Changelogs
.png)
Radically improve the accuracy of your automatic evaluations by integrating each call's unique data (metadata) directly into your criteria.
Move from generic verification ("Did the agent ask for the phone number?") to factual, dynamic validation ("Did the agent confirm that the number was 769965772?").
How does it work? The {{ }} syntax
Le principe est simple : utilisez des doubles accolades {{ }} pour insérer une variable correspondant au nom exact de l'une de vos métadonnées existantes.
Par exemple, si vous envoyez une métadonnée nommée client_phone avec chaque appel, vous l'utiliserez dans votre grille en écrivant : {{client_phone}}.
During evaluation, our system will automatically replace this placeholder with the actual value of the metadata for the call being analyzed.
Putting it into practice
- Access your evaluation grid configuration.
- Modify a criterion. Include your variable in the description.
- Exemple concret de la vidéo :
Le gestionnaire vérifie que le numéro de téléphone du client est {{client_phone}}
- Exemple concret de la vidéo :
- Save. That's all there is to it!
Advanced use: All types of evaluation
This {{ }} syntax is not limited to general item descriptions. You can also use it in the text fields of other notation systems to define even more refined conditions.
- Exemple pour une condition d'un niveau "moyen" :
L'agent demande l'email {{client_email}} mais ne le répète pas pour confirmation avant de conclure l'appel.
The result: improved precision
Once your grid has been updated, the AI will validate the information against the actual call data.
In the video, the item's rating is NOK because the AI's comment confirms it:
"...it has not been repeated or explicitly confirmed as 769965772."
The system compared the call transcript with the actual value of the {{client_phone}} metadata, providing an objective and accurate assessment.
Resolve "Auto evaluation failed" error
This error occurs when the name of the metadata you've inserted in your {{ }} grid doesn't exactly match the actual name of the call metadata.
As the system cannot find the requested data, it cannot evaluate the criterion.
Video example:
The error Cannot evaluate item without metadata cliente_phone1 is caused by a simple typing error.
- Variable incorrecte dans la grille : {{cliente_phone1}}
- Correct metadata name: client_phone
The golden rule: Copy and paste!
To avoid errors, never type the name of the memory metadata.
- Go to the call page and view your metadata.
- Copy the exact name of the metadata (e.g. client_phone).
- Paste it into your evaluation criteria between the {{ }} braces.
This method guarantees a perfect match and error-free evaluations.

Our new feature automatically detects bots and IVRs in your call recordings. It clearly distinguishes between three parties (agent, customer and bot), preventing the automated voice from being confused with the agent's voice. As a result, you benefit from accurate conversation analysis based solely on actual interactions, improving the reliability of your call evaluations.


Thanks to this new feature, you can now set up alerts for incoming calls using natural language. For example, by defining a prompt such as "A customer is complaining of having been a victim of fraud", any conversation addressing this topic will automatically trigger an alert. These notifications, sent by e-mail or directly to the platform of your choice, enable you to react quickly to critical situations.


Integrated Multilayer Anonymization offers complete and irreversible protection of sensitive data in your calls. Audio is first processed to automatically replace personal information with audio "beeps", which are then transformed into contextual tags in the transcript (e.g. [phone_number], [customer_name]). This process preserves analytical performance thanks to intelligent tags, enabling analysis models to remain effective on anonymized data, while guaranteeing strict compliance with the RGPD and enhanced security thanks to full traceability and an infrastructure hosted in France.
