Synthesising selected responses of individual respondents

Survey reports typically show aggregated data across all participants, but understanding individual response patterns requires manually reviewing each person’s complete answers. Deep probe automates this process, synthesising individual participants’ responses to identify deeper insights into their specific preferences, behaviours, and characteristics.

The example below shows you how Deep probe can help you identify specific findings about individual respondents across all their responses.

Working example: Understanding financial concerns of respondents

A fast food chain surveyed 202 customers about their dining habits and concerns. Rather than just seeing overall trends, they wanted to understand each customer’s specific financial concerns to better inform their overall pricing strategy.

To save time from going through individual respondent answers, Deep probe’s LLM analysis was used to summarise the primary reason for reach respondent.

Deep probe setup

1. Navigate to the Deep probe tab in the experiment report and click Add a deep probe .
2. Select Add LLM analysis .
3. Describe what you want to learn about each respondent. For example, What is the primary financial or economic concern of this respondent?
4. The system suggests categories as output type with options such as “Personal financial strain”, “Increased fast food prices”, “Delivery fee concerns”, etc. However, after reviewing the suggested categories, researchers can accept the recommendations or modify them based on their analysis objectives. In this example, the researcher chose string as an output type to generate text summaries rather than categories.

Generated prompt for synthesis

The system generates a prompt based on the settings. Final output quality depends on this prompt and LLM processing. Refine the prompt and preview results to ensure it captures what you want to discover before processing begins.

The following shows an example prompt generated by the LLM based on the request in this example.

Request: What is the primary financial or economic concern of this respondent?

Response:

Outputs overview

In this case, the Deep probe generates a summary for each respondent. Please note that summarisation accuracy varies depending on prompt and LLM processing and cannot guarantee 100% accuracy. Conjointly recommends reviewing outputs and editing individual results where needed.

Based on these individual results, the Summary for string outputs tab presents the overall AI-generated summary identifying overall key themes and patterns across all responses.

Best practices for individual response synthesis

• Analyse complete response sets rather than single questions to capture full participant context.
• Define classification criteria that account for response consistency.
• Include sufficient context in your request to guide accurate profiling.
• Use meaningful category names that clearly communicate each conclusion for stakeholder understanding.
• Layer multiple deep probe analyses to build comprehensive respondent profiles examining different dimensions.

Other example requests for individual respondent synthesis

Individual respondent synthesis extends beyond simple classification, enabling sophisticated participant profiling across multiple dimensions:

Other Deep probe use cases

You can also read about:

• Coding open-ended responses.
• Extracting insights from conversational surveys.
• Creating calculated values from existing data.