AI assistant
Improving answer quality
A repeatable workflow to diagnose bad or missing AI answers, the quality tools in the dashboard, common failure modes with fixes, and a checklist to run before going live.
Last updated: 2026-09-29
Almost every bad answer comes from one of a handful of causes, and each has a specific fix. Follow this page in order: find what the AI was allowed to know, fix the source, then test again.
Diagnosis workflow#
- Reproduce. Open the conversation in the inbox and note the customer's exact words and channel. Send the same message from the web widget or a test number.
- Was the AI even allowed to answer? If there was no reply at all, run the silence checks below. See How the AI works for the gate.
- Find the source of truth. Ask: where should this fact live? Text policy or contact: knowledge base. Price, stock or menu: catalog. Branch address and hours or an offer: business records. Delivery fee: delivery settings. Tone or format: assistant identity.
- Check that the source is correct and ready. Is the file ready? Is the fact stated plainly, once, without a contradicting copy?
- Fix the source, not the prompt. Add or correct the fact. Only then adjust rules.
- Retest with the original wording and two paraphrases, including a dialect version.
If the AI did not answer#
| Check | Where |
|---|---|
| Disable AI replies on | Settings → Inbox settings → AI Assist |
| No AI Assist add-on or subscription inactive | Settings → Plan & usage |
| Credits and wallet empty | Settings → Plan & usage. See Credits and usage |
| No brand in the assistant identity | AI identity: save with a brand. See Assistant identity and scope |
| Conversation Escalated, assigned to a person, or assistant paused | Inbox conversation header |
| WhatsApp AI automation off | Integrations, WhatsApp card |
| Customer sent only emoji, or an automatic reply loop | By design, the AI stops after a few |
Quality tools in the dashboard#
- Inbox. Read the customer message, the AI reply and any handoff summary. Escalated conversations show why the AI stopped.
- Automatic quality review. On the AI identity page, turn on Automatic quality review. Set Replies reviewed (%) (default 5) and a Daily cap (default 20). Each review uses credits.
- AI quality report. In Reports, open AI quality. It shows the average score, the number of reviews under 60, issue types such as hallucination, and recent reviews with an Open conversation link. See Reports and analytics.
- Learned from chats. Human-handled conversations become suggested knowledge for you to approve. See Knowledge base.
- Copilot. Shows draft answers to your operators from the same knowledge, revealing gaps quickly.
Common failure modes and fixes#
| What you see | Likely cause | Fix |
|---|---|---|
| "I could not verify..." reply | The AI's draft was not supported by tool results | Add the missing fact to the KB, catalog or records |
| AI says it does not know | Fact is missing, file not ready, or wording far from the document | Write the fact as text with the customer's words; wait for ready |
| Wrong price | Old price in a KB file, or product entry outdated | Remove prices from KB; correct the catalog |
| Says you are open or closed wrongly | Working hours or timezone wrong, or no published branch | Fix hours in Environment and publish branch records |
| Contradicting answers | Two versions of a policy | Delete the old file |
| Ignores your rule | The rule conflicts with a platform rule, or is vague | Rewrite as one short, checkable instruction; remove conflicting demands |
| Wrong language or dialect | No language rule, or Arabic names not aliased | Add a language rule and aliases for products and areas |
| Refuses a topic | Off-topic for your business | Add real knowledge for the topic, or accept the refusal |
| Escalates often | Repeated unverifiable answers, or customers requesting people | Fill the fact gaps and review the handoff summaries |
| Cannot quote products | General environment without a catalog | Use a Store or Restaurant environment and add products |
| Order not created after "yes" | Quote expired after 15 minutes, a newer message arrived, or the reply had extra words | Ask the customer to confirm again. See Orders and payment links |
| Quiet after a handoff | The conversation is still Escalated or assigned | Reopen it and remove the assignment before handing back |
Pre-launch checklist#
Work through this once before you turn the AI loose on customers.
- [ ] AI Assist add-on is active and credits are available.
- [ ] Assistant identity has a name and a brand, and is saved.
- [ ] Tone, style and 3 to 6 short rules are set.
- [ ] Knowledge base has your policies, contact details and payment methods, all showing ready.
- [ ] No prices, stock or hours in KB files.
- [ ] Catalog or restaurant menu is complete, with Arabic names and aliases.
- [ ] Branches and offers are published in Business records.
- [ ] Working hours, timezone and delivery settings are correct.
- [ ] WhatsApp AI automation is On, and other channels are connected.
- [ ] You tested: an FAQ, a price question, a delivery fee, an order end to end, and "I want to talk to a person".
- [ ] Your team knows how to take over, pause the assistant and approve orders.
- [ ] Automatic quality review is on at a low sample rate.
Keep improving#
Once a week, open the AI quality report, read the lowest-scoring conversations, and fix the source for each one. Review Learned from chats items and publish the good ones. Repeat until the same problems stop appearing.
Can't find what you need? Contact support.