Hi Product Hunters! 👋 I'm happy to show you our vision for the future of app development - GPT Pilot beta. 🤔 Why we decided to build GPT Pilot? After talking to over 200 users of our previous project Pythagora, there was one feedback that kept popping up. That many developers are more prone to trusting the code that’s generated from tests than the test that’s generated from code. When you look at it closely, an automated test is nothing more than a description of what needs to happen and since LLMs process natural language so good, we decided to create a tool that would create features from a developer’s prompt. So, we sketched how could that work and the idea behind GPT Pilot is that it serves as a blueprint of how an app development process looks like. For example, when you start working on a feature, you need to first break down the feature into smaller steps, then write initial code, run it, look at the logs, debug the code, etc. LLMs (eg. GPT-4) can write code amazingly well. However, writing code is only 1 part of creating an application. To fully build an app, LLMs need to be able to - write code - run it - read the output - add logs around the code to better understand an issue - debug the code - etc. GPT pilot provides a way so that LLMs can interact with the machine resources like the ones listed above so that AI can, not only generate code, but do real work of app development. 🏗️ How GPT Pilot works? Here are the steps GPT Pilot takes to create an app: 1. You enter the app name and the description 2. Product Owner agent asks a couple of questions to understand the requirements better 3. Product Owner agent writes user stories and asks you if they are all correct (this helps it create code later on) 4. Architect agent writes up technologies that will be used for the app 5. DevOps agent checks if all technologies are installed on the machine and installs them if they are not 6. Tech Lead agent writes up development tasks that Developer will need to implement. This is an important part because, for each step, Tech Lead needs to specify how the user (real world developer) can review if the task is done (e.g. open localhost:3000 and do something) 7. Developer agent takes each task and writes up what needs to be done to implement it. The description is in human-readable form. 8. Finally, Code Monkey agent takes the Developer's description and the existing file and implements the changes into it. We realized this works much better than giving it to Developer right away to implement changes. 🔮 Vision behind GPT Pilot We see how LLMs can code amazingly well. However, they are not 100% perfect so developers will be needed until we get to AGI. We think that now, developers can act as tech leads who are reviewing the code that LLMs generate instead of coding the entire day. With this, we're imagining a future in which developers can create full production-ready apps in days rather than in months. 📖 Additional resources 👨‍💻 [Github repo](https://github.com/Pythagora-io/...) 📝 [Technical blog post explaining how GPT Pilot works](https://blog.pythagora.ai/2023/0...) [part 1/3] 📝 [Technical blog post explaining how GPT Pilot coding works](https://blog.pythagora.ai/2023/0...) [part 2/3] ### Finally, since GPT Pilot is open source, we’d be so grateful if you could star GPT Pilot repo on Github - https://github.com/Pythagora-io/.... After a year of iterating on 4 different test automation products, I believe we finally hit the market need so I’m super excited to present to you Pythagora - an open-source dev tool that creates automated integration tests by analyzing server activity without you having to write a single line of code!

Wow. I am interested in the potential time it could save for developers who are building projects to scratch their itch. Is there a specific programming language or tech stack that works best with GPT Pilot? @leon_ostrez

congrats on your launch 🎉

Looks exciting! What are the weakest points at the moment? How does it compare to others, e.g. smolai or metagpt?

Hey GPT Pilot team! 👋 I curate Quick Byte, a newsletter exploring innovative tech tools. Your dev tool, aimed at skyrocketing developer productivity with AI, is super intriguing! I'm considering featuring it in an upcoming issue to share with our tech-enthusiast readers. Feel free to check out Quick Byte (quickbyte.tech) and consider subscribing. Keep boosting developer productivity! 🚀

Congrats!! It looks amazing! What was/is the biggest challenge you encountered during development of gpt pilot?

if it was 50x I'd try it

Congratulation! Looks exciting! If I lose job because of you you own me a beer

This is a game-changer for any dev. Nice and keep grinding

Very impressive! I knew what Zvonimir and the team were working on and was still floored when I saw the demo. The ability to basically write a tech spec from user requirements, then plan the project and then execute it step by step is a game changer, and a definitive difference from other "code-with-ai" tools out there. I also like that it shows you exactly what it's doing along the way (so you know why it does what it does), and that it asks you to allow it to run commands (I'm wary of just giving some AI full control of my terminal). Amazing work so far, looking forward to using this and seeing you grow the product!

its a wonderful idea. why not 30x? congratulations in the launch

Forwarding this to our devs now, gonna be helpful for them for sure 🙏

Congrats on your launch @leon_ostrez @zvonimir_sabljic1 !!

Congrats on the launch of GPT Pilot. This is a game-changer for devs, seriously. Offloading coding tasks? Mind-blowing! Maybe think about adding some cool customization options to make it even more user-friendly. Keep rocking!

Hey makers, Finding your post has doubled my happiness 😊 First, I was thinking myself to do something like this for a while. However, due to other priorities I wasn't able to do so. Second, I am instantly starting to use it. I will keep contributing my feedback and someday soon will actively contribute to the project. May the force be with you!!

@leon_ostrez : Congrats on the launch team, the product looks amazing.

Being able to offload 95% of coding tasks to AI seems awesome! What specific coding tasks can be automated with GPT Pilot? Keep up the great work and congratulations on the launch @zvonimir_sabljic1!

GPT Pilot's premise of significantly enhancing developer productivity is compelling. To augment its utility further, contemplate the following suggestions: Incorporate a real-time collaboration feature, enabling multiple developers to work simultaneously and interact on the same codebase. Offer a version control system within the tool, to track changes and maintain a history of code alterations. Integrate with popular IDEs and coding environments to ensure seamless transition and compatibility. Your venture into this realm is indeed promising. On a related note, I'm in the process of launching Mentor.AI https://www.producthunt.com/prod..., a platform aimed at providing AI-driven mentorship. I'd value any insights or feedback you might have to enhance its offering. Let's engage on Product Hunt and exchange perspectives!

That sounds like a great tool! I'm sure it will help a lot of developers increase their productivity and save them a lot of time and effort.

You’re so right! When you think about it, code generation is - in terms of time - a small part in the development, much more time is spent on the specification, creation of documentation, and testing. Great work!