📘

Part of AI Quality Monitoring. New to the feature? Read the Overview first.

AI Resolution is the share of conversations where the evaluator judged that the user's request was handled.

Resolution = resolved conversations ÷ evaluated conversations × 100

You'll see it in Overview → Health, Overview → AI Impact, Overview → Louis, Use Cases and across the Performance report. The tooltip reads: "AI-assessed conversation resolution rate".

What the evaluator is told to do

The evaluator opens with one instruction:

You are a strict evaluator for customer/virtual assistant conversations. Your task is to judge whether the assistant resolved the user's request.

It has an explicit list of what counts and what doesn't. Here it is, in plain language.

Counts as RESOLVED

1. The bot answers directly. The user asked, the bot told them.
2. The bot identifies the need and points to a valid, specific resource that actually matches the problem — a page, a link, a form. Not "see our website", but the right destination.
3. The bot correctly escalates to a human agent, and that agent handles the request in the conversation. The outcome is positive even though the bot itself did not answer.
4. The bot correctly recognises that the action requires customer support and says so clearly — provided this is genuinely the right process, and not a way of dodging a request it could have handled.
5. The user asks to be escalated and the bot gives a concrete way to reach support — a phone number, an email address, a link, specific instructions. The user leaves with an actionable next step, so it counts.

Counts as NOT RESOLVED

1. Generic, unhelpful or irrelevant answers. Words were produced. Nothing was solved.
2. The bot misses the intent and answers a different question.
3. The user asks to be escalated and the bot refuses, with no alternative contact and no next step. A dead end.
4. The bot deflects to customer support when it could have resolved the request itself. Passing the buck.
5. The conversation ends with neither a resolution nor a proper escalation. It just stops.

Two things this number is not

These are the two misreadings that cause every argument about this metric.

⚠️

Resolution is not "the bot answered without a human"

A correct escalation counts as resolved. The user needs a human. The bot recognises it and hands over cleanly, or gives them a real way to reach support. The request was handled. That is a good outcome, and the evaluator scores it as one.

What is not resolved is a dead end: refusing to escalate with nothing offered instead, or deflecting to support on a question the bot could have answered.

If you are used to reading "resolution = no handover", set that definition aside here. It is a different metric. You'll find the no-handover view under Automation rate in Overview → Health.

⚠️

Resolution does not measure whether the user was happy

The user's feelings are not part of this judgement. The evaluator measures objective effectiveness: was the request handled, yes or no.

Example. A customer asks for a refund. The policy says no refund. The bot states the policy correctly, clearly, with the right conditions. The customer is furious.

That conversation is RESOLVED. The bot did its job perfectly. The customer didn't like the answer — but "the customer didn't like the answer" is not a bot problem, it's a policy reality. Scoring it as a failure would tell you to fix a bot that isn't broken.

Frustration is not ignored, though. It is captured separately, in the CX Score and in Sentiment → Dissatisfaction Drivers. That separation is the point: it lets you tell "my bot is failing" apart from "my customers dislike this policy". Those two problems have very different fixes.

How to read this number

Expect a number lower than you imagined. That is normal.

You have never had this number before, so you have no reference point for it.

There is no target to hit here, and no benchmark to compare yourself against. This metric is new, and a resolution rate only means something against your own bot, on your own topics — it depends entirely on what you ask your bot to handle. A bot answering opening hours and a bot handling payment disputes are not the same job, and no single number is "good" for both.

What we can tell you is what to expect. The first number almost always reads lower than the impression you had. That is what happens when a strict evaluator — one that gives no credit for words that didn't help anyone — replaces an impression.

You are not reading a drop in performance. Nothing changed in your bot this month. You are reading the first honest measurement of a level that was always there.

The comparison that means something starts today: this topic against that topic, this month against last month. The level tells you where you start. The trend tells you whether the work is paying off.

These numbers move

This is not a fixed property of your bot. It is a measurement, and measurements move.

Three things move it, and you control two of them. Content: a topic fails because the answer isn't there, you add it, the topic recovers. Flows: a request needs a real path — a failed payment needs a retry, not a paragraph — and you build it. And the share of conversations you hand to a generative AI step rather than a scripted one, which the AI Impact section measures on your own data.

The point is narrower than a promise, and it holds: this is a number that moves — and you now have it.

The evaluator can be wrong, and it will get better

Be clear-eyed about what you are holding:

• It produces false positives. Some conversations it marks resolved were not.
• It produces false negatives. Some conversations it marks unresolved were handled fine.
• It is a judgement, not a fact. A different reader — including you — might rule differently on a borderline conversation.
• It will be improved over time. The criteria evolve as we learn where the evaluator is wrong.

None of this makes the number useless. Two reasons:

1. It is consistent. The same criteria are applied to every conversation, every day. Even if the absolute level is imperfect, comparisons are solid — this topic versus that topic, this month versus last month. That is what you actually need to make decisions.
2. You can check its work. Every number drills down to the real conversations behind it. Click a topic, read the transcripts, form your own opinion. If you disagree with the evaluator, you can see exactly where and tell us. Nothing is hidden.

📘

Use it as a compass, not a verdict

Don't put this number in a contract or a bonus target. Use it to find where to look. Its job is to point you at the handful of topics that are costing you the most, out of the thousands of conversations you will never read. It does that job well.

Now act on it

Reading the number is step 1. To move it, follow How to improve your resolution — it starts from Performance → Unresolved Drivers and walks the find → read → fix → re-measure loop.