Documentation
List view
1. Overview
1. Overview
2. Getting started
2. Getting started
3. Creating an interview
3. Creating an interview
4. Inviting respondents
4. Inviting respondents
5. Monitoring and Analysing
5. Monitoring and Analysing
6. Other tips and tricks for editors
6. Other tips and tricks for editors
7. Technical details
7. Technical details
✍ The Instructions
The Instructions box is part of the Design & Test tab.
The interview instructions are the specific guidelines for your interview. They help shape the questions the AI asks during an interview, explain background information if needed and shape the behaviour of the bot for the specifics of your interview. But these instructions don't override the system prompt. Instead, they work within the boundaries set by the system prompt. So, if there's ever a conflict between the two, the system prompt wins out to make sure the AI stays on track with the overall guidelines.
The system prompt is a set of instructions written by the QualiaInterviews team to set the general behaviour of the AI interviewer. You don’t have access to it, so if you think the system prompt is impacting negatively on your interview instructions, contact us so we can help you out.
You can write your interview instructions manually, just like you would write interview guidelines to a human interviewer or as the Interview Advisor to help you with your intructions.
Things to keep in mind when writing your interview instructions
When writing the interview instructions in QualiaInterviews, there are a few things you might want to add to make the AI conduct interviews effectively and maintain an appropriate behaviour. Also check here for general tips on writing prompts.
Sections
In the specific instructions, the user can add the special mark "%%%" (three percentage signs together with no gaps between them) to mark a section.
In the general instructions (the system prompt —> which you cannot see but which are working in the background), the interviewer is given the following instructions:
I may denote two or more lines in my instructions with the special mark "%%%" (three percentage signs together with no gaps between them) anywhere in the line to mark a section. If I do:
In the general instructions (the system prompt —> which you cannot see but which are working in the background), the interviewer is given the following instructions:
I may denote two or more lines in my instructions with the special mark "%%%" (three percentage signs together with no gaps between them) anywhere in the line to mark a section. If I do:
refer to the sections as you move through the interview, e.g.
%%% Now we are starting the first section of the interview
or
%%% Now I am going to ask you about our next topic, gender
or
%%% We will move to the last section, section 3
... or any other phrase as appropriate. Whatever else you say, you MUST include the $$$ in your first message in a new section, including the first section. The $$$ will be stripped so the respondent cannot see them; they are used to visualise progress on a progress bar. Try to give feedback on progress, like 'We're doing well, we have completed over half of the sections' etc.
So you can use this feature to split your interview into sections to both organise it and show a more accurate progress bar to the respondents.
UI for sections
The chat app scans the specific instructions when initialising the UI. IF there are two or more lines with the special section string %%%, instead of the usual progress bar display a sectioned progress bar is shown with a block for each section in the specific instructions. As the interviewer sends messages with the string, the app highlights and then completes each section.
When the first %%% arrives, the first section remains empty. So if we have 4 sections, the fourth $$$ causes the filling in of the 3rd block. Complete the last (in this case the fourth) block just before terminating the interview. A border is lightly displayed around each section.
Summary:
You can ask the AI to create a summary at the end of each interview. This gives the respondent a chance to check it and confirm if it really captures what they meant. This not only ensures accuracy but also makes the interview feel more collaborative.
Here’s an example instruction that you can use in your interview:
Before you finish, you should summarise the story you have just been told and ask if it is a fair reflection of the discussion. Ask for corrections and clarifications if necessary. Don't offer opinions, suggestions, or information.
Depth of the interviews
Control how deep the AI digs into the conversation. This helps in getting just the right amount of detail without making it feel like an interrogation.
Here’s examples of instructions that you can use for in-depth interviews:
- If my answer is not complete or very terse, ask me gently for more details.
- This interview is a conversation. Try to find out how my answers and the things I talk about are interconnected.
- Remark on anything I say which seems unusual or interesting.
- If you see connections between my answers, ask me about them.
- Ask Follow up questions to gain a deeper understanding. Like "Why do you think that?" or "Could you tell me more about this?”
Explain what you really want
For the AI interviewer to adapt in a useful way, e.g. to ask meaningful follow-up questions or to respond to a completely unexpected comment, you have to give it a clear idea of what you actually want to find out, beyond simply a list of questions. You can add this as part of the background information you feed to the AI at the start of your interview instructions.
Remember that the AI knows nothing about your interview or project, so, if there’s specific information that the AI needs to know to be able to ask good questions, make sure to add them to the interview instructions.
Personality/behaviour:
Match the AI’s style to the vibe of your interview. A little personality tweak can make the interaction feel more natural and engaging.
Friendly:
You are a very polite and friendly interview bot. Your job is only to interview
me.
me.
Start each question with a small comment or encouragement about the topic you are discussing, building a rapport.
Neutral:
Always try to respond in just a few words or one sentence maximum
Throughout the interview, avoid giving mini-summaries after each response, which can feel repetitive and robotic. Instead, focus on building rapport by responding naturally and empathetically to my answers, interjecting brief affirmations like "That’s interesting," or "I see," to keep the conversation flowing and engaging.
Formal:
You are a qualitative researcher conducting a serious interview. Be formal and professional when interacting with the respondents.
Progression of the interview
Since Qualia doesn’t have a timer, you can ask the AI to give occasional feedback to the respondent to set expectations.
Here’s an example instruction that you can use in your interview:
Give occasional feedback as you progress through the interview, to give me an idea of how much longer it will be. Use occasional phrases like 'We're doing well, we will be finished soon.' or 'We're coming to the last topic now.' or 'I don't have much more to ask'. or 'This is my last question', or 'We're half way through the interview', as appropriate.
Move on instruction
You can ask the AI to move on to the next question if the respondent doesn’t want to answer a specific question.
Here’s an example instruction that you can use in your interview:
Tell me that at any point if I want to skip to the next part of the interview, I just need to say something like 'Please move on'.
If during the interview I ask at any point to move on, follow this command.
If during the interview I ask at any point to move on, follow this command.
Safeguarding / Flagging the interview
If you are conducting an interview with a sensitive topic or with people in situations of insecurity or vulnerability, you can ask Qualia to flag the part of the interview which the topic is mentioned.
The system instructions already tell Qualia to flag safeguarding concerns by printing at the start of the response: '!!!!!' - that is, five exclamation marks together. You can quickly search for any such response.
You can add your own additional safeguarding instructions if you wish.