Automating feedback using ChatGPT and Zapier

Underfitted · Beginner ·🧠 Large Language Models ·1y ago

Key Takeaways

The video demonstrates how to automate feedback processing using ChatGPT and Zapier, showcasing the creation of a form to collect feedback, configuring a workflow to trigger on form submission, and using ChatGPT to generate actionable items from user feedback. It utilizes tools such as Sappier, Zapier, ChatGPT, and Google Sheets to achieve this automation.

Full Transcript

here's the backstory I teach a machine learning class and I get a ton of feedback from my students and the feedback is great but I just don't have time to go through all of it so I've been thinking about hiring someone who can just go and process the feedback for me but then a couple weeks ago coincidentally sappier reached out to me to show me what they're doing with AI in their platform and then I had an idea what if instead of paying someone else to process the feedback what if I build an automation using sappier that processes the feedback automatically for me using artificial intelligence that is what I'm about to do right here and I'll show you how to do the same thing by the way this video is sponsored by sappier and I'm going to be recording a bunch of these workflows and a bunch of these Integrations on their channel so go and subscribe to their channel so you can see more about this in order to build my feedback automation I'm going to start by creating an interface this is my sappier account I'm going to click on form and I'm going to create a simple form to do this now I like to ask people for two questions what do you like about the program and what can I do to improve it so let's edit this form and add those two new Fields I'm going to add a new field here I'm going to make it long text and I'm going to say what do you like about the program when I insert this feel that's awesome and then I'm going to add a new one that says it's also long text what can I do to improve it okay let's keep it simple one thing that I don't feel comfortable doing is asking for email so I'm going to change the position of that the email field I'm going to put it uh last and then I'm going to edit it so I don't make it required so whoever wants to give an email that's awesome if not they don't have to okay cool now I have a form now I can just go and click on this link and this link is going to open the form and I can just try it out I have some feedback real feedback that I receive and I'm going to use that content just to submit it here just for testing purposes what do you like about the program well here is some content what can I do to improve it well extending the course one two more lessons will be nice okay that's awesome let me provide an email here that's my email and I just submitted the form okay so this is working that's the form let's now build the Integrations here so I'm going to close this and I'm going to edit the form and I'm going to go to actions and I'm going to add an action for this form so this action is going to get triggered whenever a user submits the form and what I'm going to do is run a sap now the sap is basically the workflow that we are going to build right now so I'm going to click on create sap and that will open the editor with the form submission right here which is the first thing that's going to happen in my in this workflow when I zoom this in you see this exclamation mark that just indicates that I have not tested this specific component so I'm going to click test the trigger this is going to use the information that I submitted before and it's just going to send that information here you can get the answers that's awesome next step is just to do something with AI so I'm going to click on that plus button and then I'm going to go to apps and click on AI and I'm going to pick cha gbt what I want to uh to do with cha gbt is basically process the feedback and turn that feedback into actionable items a lot of people the feedback that they send me is just is huge there's a lot of content there I just need a bullet list okay so that's what Char gbt is going to help me do so the event here A bunch of uh things that I can do with chat GPT that are pre-created for me I'm going to focus on conversation where I can just provide a prompt and be done with it uh obviously here you're going to have to connect your chpt account to sappier so you can communicate with it I'm going to click continue and here in action is where I'm going to be typing the user message okay so this is the prompt that I'm going to be using write a number list of action questionable tasks based on the feedback received from a user very very simple notice that I added here triple quotes and within the triple quotes I'm going to specify the content that the User submitted through my form now here you get this popup that says insert data and if I scroll down you're going to find the form data which is automatically created by sapure based on the fields that I added form so you see the email you see the first question and you see the second question so I'm going to add the first question I'm going to hit enter here just to give some space and then I'm going to add the answer to the second question so now I'm condensing the user feedback into you know inside the triple quote so chib recognizes that all of that is part of the feedback okay so that is uh good the model that I'm going to be using is going to be GPT 40 mini that is a good enough model for for me you can use any of the models that CH GPT provides I'm not going to make any othero changes here I'm just going to click continue and now I can just test that this integration is working I'm going to click on test step this is going to send now the information the form submission that I created is going to send it to chat GPT and then it's going to show me what CH GPT is going to reply so this is the request and the response says consider adding one to two additional lessons to the course that's it it's just one thing that's coming out of the feedback so this is awesome I can either publish my sap or I can keep adding stuff I'm going to keep adding stuff because I need to send those action items somewhere so what I created before is I have this Excel uh cheet this spreadsheet a Google spreadsheet with what's good what spot