> ## Content Index
> Fetch the complete content index at: https://blog.jestor.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# How to Tell Whether Your AI Agent Is Improving
- URL: https://blog.jestor.com/tell-whether-your-ai-agent-is-improving/
- Published: 2026-09-17T22:39:58.000Z
- Updated: 2026-09-17T22:39:58.000Z
- Author: Bruno Bannach

To **tell whether your AI agent is improving**, track the same measures over time. Improvement is a trend, and a trend requires consistent measurement from the start.

## Why single measurements mislead

A month's figures reflect that month's mix of requests.

- An easier month read as improvement
- A harder month read as regression
- Volume changes mistaken for capability changes
- Knowledge base updates uncorrelated with the result

## What to track over time

| Measure                       | What a trend shows                                |
| ----------------------------- | ------------------------------------------------- |
| **Resolution classification** | Share handled without a person, rising or falling |
| **Handover rate**             | How often a person had to step in                 |
| **Repeat contacts**           | Whether its resolutions held                      |
| **Time to first response**    | The customer-facing effect                        |
| **Volume**                    | So mix changes are visible                        |

## How to track it in Jestor

1. Keep the same classification field in **Jestor** from the first day of deployment.
2. Enable log metrics so response and resolution timing accumulate.
3. Chart the classification distribution by month.
4. Track repeat contacts to confirm resolutions held.
5. Note when the knowledge base was updated, so changes can be correlated.

## Why choose Jestor for tracking AI capability?

Because the agent classifies its own contribution as a permitted field, the trend data accumulates without any separate logging process.

Models are updated periodically per function, so part of any improvement comes from the platform rather than from your material — which is worth knowing when attributing a change.

## Frequently Asked Questions

### Why track volume too?

So a change in request mix is visible. See [jestor.com](https://jestor.com/?ref=blog.jestor.com).

### What shows resolutions held?

Repeat contacts on the same issue.

### Do models change independently?

Yes, they are updated periodically.

## Video Tutorial: Step by Step

Check out other practical tutorials on the Jestor YouTube channel.

## Get to know Jestor

With **Jestor**, you can automate workflows, connect teams, and build internal systems your way — all without code and powered by **AI**. Discover Jestor at [jestor.com](https://jestor.com/?ref=blog.jestor.com) and see how to take your company's operations to a new level of efficiency and control.