Let Safina create individual AI evaluations in the background.

You have already learned how to teach Safina to ask direct questions in a conversation. But what if your assistant could do even more? What if it could also recognize things that are not directly stated?

This is exactly the function of individual AI evaluations. You assign a second, specialized AI here, which analyzes the entire call log after the call and searches for hidden features defined by you.

Why not just ask directly?

Some information is better obtained through analysis than by asking a direct question.

A good example is urgency. If you ask a caller directly: "Is this an emergency?", the answer is often "Yes" out of a concern of not being taken seriously. However, an AI can assess the urgency much more objectively from the context. It pays attention to word choice ("everything is underwater", "it smells like gas") and wording to distinguish real urgency from perceived urgency.

You can leverage exactly this ability.

How to create an individual evaluation

The setup is simple and follows a similar logic to creating questions in the conversation guide.

Step 1: Find the right menu item

Go to the "Safina AI" tab in your Safina app. Scroll down to the bottom of the configuration list and select "Individual AI Evaluations".

Step 2: Create a new evaluation

Click on the "Add Evaluation" button or a similar plus symbol. You will now see the familiar mask where you can assign a title and select an evaluation type (e.g., Yes/No, Rating, etc.).

Step 3: Formulate the instruction to the AI

Here lies the crucial difference. In the large text field, you do not write a question that Safina should ask the caller; rather, you write a clear task for the analysis AI that reads the conversation afterwards.

Practical example: Recognizing "Revenue Potential"

Let's go through a concrete example. We want Safina to automatically recognize whether a caller is a potential new customer with a lucrative project.

1. Click on "Add Evaluation".

2. Assign title: Enter the title Revenue Potential.

3. Choose type: Select a "Yes/No question" as the evaluation type.

4. Formulate instruction: Write your exact task to the AI in the instruction field. Be as precise as possible here. For example:

"Analyze the entire conversation transcript. Return 'Yes' if the caller is a potential new customer and signals interest in a comprehensive service or an expensive product (Examples: complete bathroom renovation, new website development, purchase of a new car). Return 'No' if it is a small repair, a simple question, or an existing customer with a support issue."

5. Save: Click on "Save". Your new, intelligent evaluation is now active for every call. You will find the result in the AI evaluations of each call summary in the future.

Your invisible data analyst

These background evaluations are like an invisible analyst who helps you prioritize your calls better, recognize sales opportunities, and understand your customers on a deeper level – all fully automated.

Your Safina Team