and action items and I have an example here in this spreadsheet I want anytime somebody builds out the form and submits it I want my my sap to add that information right here so let's build that is going to be very very simple so I'm going to go to this plus button I'm going to click add step I'm going to find Google Sheets it's right there you can connect to anything here that's the good thing about Sapp here which by the way have been around for a long long time so you can connect to anything applications here so what will be the event well I want to create a spreadsheet row I want to add a new row to my spreadsheet I'm going to click continue I'm going to connect to my Google sheet account I already did that click continue the action okay so I have to select my Google Drive and then I have to select my spreadsheet which is going to be the course feedback here and now I have to select the worksheet I have only one worksheet within that spreadsheet so that's speedback and now this is automatically populating every column on that worksheet that's awesome what do we want to enter under what's good well I can just go to form submission I can look for the first field of feedback and I can enter that bit back there and I can go to what's bad do the same thing for the second question that I'm asking and finally for the action items I can select conversation so I can get the response from CH GPT and add it here I'm going to look for that response here there we go reply there we go I'm going to add that right here that's the connection so I'm going to click continue and now I can just give it a try when I click on test step now this is just connecting to my spreadsheet look at this this is just beautiful now all of the sudden I have the data that I enter right here that's pretty cool but I'm not done yet I'm going to do something else because some of the users might give me an email address and if they do I want to be nice and I want to reply to them saying thank you for sending me feedback this is how your feedback is going to help me something like that right how do I do that well not everyone is giving me an email so I'm going to click add step and I'm going to use the path by sapier which is a built-in tool and what this is going to allow me to do is just to create a condition here now I only need one condition so I'm going to get rid of path B I don't need a path B here just going to click here delete really delete yes please get rid of it and now I can write a condition so I'm going to click there and it says only continue if okay that's good let me just go and select the email from the form if that email exists that's it if it doesn't exist then just don't go down this path so I'm going to click continue and then is go going to tell me whether or not my path would have continued for the test data that I have because I provided an email it says that yes this path would have continued that's awesome I'm going to click continue and now it's asking me for the action that this path is going to lead me to and for that I just want to send an email to that person so I'm going to click Gmail here what will be the event let's just send an email I'm going to click continue I'm going to connect my Gmail account which I already did click continue and here is where I'm going to peel out the pills to send that email to who am I sending an email well obviously to the email provided by the user which I know if I'm here I know the user provided it already because I'm under specific condition from who I'm just going to pick my email address here from the list what will be the subject I'm going to say thanks for the feedback and now I need to to just enter the body here okay so here is just a quick quick email here I'm saying hi there this is an AI response I'd like to disclose that this is not me uh replying to the email directly but I wanted to let you know that I received your feedback and here are the action items that chbt generated from what you told me now obviously here I need to just show the generation whatever chpt decided to create as action items so I'm just going to go to the the popup of insert data going to go to conversations find the reply and I'm going to add right here and then I'm going to finish the email saying let me know if I'm missing something thanks Santiago's AI B okay so that's cool I think what am I missing here am I missing anything I don't think so I think this is done already let me just see I'm not going to enter any attachments no signature I'm going to click continue and now I can give this a test so I'm going to just test this step and this should send an email to myself from myself so I'm going to go to my Gmail account I see okay there is a sent message and as you can see this is the email that I just sent myself okay so now I'm ready to go this is it it took me how long five minutes this is it and I'm honestly don't have to pay anyone to just do this so the final step is to publish this thing I need to publish this app so I can actually share the link to my form and people start entering my feedback so I just click on published uh awesome my sap is live I'm gonna go home this is taking me home uh let me go home let me go to the interfaces and let me just find the link to the interface that I just created here is the link I'm going to click on that link and this is the link that I have to share with people so let's give it one more try let's enter some feedback and let's see if everything is working as it's supposed to be working again I'm just typing here feedback that I already got from other users what can I do to improve it that is a long paragraph that's really really hard to process manually so I'm just going to submit it here also going to add my email and then I'm going to click submit and I'm then I'm going to wait just a few seconds to give time to that sa to do all of the processing and here it is I have what's good what's bad and then I have three action items coming from the feedback of the user and all of that took me 5 minutes to build and it's just running so anyway if you really really like this make sure you go to the sap your channel And subscribe today and they're sponsoring this video I'm going to be building some of these Integrations on their Channel and I hope you I hope to see you in the next one bye-bye

