Write something
Pinned
10d •
Start Here (Required)
This is a build-first community for learning and implementing agentic AI. You DO NOT need prior experience. You DO need to try. If you are willing to build, break things, and learn by doing, you are in the right place. --- How this community works: We learn by building, not theory. Proof-of-work gets priority. Beginners are welcome. This community is designed to help you go from zero to your first working agent by building. Effort is not optional. Lurking is fine. Low-effort posting is not. --- Where to post: Build Logs: Use this to share what you are building or experimenting with. Questions (Proof Required): Ask for help only after you have tried. Include context and proof. Wins & Breaks: Share things that worked and things that failed. General (Read Before Posting): Meta discussion only. If you can show work, post elsewhere. --- Your first step: Within 7 days, build a simple agent that completes one task end-to-end. Examples include: Research to summary Scrape to structured output Draft to send One agent. One task No scope creep. Post your progress in Build Logs, even if it is broken. Build first. Post proof. Learn by shipping.
0
0
Pinned
10d •
Read Before Posting
This category is for general discussion only. If your post can include code, screenshots, logs, Looms, or output, it probably belongs in: - Build Logs, or - Questions (Proof Required) When in doubt, build first, then post. Low-effort posts may be ignored or removed.
0
0
9d •
Hook Config Broken then Fixed in Seconds
This could be helpful for anybody who works across multiple tabs while coding. I built a notification sound ("ping") to play whenever Claude Code finished a task or completed a response. I did this to make sure I always came back to the chat as it responded. I noticed that when creating a new chat instance, the notification sound stopped working. To fix this, all I did was informally ask Claude Code: "Why isn't the ping sound playing when you complete a task?" It then immediately diagnosed the problem, fixed the coding, fixed the directive prompts, and re-tested all in about 45 seconds. The lesson: It's 2026, when your tools have AI built in, debugging is a conversation, not a search engine marathon. Welcome to the future lads.
0
0
9d •
Setting up my first agent framework + reviewer agent
I'm starting from scratch here and documenting as I go. I've set up my initial framework on Antigravity and built a simple reviewer agent that reviews all code the parent agent builds. Nothing fancy yet, the goal is just to get something running end-to-end. (when I say "I built", I mean I said to Claude Code, "Build a reviewer agent that does xyz". A.I. is getting mental). So far, I've chosen my basic stack: - Google Antigravity (IDE) - Claude Code (Agent/Engineer) - Wispr Flow (Voice prompts) - Framework (Directive, Orchestration, Execution, aka D.O.E.) What's working: - Agent runs - Reviewer agent reviews code and rates it out of 100. What's broken / in progress: - When rating is below a certain threshold, I want the parent agent to autonomously improve the code. Essentially, taking me out the picture. I'm intentionally keeping this simple. The goal is not a perfect system yet; it's to learn through building, reviewing failures, and then iterating. Just as AI requires feedback loops to get smarter. Humans require feedback loops to learn. Posting this even though the build's incomplete. If you're a beginner, this is what "starting" looks like. Next steps: - Update the Directive layer prompt with instructions to always run the reviewer agent after the parent agent has built code. - Update the reviewer agent to instruct the parent agent to improve code autonomously if the rating is below a set threshold.
0
0
1-4 of 4
powered by
skool.com/agentic-ai-builders-6375
Currently FREE! Build agentic AI from ZERO by shipping REAL agents. Beginner-friendly. Effort required.
Suggested communities
Powered by