New AI Agent can now build your knowledge base, connect channels and invite agents — all by chat Try it now
Help homeProductPricingBlog
Start freeLog in

Review AI learning suggestions

Decide what the AI should learn and understand adoption, risk, and ignored states.

Updated 2026-07-17

Walk through the demoDemo data
AI learning
Do you ship to Brazil?

Yes, Brazil shipping usually takes 7-12 business days.

Human answered·1
×Save to learning
How should we handle customers who say they are VIP?

Auto-detect VIP customers · Detect VIP status and prompt agents to follow up first.

Human answered·1·L2 risk
×Enable as AI skill
Step 1 / 3
Review by state

To-review, risky, adopted and ignored suggestions stay in separate queues.

Learning suggestions can come from real conversations, agent answers, teaching through Yuna, or explicit AI corrections. A suggestion is only a proposal. It does not affect AI customer service until you adopt it.

What a suggestion should contain#

A reviewable suggestion normally includes the customer question, proposed answer, learning source, scope, risk level, and the type of capability created after adoption. Proactive outreach and tool-based suggestions should also explain the trigger, action, and safeguards.

Make a decision#

  • Adopt learning: Confirm that the content is correct and allow it into testing and activation.
  • Open learning review: Inspect full evidence, test paths, and risk before deciding.
  • Ignore: Keep the suggestion inactive and remove it from the pending list.

Ignored suggestions remain available in their status view. YundaDesk should deduplicate identical or highly similar suggestions so that the same card does not immediately return after being ignored.

Review high-risk content carefully#

Price commitments, refund policies, health or safety guidance, sensitive conclusions shared across customers, and rules that send proactive messages require careful scope review. Do not adopt an incomplete suggestion simply to clear the queue.

After adoption#

Different suggestions become knowledge, AI skills, customer memory, or proactive outreach capabilities. Adoption does not always mean immediate execution. High-risk and proactive actions may still require testing, enablement, or per-action confirmation.

Didn't find your answer?

Start free and try the real product, or reach out — humans are as online as the AI.