Original Description

Instead of hiring someone else, what if I use ChatGPT and Zapier to automate the processing of feedback from my class? I'll be recording a ton more of these automation videos. Subscribe here: https://bit.ly/3WX0JVi. I teach a live, interactive program that'll help you build production-ready Machine Learning systems from the ground up. Check it out here: https://www.ml.school To keep up with my content: • Twitter/X: https://www.twitter.com/svpino • LinkedIn: https://www.linkedin.com/in/svpino 🔔 Subscribe for more stories: https://www.youtube.com/@underfitted?sub_confirmation=1
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Playlist

Uploads from Underfitted · Underfitted · 60 of 60

← Previous Next →
1 Test-Time Augmentation In Machine Learning.
Test-Time Augmentation In Machine Learning.
Underfitted
2 Don't Replace Missing Values In Your Dataset.
Don't Replace Missing Values In Your Dataset.
Underfitted
3 Introduction to Adversarial Validation In Machine Learning.
Introduction to Adversarial Validation In Machine Learning.
Underfitted
4 Introduction To Autoencoders In Machine Learning.
Introduction To Autoencoders In Machine Learning.
Underfitted
5 Active Learning. The Secret of Training Models Without Labels.
Active Learning. The Secret of Training Models Without Labels.
Underfitted
6 Early Stopping. The Most Popular Regularization Technique In Machine Learning.
Early Stopping. The Most Popular Regularization Technique In Machine Learning.
Underfitted
7 The Confusion Matrix in Machine Learning
The Confusion Matrix in Machine Learning
Underfitted
8 3 Tips to Build a Career in Machine Learning (Unconventional Advice)
3 Tips to Build a Career in Machine Learning (Unconventional Advice)
Underfitted
9 I can predict cars CRASHING. And it's 99% accurate!
I can predict cars CRASHING. And it's 99% accurate!
Underfitted
10 A Critical Skill People Learn Too LATE: Learning Curves In Machine Learning.
A Critical Skill People Learn Too LATE: Learning Curves In Machine Learning.
Underfitted
11 The BEST Machine Learning Interview Strategy.
The BEST Machine Learning Interview Strategy.
Underfitted
12 OpenAI’s Whisper is AMAZING!
OpenAI’s Whisper is AMAZING!
Underfitted
13 5 Lessons You’re NOT Taught in School
5 Lessons You’re NOT Taught in School
Underfitted
14 TensorFlow On Apple Silicon. Step-by-Step Instructions
TensorFlow On Apple Silicon. Step-by-Step Instructions
Underfitted
15 Generating Images From Text. Stable Diffusion, Explained
Generating Images From Text. Stable Diffusion, Explained
Underfitted
16 The Wrong Batch Size Will Ruin Your Model
The Wrong Batch Size Will Ruin Your Model
Underfitted
17 8 Mistakes Holding Your Career Back | Machine Learning
8 Mistakes Holding Your Career Back | Machine Learning
Underfitted
18 AI Just Solved a 53-Year-Old Problem! | AlphaTensor, Explained
AI Just Solved a 53-Year-Old Problem! | AlphaTensor, Explained
Underfitted
19 Bias and Variance, Simplified
Bias and Variance, Simplified
Underfitted
20 Should You Stop Splitting Your Data Like This?
Should You Stop Splitting Your Data Like This?
Underfitted
21 The Function That Changed Everything
The Function That Changed Everything
Underfitted
22 This Model Caused A Nuclear Disaster
This Model Caused A Nuclear Disaster
Underfitted
23 Will Your Code Write Itself?
Will Your Code Write Itself?
Underfitted
24 The Simplest Encoding You’ve Never Heard Of
The Simplest Encoding You’ve Never Heard Of
Underfitted
25 Superhuman AI Cracked An Impossible Game! | DeepNash, Explained
Superhuman AI Cracked An Impossible Game! | DeepNash, Explained
Underfitted
26 Can you become a Data Scientist without a Ph.D?
Can you become a Data Scientist without a Ph.D?
Underfitted
27 How to 10x your productivity with ChatGPT?
How to 10x your productivity with ChatGPT?
Underfitted
28 Cheating the Prisoner's Dilemma
Cheating the Prisoner's Dilemma
Underfitted
29 We integrated OpenAI's Whisper with Spot
We integrated OpenAI's Whisper with Spot
Underfitted
30 The Machine Learning School program
The Machine Learning School program
Underfitted
31 We integrated ChatGPT with our robots
We integrated ChatGPT with our robots
Underfitted
32 Solving complex tasks using a Large Language Model (LLM)
Solving complex tasks using a Large Language Model (LLM)
Underfitted
33 5 problems when using a Large Language Model
5 problems when using a Large Language Model
Underfitted
34 We just discovered faster sorting algorithms!
We just discovered faster sorting algorithms!
Underfitted
35 The 3 most important updates to OpenAI's API.
The 3 most important updates to OpenAI's API.
Underfitted
36 People are divided! Does GPT-4 understand what it says?
People are divided! Does GPT-4 understand what it says?
Underfitted
37 How much should you charge hourly as a Machine Learning freelancer?
How much should you charge hourly as a Machine Learning freelancer?
Underfitted
38 Building a RAG application from scratch using Python, LangChain, and the OpenAI API
Building a RAG application from scratch using Python, LangChain, and the OpenAI API
Underfitted
39 Building a RAG application using open-source models (Asking questions from a PDF using Llama2)
Building a RAG application using open-source models (Asking questions from a PDF using Llama2)
Underfitted
40 How to evaluate an LLM-powered RAG application automatically.
How to evaluate an LLM-powered RAG application automatically.
Underfitted
41 Step by step no-code RAG application using Langflow.
Step by step no-code RAG application using Langflow.
Underfitted
42 I built a simple game using Langchain. Here is a step by step tutorial.
I built a simple game using Langchain. Here is a step by step tutorial.
Underfitted
43 I used the first AI Software Engineer for a week. This is happening.
I used the first AI Software Engineer for a week. This is happening.
Underfitted
44 I deployed a recommendation model. Testing Models In Production using Interleaving Experiments.
I deployed a recommendation model. Testing Models In Production using Interleaving Experiments.
Underfitted
45 How to run PyTorch, TensorFlow, and JAX on your Mac (Apple Silicon)
How to run PyTorch, TensorFlow, and JAX on your Mac (Apple Silicon)
Underfitted
46 How to train a model to generate image embeddings from scratch
How to train a model to generate image embeddings from scratch
Underfitted
47 Building an AI assistant that listens and sees the world (Step by step tutorial)
Building an AI assistant that listens and sees the world (Step by step tutorial)
Underfitted
48 Why are vector databases so FAST?
Why are vector databases so FAST?
Underfitted
49 A Machine Learning roadmap (the one I recommend to my students)
A Machine Learning roadmap (the one I recommend to my students)
Underfitted
50 How to build a real-time AI assistant (with voice and vision)
How to build a real-time AI assistant (with voice and vision)
Underfitted
51 An introduction to Mojo (for Python developers)
An introduction to Mojo (for Python developers)
Underfitted
52 How does Lexical Scoping in Mojo 🔥 works (under 3 minutes)
How does Lexical Scoping in Mojo 🔥 works (under 3 minutes)
Underfitted
53 Building a CI workflow for those who hate it (using GitHub Actions)
Building a CI workflow for those who hate it (using GitHub Actions)
Underfitted
54 How to run Python Code in Mojo 🔥
How to run Python Code in Mojo 🔥
Underfitted
55 AI will not take your job. Here is what I think will happen instead.
AI will not take your job. Here is what I think will happen instead.
Underfitted
56 How to fine-tune a model using LoRA (step by step)
How to fine-tune a model using LoRA (step by step)
Underfitted
57 Late initialization in Mojo🔥 (Python doesn't support this)
Late initialization in Mojo🔥 (Python doesn't support this)
Underfitted
58 The $1,000,000 problem AI can't solve
The $1,000,000 problem AI can't solve
Underfitted
59 A gentle introduction to RAG (using open-source models)
A gentle introduction to RAG (using open-source models)
Underfitted
Automating feedback using ChatGPT and Zapier
Automating feedback using ChatGPT and Zapier
Underfitted

