How to Export and Analyze Conversations from Custom GPTs Across Channels
Are you looking to track and analyze interactions with your users across various channels like web chat widgets, WhatsApp, Instagram, and more? If so, you're in the right place. In this article, we'll show you how to automate the exporting of transcripts from your custom GPT deployments and provide you with a complete automation template for analyzing and extracting valuable data from them with the help of AI. By the end of this article, you'll not only know how to automate the exporting of transcripts from your custom GPT deployments, but you'll also get access to a complete automation template for analyzing and extracting valuable data from them with the help of AI, adding huge value to your GPT-powered solutions.
Table of Contents
- Introduction
- How the System Works
- Setting Up the Airtable Database
- Setting Up the Make Automation
- Aggregating the Data
- Analyzing the Transcripts
- Overview of the Data
- Pros and Cons
- Highlights
- FAQ
Introduction
Many businesses are deploying custom GPTs to various channels like web chat widgets, WhatsApp, Instagram, and more. However, without properly storing and analyzing the data from these channels, you're losing half of the value of your GPTs. This data can contain valuable information for use in future decision-making. In this article, we'll show you how to automate the exporting of transcripts from your custom GPT deployments and provide you with a complete automation template for analyzing and extracting valuable data from them with the help of AI.
How the System Works
We'll be using the OpenAI Assistant API to request and pull all of the transcripts and messages from the interactions that our users have had with the API. OpenAI allows us to get that information at any time we want, but we need to know how to request that information from the API, which is what we'll be covering in this article.
We'll be building on top of all of the work we've done in our prior videos, such as our WhatsApp and Instagram deployments. In order to fully understand this and how it's all working, you need to watch one of those videos. Essentially, we'll be using that same system, adding a little bit in that allows us to export the transcripts and then showing you the Airtable setup that we're using and also the Make automations.
Every time a conversation is started on our website, on WhatsApp, on Instagram, or wherever it is, we are going to be saving what's called a thread ID. In my prior builds, we hadn't been doing anything with that thread ID apart from using it in the conversation. In this case, we are going to be saving that thread ID to an Airtable and then we're going to be taking that thread ID and looking up all of the messages within that thread ID, pulling them all out, packaging them up, analyzing them, and then putting them all into a nice database and spreadsheet for us to look at and analyze later.
Setting Up the Airtable Database
To get started, you need to clone our Airtable base, which will be available in the resource hub. Once you've cloned the Airtable base, you need to do one thing in order to make this work on the Make side, which is to go over to the top right and click on the API Keys. You can click on the web API documentation, and if you go down to the Smith Solar CRM, you can scroll down to the threads table and if we go to create a record, it will get this URL here that says threads at the end. You need to copy that and then head back to our main.py file and delete this, which will be my one, and paste in yours. That will make sure that it's trying to send to yours and not mine.
Setting Up the Make Automation
To get started with the Make automation, you need to download the template from the resource hub and import it into Make. Once you've done that, you need to set up the Airtable connection and copy the exact settings for the base, table, view, and output field. You'll also need to set up the other Airtable nodes with the same settings.
Once you've set up the Airtable connection, you can run the automation, which will search for records in Airtable that are ready to be processed. It will then aggregate them into an array and loop through each record, pulling the thread ID and calling the OpenAI API to get the information from the thread. It will then process the data and send it back to Airtable, updating the record with the transcript and the tags.
Aggregating the Data
Once you've run the automation, you'll see the processed records in the Airtable base. You can then aggregate the data into an overview table, which will allow you to see how many messages are coming in, how many are related to pricing, features, about, and other questions.
Analyzing the Transcripts
With all of the data in one place, you can start to analyze the transcripts and pull out valuable insights. You can use the Make automation to label the transcripts with tags and then use Airtable to filter and sort the data based on those tags.
Pros and Cons
Pros:
- Automates the exporting of transcripts from custom GPT deployments
- Provides a complete automation template for analyzing and extracting valuable data from transcripts with the help of AI
- Allows businesses to track and analyze interactions with users across various channels
- Provides valuable insights for future decision-making
Cons:
- Requires some technical knowledge to set up
- May require additional tools and software to fully analyze the data
Highlights
- Export and analyze conversations from custom GPTs across channels
- Automate the exporting of transcripts and extract valuable data with the help of AI
- Use Airtable to store and manage the data
- Use Make to automate the analysis of the data
- Aggregating the data into an overview table to see how many messages are coming in and what they're related to
- Analyzing the transcripts to pull out valuable insights for future decision-making
FAQ
Q: What is a custom GPT?
A: A custom GPT is a machine learning model that has been trained on a specific dataset to generate text that is specific to a particular domain or use case.
Q: What channels can I use to deploy my custom GPT?
A: You can deploy your custom GPT to various channels like web chat widgets, WhatsApp, Instagram, and more.
Q: What is Airtable?
A: Airtable is a cloud-based database management system that allows you to store and manage data in a spreadsheet-like interface.
Q: What is Make?
A: Make is an automation platform that allows you to automate repetitive tasks and workflows.
Q: How can I use the insights from the transcripts to improve my business?
A: You can use the insights from the transcripts to identify common questions and issues that users are having and use that information to improve your product or service.
