Notifications
Clear all
Topic starter
Customer or User Interviews are time consuming and expensive. I show you how to automate them using callin.io’s AI Agents and Multi-page Form nodes.
Hey there
I’m Jim and if you’ve enjoyed this article then please consider giving me a “like” and follow on callin.io or X/Twitter . For more similar topics, check out my other AI posts in the forum.
With callin.io’s recently released multi-page forms, I was curious to explore ways to utilise this functionality with AI agents. After a week of experimentation, I’m happy to report AI-powered forms are now definitely a “thing” in callin.io! I have a few templates lined up to share but my fave so far has been my (totally original!) AI interviewer template I’ll talk about in this post.
What is an AI Interviewer?
User research interviews are known to be quite expensive. If you think of the time and cost for preparation, resourcing, executing and reporting, it’s not hard to see why companies do only a few per year and prefer to outsource. The alternative is to run a survey but they’re low ROI - static questions make for a boring experience and don’t serve to dig deep enough to capture insights. How might we conduct quick, cost-effective interviews that still uncover meaningful insights and provide the depth we need?
The AI interviewer could be the perfect solution! An agent can conduct a dynamic interview where it intelligently adapts its questions in response to a user’s answers, is available 24/7 to suit the customer’s availability, can handle hundreds of sessions simultaneously and effortlessly streamlines post-interview data-entry and reporting. I was able to build out the template for my AI interviewer in a matter of days and best part is, by using a free model such as LLama3.2 via Groq.com, the cost of running an interview is close to nothing!
Try out this live demo here: Interview for uncovering people’s experiences preparing for and taking the UK practical driving test
Good to know about the demo
- The topic is UK specific so a little roleplay and imagination is required
- Questions are dynamically generated Using LLama3.2-90b via Groq (free tier). It may bug out at times where the response isn’t formatted correctly. If this happens, start over and try again.
- Responses are deleted after a short period.
How does it work
- Start by providing the AI Agent with an interview topic and the user’s name.
- The AI Agent’s question is presented as a callin.io form and the answer is capture via form submission.
- Each question and answer pair is then recorded in a Google Sheet.
- A loop is then created by directing the flow back to the agent for it to generate another question, repeating step 2.
- When the user asks to stop the interview, the workflow breaks out of the loop and shows the completion screen.
Template
Conclusion
callin.io multi-page forms are an exciting addition to the callin.io AI builders toolkit and opens up new channels where AI can meaningfully interact with your users. I’m still experimenting with other callin.io x form scenarios and will share more templates around this combination in my creator hub soon so watch this space! Working on something similar? Let me know!
if you’ve enjoyed this article then please consider giving me a “like” and follow on callin.io or X/Twitter. For more similar topics, check out my other AI posts in the forum.
Still not signed up to callin.io cloud? Support me by using my callin.io affliate link.
Need more AI templates? Check out my Creator Hub for more free callin.io x AI templates - you can import these directly into your instance!
Posted : 19/11/2024 1:51 pm
My initial thought: A survey with an “unending series of questions” sounds like a terrible customer experience.
Interestingly, this conversational format proved to be quite enjoyable!
It was so engaging that it made me consider if this could represent a paradigm shift in how surveys are delivered to users. Participants can answer as many questions as their patience permits, while the AI keeps them engaged and somewhat entertained.
The conversation, which felt very natural, was slightly at odds with the rapid-fire sequence between input and the subsequent question. Perhaps introducing a small, random delay between steps would enhance the feeling of a genuine conversation. That's my perspective from a UX standpoint.
Well done, excellent concept and very well executed!
Posted : 20/11/2024 9:12 am
Thank you for sharing.
There might be a bug in this workflow.
I tried it out and found that if the browser window is closed midway, the Get Answer node remains in a permanent waiting state with no way to stop the waiting. I restarted callin.io, but after reopening the workflow executions panel, the node is still waiting.
I am currently unable to resolve this issue and would appreciate your assistance. Thank you very much!
Demo video:
I tested the following template:
Conversational Interviews with AI Agents and callin.io Forms | callin.io workflow template
Posted : 09/12/2024 6:50 am
Topic starter
Hello!
