# Interviewer Agent (Rather than Q&A Agent) **URL:** \ **Category:** API\ **Tags:** prompt-engineering\ **Created:** [August 11, 2023, 12:12pm UTC](https://community.openai.com/t/interviewer-agent-rather-than-q-a-agent/320527 "2023-08-11T12:12:28Z")\ **Posts on this page:** 10\ **Page:** 2
**Author:** ![lwd891214](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/lwd891214/32/77376_2.png) [@lwd891214](https://community.openai.com/u/lwd891214)\ **Post date:** [August 21, 2023, 7:06am UTC](https://community.openai.com/t/interviewer-agent-rather-than-q-a-agent/320527/23 "2023-08-21T07:06:28Z")
Following on this thread and I am working on the similar case - enforce GPT to follow the guideline to conduct diagnosis. It seems like two major routes: 1. Agent/Prompt: explore way to coordinate different prompts/ agent and state to follow the guidelines. 2. Fine-tune model: fine-turn model on specific conversation data which I am not quite sure how to train such data which is not a Q&A pair rather a conversation. ---
**Author:** ![alden](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/alden/32/48075_2.png) [@alden](https://community.openai.com/u/alden)\ **Post date:** [August 21, 2023, 3:05pm UTC](https://community.openai.com/t/interviewer-agent-rather-than-q-a-agent/320527/24 "2023-08-21T15:05:21Z")
> [@dorait1](#): > > You can build it as a custom LLM but that may not work well (we tried it for Python). Foundation models are too big and generic to customize. But here are some thoughts. It might be possible to do this much more cheaply using multi-agent RAGs … not sure a custom tuned LLM is needed (which would be much more expensive to build). > [@N2U](#): > > If you’re open to advise, I’d say try connecting with organizations or groups dedicated to mental health and storytelling. +1 ---
**Author:** ![tekelsey](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/tekelsey/32/119018_2.png) [@tekelsey](https://community.openai.com/u/tekelsey)\ **Post date:** [August 22, 2023, 12:49am UTC](https://community.openai.com/t/interviewer-agent-rather-than-q-a-agent/320527/25 "2023-08-22T00:49:34Z")
There is some very interesting discussion and further information in an exchange on Linkedin including a newsletter article from @bill.french about CustomGPT from @alden and a nice additional blueprint from Bill that people might be interested in. > **[Todd Kelsey PhD on LinkedIn: I like to Pick Winners - I Picked CustomGPT](https://www.linkedin.com/posts/tekelsey_business-blueprint-this-is-a-very-good-resource-activity-7099383349084880897-Ybsn)** > > Business Blueprint: This is a very good resource to file away from Bill French about making a custom ChatGPT for a business. (using CustomGPT) If you want to… See Bill’s draft: [The Hidden Side of Conversational AI · GTC](https://coda.io/@billfrench/gtc/the-hidden-side-of-conversational-ai-43) Basically a set of recipes for making a business. ---
**Author:** ![haymingway](https://avatars.discourse-cdn.com/v4/letter/h/3d9bf3/32.png) [@haymingway](https://community.openai.com/u/haymingway)\ **Post date:** [August 25, 2023, 3:22pm UTC](https://community.openai.com/t/interviewer-agent-rather-than-q-a-agent/320527/26 "2023-08-25T15:22:28Z")
Is there a reason that you have to use system? I love the idea of doing interview by AI . It might be a good alternative to survey monkey, anyone agree? ---
**Author:** ![alden](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/alden/32/48075_2.png) [@alden](https://community.openai.com/u/alden)\ **Post date:** [August 25, 2023, 3:45pm UTC](https://community.openai.com/t/interviewer-agent-rather-than-q-a-agent/320527/27 "2023-08-25T15:45:17Z")
> [@haymingway](#): > > It might be a good alternative to survey monkey, anyone agree? Absolutely – surveymonkey is nice when the questionnaire is very structured and rigid. But when the interview is open ended and diagnostic for example, one can’t have rigid forms. That is where generative AI can really help understand “language” and get behind the meaning of things. ---
**Author:** ![dorait1](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/dorait1/32/8770_2.png) [@dorait1](https://community.openai.com/u/dorait1)\ **Post date:** [October 24, 2023, 4:58am UTC](https://community.openai.com/t/interviewer-agent-rather-than-q-a-agent/320527/28 "2023-10-24T04:58:37Z")
Thanks. Will ping you when the team is ready for early adopter program. ---
**Author:** ![ppatlola](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/ppatlola/32/149972_2.png) [@ppatlola](https://community.openai.com/u/ppatlola)\ **Post date:** [December 22, 2023, 1:04am UTC](https://community.openai.com/t/interviewer-agent-rather-than-q-a-agent/320527/29 "2023-12-22T01:04:31Z")
Have you tried this by chaining agent + voice and if yes, are you seeing issues with latency? ---
**Author:** ![alden](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/alden/32/48075_2.png) [@alden](https://community.openai.com/u/alden)\ **Post date:** [January 12, 2024, 10:46pm UTC](https://community.openai.com/t/interviewer-agent-rather-than-q-a-agent/320527/30 "2024-01-12T22:46:09Z")
Nope – didn’t do the chaining yet. But I did just get the basic interviewer agent working. Hoping to release the github code and streamlit app soon (along with a medium article) ---
**Author:** ![scotfrank](https://avatars.discourse-cdn.com/v4/letter/s/e0b2c6/32.png) [@scotfrank](https://community.openai.com/u/scotfrank)\ **Post date:** [May 9, 2024, 5:57am UTC](https://community.openai.com/t/interviewer-agent-rather-than-q-a-agent/320527/31 "2024-05-09T05:57:53Z")
@alden did you have any luck with the interviewer agent? Would love to see what you built! ---
**Author:** ![bamboriz](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/bamboriz/32/448621_2.png) [@bamboriz](https://community.openai.com/u/bamboriz)\ **Post date:** [September 3, 2024, 9:23am UTC](https://community.openai.com/t/interviewer-agent-rather-than-q-a-agent/320527/32 "2024-09-03T09:23:48Z")
A somewhat good solution will be combining a traditional bot with an LLM. For the Question flow + more natural conversation. For anyone still struggling with this, you can check out this post. > **[Say Goodbye to boring Chatbots by combining Structure (Bot Frameworks) &...](https://ai.gopubby.com/say-goodbye-to-boring-chatbots-by-combining-structure-bot-frameworks-flexibility-llms-18ae70bc73c5)** > > A few months ago, I was scouring the web with one question in mind: Is it possible to control the flow of a conversation with an LLM like… [Previous page](https://community.openai.com/t/interviewer-agent-rather-than-q-a-agent/320527.md?page=1)