Hi Everyone With over 8 years of experience in full-stack engineering and AI-driven automation, I specialize in designing and delivering complex, high-impact systems. My expertise spans web applications, distributed systems, real-time infrastructure, and conversational agents, enabling me to build solutions that are both resilient and scalable. On the AI front, I have deep knowledge in voice AI, conversational agents, and workflow automation. I’ve worked extensively with frameworks like LiveKit, LangChain, Twilio, n8n, and Make.com to deliver end-to-end automation and real-time AI solutions. I’m passionate about working in fast-paced environments where ideas are rapidly transformed into production-ready systems. Whether it’s building low-latency voice pipelines or crafting comprehensive automation workflows, I focus on creating user-centric, scalable products that drive growth and innovation. I am currently exploring opportunities to collaborate on ambitious projects that push the boundaries of technology. If you’re looking for a highly skilled engineer with a strong AI automation background, I’d love to connect and help bring your ideas to life at scale.

We are working on the Subordinate Agents Editor, that will allow you to override default prompts and give custom instructions/knowledge to specialized AI agents right away, from the UI, just like you do with Projects. Meanwhile, use the `a0/agents/` directory as your reference, and let's go through the creation of a new agent. Easy way: ask A0 to look into a0/agents and walk you through the creation of your new set of prompts for the new agent. But let's see how it works internally. For example, look at `a0/agents/hacker/prompts`: notice how it overrides the environment and the main role of the agent with `agent.system.main.environment.md` and `agent.system.main.role.md`. 1 - Open the A0 File Browser 2 - In `a0/prompts` you’ll find all the default framework prompts. 3 - These cover every step of the pipeline, including things like the summarization prompt used when a chat gets too long. All of these can be customized if needed. 4 - Take your time to review what you actually want to override or edit, for instance, the communication prompt if you want the agent to output custom fields after “Thoughts” or to change its thinking style, or again the role prompt to make it more robot-like "Executing task... Running code" in a concise way without conversational text. 5 - Copy only the files you intend to modify into a0/agents/your-agent/prompts/, and edit them there. Important: do not copy the entire a0/prompts folder into a0/agents/your-agent/prompts/. You don’t need all prompts whatever your use case is, because any file not present in your agent folder will fall back to the framework default. 6 - Once the new folder is created, your agent automatically appears in the Settings UI (first tab). The folder name becomes the agent name.

That's half of my monthly Claude Max subscription I use for Claude Code. I am very satisfied with the results–built a helpful image generation content agent and Telegram bot interface for it–but I am appalled by how much it cost. Yes, I am spoiled by Claude Code. So I have 2 questions here on this topic: 1. Has anyone found a way to use Claude Code (in particular: your subscription to it) within A0? I have read of people "hacking" CC to use any model within it; this sounds like it would be somewhere in the same realm? Now that I'm done "building", I'm switching over A0's default model to Venice's google-gemma-3-27b-it so it'll just be using DIEM to run the recurring tasks... but damn, that's also horribly inconvenient to have to change the model like that all the time. Which leads to a second question: 2. Any plans for some kind of "model profiles" in the A0 interface so it's quicker to switch in & out of "building" and "automation" modes? Some kind of dropdown of frequently used models would also be helpful to speed things up. (BONUS QUESTION: Maybe there's a way to use A0 more efficiently to bring my Anthropic API calls down? Thanks for any tips)

Sorry if this has been covered maybe needs a reboot: Is there some kind of disclaimer or indemnification needed to shield from lawsuits the use of A0 in malicious attacks? I don't think is necessary is it? I'm curious. I mean there is hacker stuff built into the system...soo...should be fine right?

I just found out about this: https://youtu.be/mMEG074Bkm4?si=4kKeCmJAcPee7vZe