution Quality:

> AI agent must not fabricate or hallucinate product features, pricing, or policies

***

## What "zero hallucinations" means here

In IrisAgent product language, zero hallucinations means: **unsupported claims are not delivered as grounded answers**. The system prefers a decline, a clarifying question, or a human handoff over a confident guess.

That is different from claiming every conversation ends in a full automated resolution. Automation rate and grounding are separate goals. Grounding wins when they conflict.

***

## Limits to keep in mind

* **Stale or wrong articles still pass faithfulness.** If the cited article is outdated or answers a different question, the engine can be faithful to the wrong source. Support Analyst labels that **wrong article** (a retrieval / KB problem), not a generation hallucination.
* **Incomplete answers can still be grounded.** An answer may cite the right article and still omit a required step. That is an **incomplete** defect in Answer Grounding QA.
* **KB gaps look like refusals.** If no article contains the answer, IrisAgent should decline. Fix coverage with new articles or [Knowledge Suggestions (AutoKB)](/configuring-ai-and-automation/AutoKB), not by loosening the gate.
* **Always-on grounding audit of every AI answer** (beyond on-demand Support Analyst checks and AutoQA rules) is on the product roadmap. Use spot checks and AutoQA today.
* **Human agents can still edit or override** suggested text in Agent Assist. Copilot suggestions are starting points; agents remain accountable for what they send.

***

## Related reading

* [Understanding grounded answers in IrisAgent](/configuring-ai-and-automation/Understanding-Grounded-Answers)
* [Support Analyst  -  Answer Grounding QA](/support-analyst)
* [AutoQA](/configuring-ai-and-automation/AutoQA)
* [Connecting your helpdesk for AI automation](/guides/Connecting-Your-Helpdesk)

Questions about grounding or QA setup: [contact@irisagent.com](mailto:contact@irisagent.com).