A little over a month ago i quit my job to fulltime pursue creating a web based character creator for AI agents and humans to quickly and easily deliver human characters to their games! You can now send your agent to creategamecharacters.ai and it can create realistic looking characters for your games. You can use AI to create outfits for your characters as well as upload a picture of yourself to make yourself a character in your game! Not only that, but the site is filled with docs so agents can easily make in-game character creators so your players can make their own characters like in skyrim or the sims. This would not have been possible without first a good understanding of context routing techniques and the documentation the agents get from the tool is based around that same principle. I will be continuing development on this and I hope it is a tool people find useful!

As always, lets celebrate the win. I have always wanted to create a 3d model, and it feels like I have now -- even though Claude did it for me. This is not refined, or perfected in any way - just asked for a 3d lantern and this is the first thing that was produced. Here is the fun part, Claude asked me if the lantern should rock back and forth in the video. I said yes. Now look closely -- the AI version of rock back and forth is forward and backwards into the frame.

Been implementing context routing on a real project. Bevy game engine, Blender export pipelines, 3D apparel assets. Not a demo, actual production work with messy real world problems. I started with "What NOT to Load" tables. Seemed smart. Tell the agent which files to stay away from. It often ignored it. Not on purpose. It just finds reasons. "I need this one file for context." "This might be relevant." Next thing I know it's loading random apparel assets when I asked it to fix a hoodie. Opening the game viewer when it was supposed to export a Blender file. The problem is simple. Telling AI not to do something is just an instruction. It weighs that against other instructions and decides actually it would be helpful to do the thing you said not to do. So I stopped telling agents what to avoid. Made avoidance structural instead. Each folder has exactly what the agent needs for one job. The Blender command, the inspect tool, the requirements. Nothing else exists in that folder. The agent doesn't avoid the viewer code because I told it to. It doesn't touch viewer code because from its perspective there is no viewer code. That's a different folder for a different agent. Orchestrator sits one level up and routes between isolated folders. Inspect the blend. Export the GLB. Verify in viewer. Three agents, three contexts. Each does its job and reports back. If your context routing relies on agents reading a list of things they shouldn't do and then choosing to comply, you are building on trust. Trust does not scale with AI. Structure does.

I'm drafting a very old sci-fi novel of mine with Claude Code. Four scenes in. More excited about a creative project than I've been in years — and the reason isn't the speed. It's that the workspace is built to refuse. Setup: a folder called `writing-room`. Eight stages, from premise to compilation, each one a markdown directory the AI loads only when it's relevant. Compass, world, characters, structure, voice, writing, revision, compilation. The first rule, hardcoded in `CLAUDE.md`: > Before generating prose, always load `voz.md` and `padroes-prosa.md`. Without these two, refuse the writing task and ask the author to do Stage 05 first. Translation: the AI cannot draft a scene until I've locked in the voice. And `voz.md` was reverse-engineered from scenes I wrote by hand. The voice is mine. The AI only gets to extend it. There's also a file called `padroes-prosa.md` — 9 anti-AI-slope techniques. Verbalized sampling. Fragmentation. Character voice. Rare vocabulary. Every generated scene must apply at least 3, and the reviser uses the same file as a checklist. What this changes in practice: - I don't fight AI prose. I gate it. - Each stage loads minimum context. The AI doesn't drown in 200k tokens of worldbuilding to draft one scene. - After every scene, a `cronista` skill updates a canon file. Continuity stays cheap. - I'm the bottleneck on voice. I'm fine with that. The transferable bit, if you build with AI: The most useful thing your workflow can do is sometimes say no. Refusing to act without the right inputs forces you to produce those inputs — and that's where your taste enters the system. Without that gate, the AI averages you out. Toward the median sentence. The median plot beat. The median version of you. A friend of mine said that "in order to have a second brain, you need to have a primary working brain". I laughed: true enough. I wanted to build the gate first. Then let it write. And I'm loving it.

came back after a week offline and spent an hour just reading posts. people are shipping. full agent teams, named specialists, live clients. and i'm still on the foundation. but here's the honest version of what's actually happening. i build something. it works. then i look at it and realise it's not what i actually wanted. so i break it and start again. then halfway through the rebuild, a new idea comes in and now i don't know if i should finish what i started or pivot to the thing that's clearly better. i've rebuilt the same system three times in a month. and the worst part.. each version was better than the last. so was the rebuilding wrong? or is that just what building actually looks like before it locks in? genuinely asking because i can't tell if this is a me problem or if everyone here is quietly doing the same thing and just posting the final version.