![[The AI Show Episode 143]: ChatGPT Revenue Surge, New AGI Timelines, Amazon’s AI Agent, Claude for Education, Model Context Protocol & LLMs Pass the Turing Test](https://www.marketingaiinstitute.com/hubfs/ep%20143%20cover.png)
.png?#)
.webp?#)
.webp?#)
.webp?#)
![[Fixed] Gemini app is failing to generate Audio Overviews](https://i0.wp.com/9to5google.com/wp-content/uploads/sites/4/2025/03/Gemini-Audio-Overview-cover.jpg?resize=1200%2C628&quality=82&strip=all&ssl=1)
![What’s new in Android’s April 2025 Google System Updates [U: 4/14]](https://i0.wp.com/9to5google.com/wp-content/uploads/sites/4/2025/01/google-play-services-3.jpg?resize=1200%2C628&quality=82&strip=all&ssl=1)
![Apple Seeds tvOS 18.5 Beta 2 to Developers [Download]](https://www.iclarified.com/images/news/97011/97011/97011-640.jpg)
![Apple Releases macOS Sequoia 15.5 Beta 2 to Developers [Download]](https://www.iclarified.com/images/news/97014/97014/97014-640.jpg)
Letting Agents Write and Review Code — A 0dev Milestone(Demo)
0devis an open-source platform that allows you to generate AI agents and query/visialize different data sources. It’s a solo project I’ve been building from scratch, with no funding or backing. Just me, working on it alongside a full-time job. That’s why it’s taken some time to reach this point — but things are finally coming together. In a recent demo, I asked the 0dev agent to send an email with HTML formatting to a specific address. The catch? It needed to fetch the content from an S3 bucket and follow a set of policies defined ahead of time. The agent took the request, generated the code to complete the task, and passed it through an automated reviewer. This reviewer ensures the generated code not only meets policy requirements but also stays true to the intent of the original instruction. It’s a small example of a bigger idea: agents that can reason about what they’re doing, stay within guardrails, and still move fast. Watch the short demo: https://youtu.be/W45FxIGdGeM Source code: https://github.com/0dev-hq/0dev
0devis an open-source platform that allows you to generate AI agents and query/visialize different data sources.
It’s a solo project I’ve been building from scratch, with no funding or backing. Just me, working on it alongside a full-time job. That’s why it’s taken some time to reach this point — but things are finally coming together.
In a recent demo, I asked the 0dev agent to send an email with HTML formatting to a specific address. The catch? It needed to fetch the content from an S3 bucket and follow a set of policies defined ahead of time.
The agent took the request, generated the code to complete the task, and passed it through an automated reviewer. This reviewer ensures the generated code not only meets policy requirements but also stays true to the intent of the original instruction.
It’s a small example of a bigger idea: agents that can reason about what they’re doing, stay within guardrails, and still move fast.
Watch the short demo:
https://youtu.be/W45FxIGdGeM
Source code:
https://github.com/0dev-hq/0dev