This video teaches how to automate feedback processing using ChatGPT and Zapier, covering the creation of forms, configuration of workflows, and generation of actionable items from user feedback. It's a beginner-friendly guide to getting started with LLM engineering and automation. By following the steps outlined in the video, viewers can create their own automated feedback systems.

Key Takeaways
  1. Create a form in Sappier to collect feedback
  2. Add fields to the form for student feedback
  3. Configure the form to trigger a Zapier workflow
  4. Use Zapier to automate processing of feedback with ChatGPT
  5. Connect ChatGPT account to Sappier for communication
  6. Use ChatGPT response as action item in Google Sheets
  7. Configure Zapier to send email to user with feedback and action items
💡 The video showcases how to leverage ChatGPT and Zapier to automate feedback processing, making it easier to collect, process, and act on user feedback, and demonstrating the potential of LLM engineering for automation tasks.

Related AI Lessons

Building LSTMs with PyTorch and Lightning AI Part 7: Resuming Training with Checkpoints
Learn to resume LSTM training with checkpoints using PyTorch and Lightning AI, enabling efficient model iteration and development
Dev.to · Rijul Rajesh
How AI Learns with Less Labeled Data
Learn how AI can learn with less labeled data, a crucial aspect of machine learning beyond model selection
Medium · AI
Comparing Sarvam-30B and Qwen2.5–14B on Spider Text-to-SQL: An Active-Parameter Perspective
Learn how to compare large language models like Sarvam-30B and Qwen2.5-14B on the Spider Text-to-SQL benchmark from an active-parameter perspective
Medium · LLM
Debugging Benchmark: DeepSeek V4 Pro vs MiMo V2.5 Pro
Compare the debugging capabilities of DeepSeek V4 Pro and MiMo V2.5 Pro on a real-world GitHub bug
Dev.to · Stanislav
Up next
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
Watch →