This isn't really a bug. Forms place the execution in a waiting state until the user submits, and it's always expected that users might abandon the process.
It's good to know that the execution waiting state doesn't consume resources; it's more of a paused/resumable state. If you're using the latest version of callin.io (1.70), the spinning animation for waiting states has been removed, in case that was a concern.
Posted : 09/12/2024 12:03 pm
I am currently using the latest test version 1.71.1 of callin.io Cloud, and so far, the node is still in a waiting state.
Posted : 09/12/2024 7:51 pm
Hello,
I'm also encountering problems with this workflow. I'm utilizing the self-hosted Community Edition version 1.74.3. The trigger form functions correctly, and the workflow appears to operate as intended until the "Get Answer" node. For an unknown reason, the initial form is activated with the correct specified path, but the "Get Answer" node is looking for a form submission on the path /form-waiting/868, where 868 seems to be the execution ID. If I access that path in a different browser tab, I can proceed with the survey flow as anticipated. It appears there's a communication gap between the form trigger and the "Next Form Page" node.
Posted : 21/01/2025 8:22 pm
I'm encountering the same problem and haven't discovered a workaround yet.
Posted : 21/02/2025 9:15 pm
Topic starter
Thanks for the update.
I'm having trouble replicating the problem; the forms are functioning correctly for me on both self-hosted and callin.io cloud instances! I've been informed about some ongoing issues with forms on specific self-hosted configurations. You might want to check out Bug Report: n8n forms "next form page" not triggering, which could be relevant.
If you're willing to share details about your setups, either publicly here or privately, I'd be glad to investigate further.
Posted : 22/02/2025 11:47 am
It's finally working! It just takes about 1-2 minutes before the next form renders. What could be causing this? The flow itself appears quite fast, but it seems to pause before rendering.
Posted : 23/02/2025 3:30 am
Topic starter
It's difficult to determine without a closer look at your configuration and whether you've modified the template. You might consider creating a new post for this issue to gain more visibility.
I'd recommend trying a different LLM, ideally a fast one like gpt4o-mini or Gemini-flash.
Posted : 23/02/2025 10:21 am
Hi there,
I'm also experimenting with your workflow—thanks for sharing it! I have a question about configuring the Agent to select questions or topics from a predefined list or sheet and then develop the Q&A around them. Ideally, once it has explored a topic in depth, it should transition to the next one, ensuring it covers a set of predefined topics/questions.
Do you have any ideas on how to achieve this?
Posted : 23/02/2025 9:32 pm
I'm also curious about this. My current thought is to utilize Redis or another database to store the workflow's questions. Then, I'd inject these questions into the user prompt message so the system knows what to ask.
Posted : 05/03/2025 8:28 pm
Just tested this out and it's very cool. The continuous question format (with relevant active listening-style questions) was interesting, and I don't think I've ever experienced anything like it before in this multi-step form approach. I suppose it could be simulated with a chatbot.
I can envision a very near future where this is performed with real-time voice-enabled interaction. And to take it a step further, a HeyGen-style avatar.
Posted : 06/03/2025 10:39 pm
Topic starter
Check out my new template which explores this idea of using preset questions for an AI agent - Create Product Satisfaction Surveys with Telegram, Google Sheets and AI | callin.io workflow template
Yes, pretty much you’re managing your own state machine to control the flow of the session and in doing so, lose a lot of that agent autonomy.
When building this new template, I found a big issue with hallucinations, i.e., questions leaking into other questions, agent generating its own questions, etc. The main reason (in my opinion!) was the long-lived and overloaded chat memory. My solution was then to wipe chat memory in between questions so the agent starts fresh.
Posted : 12/03/2025 10:04 am
Hi, this is an amazing workflow. I have a question: can the agent be programmed to ask the same 5 base questions to everyone, and then ask additional questions based on the provided answers? For example, if a person answers that they have 3 siblings, can I program the AI agent to ask the same questions 3 times over (one for each sibling)?
Posted : 12/06/2025 9:33 pm
Page 1 / 2
Next