ChatGPT Plus helped me skip reading online reviews when I needed a mechanic.

ChatGPT Plus helped me skip reading online reviews when I needed a mechanic.

AI Helps Find the Perfect Car Mechanic: A Hilarious Experiment

mechanic

Finding a reliable car mechanic can be quite a challenge. So, I decided to put AI to the test and see if it could help me locate the perfect mechanic. Armed with my trusty ChatGPT Plus subscription, I set out on an adventure to find the best car repair shop locally.

Before we dive into the details, let me first explain the power of ChatGPT Plus. Besides the obvious advantage of it being based on the advanced GPT-4 model, ChatGPT Plus comes with some incredible features like the Code Interpreter and ChatGPT plugins. These plugins are game-changers as they allow ChatGPT to tap into the current data available on the web. For this experiment, I made use of the WebPilot plugin.

Our car, a 13-year-old Ford, has served us well over the years. However, it has reached a point where it requires some serious attention. Instead of taking it to the dealer, we wanted to find a local mechanic here in town. This is where ChatGPT Plus came into play. I decided to run the same queries using Melbourne, Florida (a town on the other side of the country) as an example to protect the identity of our actual mechanic.

My plan was simple: I wanted ChatGPT to analyze Yelp and Google reviews of local car repair shops to determine the one with the highest customer satisfaction. With ChatGPT Plus, enabling plugins is the first step. So I activated the WebPilot plugin to get started.

It’s worth mentioning that during my experimentation, I discovered that ChatGPT often got confused when scanning both Yelp and Google reviews together. So, I separated those queries, but it still occasionally got lost in the process. Nevertheless, I persisted and fed it my first prompt:

“Use WebPilot to scan Yelp reviews for car repair shops local to Melbourne, Florida. Aggregate the review results and let me know which repair shops, based on the average review value and the number of reviews, produce the highest level of customer satisfaction. Do not include any car dealers or repair shops that are part of car dealers, and be sure to stay solely within Melbourne.”

The response I received was fairly useful, providing some valuable insights. Encouraged by this, I proceeded to instruct ChatGPT to do the same with Google reviews. Unfortunately, it got a bit lost, confusing LA Fitness and Home Depot with auto mechanics. Undeterred, I gave it another chance, asking it to substitute Google for Yelp:

“Do the same, but use Google reviews instead of Yelp reviews.”

However, this time it simply failed and directed me to search for the results myself. It was clear that a more comprehensive prompt would be needed, so I modified the original prompt, replacing “Yelp” with “Google”:

“Use WebPilot to scan Google reviews for car repair shops local to Melbourne, Florida. Aggregate the review results and let me know which repair shops, based on the average review value and the number of reviews, produce the highest level of customer satisfaction. Do not include any car dealers or repair shops that are part of car dealers, and be sure to stay solely within Melbourne.”

This time, it worked like a charm! I proceeded to ask ChatGPT to perform a sentiment analysis on both sets of shops based on their Yelp and Google reviews, ranking them in terms of customer satisfaction. I also requested a short descriptive summary reflecting overall satisfaction levels. However, the initial attempt did not yield an aggregated ranking.

Determined to obtain the results I desired, I added more specificity to my prompt, highlighting the importance of combined Yelp and Google reviews, including review count, number of stars, and customer comments:

“Now perform a sentiment analysis on both sets of shops based on their COMBINED Yelp and Google reviews (REVIEW COUNT AND NUMBER OF STARS), AS WELL AS ALL THE CUSTOMER COMMENTS, and rank them in terms of how customers rate them OVERALL, along with a short descriptive summary that reflects overall customer satisfaction or lack of satisfaction.”

Finally, things fell into place. ChatGPT presented a combined detailed report, followed by an overall ranking of the repair shops.

With these valuable insights in hand, we decided to take our Ford to the repair shop recommended by ChatGPT Plus. So far, the experience has been truly satisfying. Not only did they provide excellent service, but they also saved us a significant amount of money by charging a fraction of what another shop had quoted. Our over-the-hill Ford is back on the road, thanks to AI!

As a college professor, I always encouraged my students to show their work, so I decided to do the same with ChatGPT Plus. The results were interesting and amusing, showcasing how the AI arrived at its conclusions. However, it’s important to approach the aggregated sentiment data with caution, as it can be challenging to verify its reliability.

Overall, this experiment with ChatGPT Plus turned out to be a delightful adventure. AI has the potential to assist us in aggregating public sentiment data, but we must be mindful of its limitations. While it may occasionally lose the thread of the conversation, it can still offer valuable insights and recommendations.

I’m intrigued by the possibilities AI presents, and this experience has been both fun and rewarding. Our Ford is proof that AI can lead us to satisfying results. So, the next time you’re in need of a trustworthy car mechanic, why not give AI a shot?


Don’t forget to follow my day-to-day project updates on social media! Subscribe to my weekly update newsletter on Substack, and connect with me on Twitter at @DavidGewirtz, Facebook at Facebook.com/DavidGewirtz, Instagram at Instagram.com/DavidGewirtz, and YouTube at YouTube.com/DavidGewirtzTV.