Hey everyone! Sharing this project we’ve been working on.
We run a coaching app for new & aspiring managers (mostly engineering managers and PMs). Users get personalized 2-minute daily tips (we shared it here way back in 2020), and they can reach out to a coach via Intercom chat if they need help with a specific problem.
We typically need at least ~15 mins or so to respond to these coaching requests via chat, and our team isn’t big enough yet to provide 24/7 coverage, so we decided to try out OpenAI’s API to see if we could build an “assistant coach” who can chime in faster and still provide actual value - partly inspired by the Marc Randolph’s (Netflix Co-Founder) quote that “the next wave of disruptive companies will be built by layering domain expertise over GPT-3”.
**We used prompts to give GPT-3 context on its coaching mission, including a coaching framework & questions, we gave it access to our content library of 2-minute tips for managers, and did our best to give it a bit more personality.
The results seem pretty good so far! We’ve introduced “Bunchee” to users in our app already, and just today released the web demo. There are definitely still some issues though:
So far, Bunchee is good at:
- empathy
- humour
- improvising (most of the times)
- understanding that she is a colleague of human coaches at Bunch
What she’s not so great at:
- Actually being available 24/7 (due to OpenAI API dependency)
- remembering past conversations to build more context about the user
- switching modes on the fly: coaching vs. advice vs. search vs. customer support
Tried it. Didn't feel the natural conversation that ChatGPT has, felt more like a regular old 'how can I help you' chatbot. Asked a few questions, picked out some keywords and pasted a very generic bit of advice that wasn't really conversational and didn't seem to take into account information already provided.
I've used the GPT-3 based coaching feature already for a couple of things.... Not bad I have to say to see that LLMs can also be useful for coaching purposes and not only for asking for summarizing books/articles :D
I was wondering how you're going to handle the biases issues that appeared also with the chat functionality in Bing?
Really good question, we're doing mainly 2 things: we're pushing hard on makiing sure that our content comes from a diverse group of experts (Bunchee is referencing the tips/content from our library, which is the main difference to ChatGTP) and we're also working on assembling a diverse panel of coaches, to diversify the perspectives and PoVs of those that "train" Bunchee. And we're open about the fact that she is limited and may give harmful or biased advice.
Hard problem to tackle, for sure! Currently, we're doing mainly 2 things:
1) we're pushing hard on making sure that our content comes from a diverse group of experts (Bunchee is referencing the tips/content from our library, which is the main difference to ChatGTP)
2) we're also working on assembling a diverse panel of coaches, to diversify the perspectives and PoVs of those that "train" Bunchee.
And we're open about the fact that she is limited and may give harmful or biased advice.
Been using Bunch.ai for daily tips for quite a while. Some were very helpful. I wasn't so good at keeping up with new features and tips, though. This will give me another reason to try it. Hopefully, this new feature is as helpful as it can be.
I've used the Bunch.ai automated coach...
And it's fantastic!
I can strongly recommend it for anyone who wants to improve their managerial skills (or soft skills in general).
It does feels quite casual, with small lessons that you can click through on your mobile device. Basically, it's like Netflix (casual), but it's educational for work-related skills :D
We run a coaching app for new & aspiring managers (mostly engineering managers and PMs). Users get personalized 2-minute daily tips (we shared it here way back in 2020), and they can reach out to a coach via Intercom chat if they need help with a specific problem.
We typically need at least ~15 mins or so to respond to these coaching requests via chat, and our team isn’t big enough yet to provide 24/7 coverage, so we decided to try out OpenAI’s API to see if we could build an “assistant coach” who can chime in faster and still provide actual value - partly inspired by the Marc Randolph’s (Netflix Co-Founder) quote that “the next wave of disruptive companies will be built by layering domain expertise over GPT-3”.
**We used prompts to give GPT-3 context on its coaching mission, including a coaching framework & questions, we gave it access to our content library of 2-minute tips for managers, and did our best to give it a bit more personality.
The results seem pretty good so far! We’ve introduced “Bunchee” to users in our app already, and just today released the web demo. There are definitely still some issues though:
So far, Bunchee is good at:
- empathy - humour - improvising (most of the times) - understanding that she is a colleague of human coaches at Bunch
What she’s not so great at:
- Actually being available 24/7 (due to OpenAI API dependency) - remembering past conversations to build more context about the user - switching modes on the fly: coaching vs. advice vs. search vs. customer support
Curious to hear what you all think!