GPT-3 For Product Brainstorming
2020-07-23 | 3 mins reading timeHere is another GPT-3 experiment for you.
In this experiment I attempt to use the GPT-3 model to help brainstorm product ideas or features. There are many ways of going about executing this brainstorm but the approach I take is to setup a conversation amongst a few characters. Initially I set the scene with some initial context. After the initial context, I let the model create a dialogue take over and sometimes inject my own thinking about through one of the "agents" that the model is communicating through.
You will see my injections and prompt in bold below.
The results
START EXPERIMENT:
The below is a conversation overheard in a product design meeting at a software company. The team has a Leader, two graphics designers, and a product manager. They are brainstorming ideas for a new software product to sell to Sales teams and help the teams close more deals.
Leader: OK remember we need to come up with something a sales team needs. Any ideas?
Designer 1: Why don't we make an application where we record all of the steps a salesperson takes to close a deal.
Designer 2: Wow that sounds great. Anyone have any other ideas?
Product Manager: We should make an application that has all of the features you need to close a deal. Like a CRM with checkboxes to tick when you reach certain parts of the sales process.
Designer 2: Yes, that sounds great, I like your idea a lot. What else do we need?
Leader: What about a budgeting tool?
Designer 2: Yes that would be great.
Designer 1: OK that sounds good, we will put these ideas together and think about it some more. What about you guys? Do you have any more ideas?
Designer 3: Why don't we make a checkbox application like the one the Product Manager mentioned. Sales people like checkboxes.
Designer 2: Yes, that sounds great, I like your idea a lot. What else do we need?
Leader: What about a budgeting tool?
Designer 3: Yes that would be great.
Leader: No I don't like that one. Any other ideas?
Designer 2: Why don't we make a checkbox application that has all of the features you need to close a deal. Like a CRM with checkboxes to tick when you reach certain parts of the sales process.
Leader: We already talked about that. How about something fresh? Are there any tools that can be used for selling with email?
Designer 3: I have an idea! What about we build an application that uses Gmail?
Designer 2: Yes that sounds great, I like your idea a lot. What else do we need?
Designer 1: We could do that. We need a way to connect to Gmail and work from Gmail. That way all of the sales person's email is in one place.
Designer 2: OK we will think about that. What else do we need?
Product Manager: Let's take a look at other companies that sell to sales teams. Are there any tools or applications that can be used for selling with email?
Leader: No one is going to buy a software product to help them sell with email. People will just use Gmail for that. Let's look for something else.
Designer 2: Why don't we make a checkbox application that has all of the features you need to close a deal. Like a CRM with checkboxes to tick when you reach certain parts of the sales process.
Leader: We already talked about that. Are there any tools that can be used for selling with email?
Product Manager: Why don't we make an application where we record all of the steps a salesperson takes to close a deal.
END:
Conclusions/Future Work
This conversation could continue forever but I stopped it after it started repeating its self. I could easily imagine, however, how something like this could be to be used to generate high level concepts. There is probably a product here.
A good followup experiment would be to try to beef up the initial prompt with data or other context and see if that improves the generation.