Checklist · 17 Nov
A setup checklist for a new AI roleplay world
Approved by the founder
How-to · 2 min read
You set up a scene, write what your character does, and the AI answers by writing your next line for you. It decides how you feel, what you say and where you go, and then adds a list of choices you never asked for. A few turns later the story is no longer yours. You spend more time deleting text than playing, and the scene loses the flow that made you start it.
Language models are trained to continue text, so they keep writing past the point where the other character should stop. In a roleplay that means they often write the player's actions too. Prompt instructions like "never speak for the user" help for a while but fade in long sessions. Many chat apps also add their own system prompts and filters on top, which you cannot see or change. And when you bring your own model or key, you still have to clean up every reply by hand. Group scenes make it worse, because the model has to voice several characters and easily slips into yours.
This part describes the usual way. It makes no claims about The Codex AI, so nothing is quoted here.
The Codex AI is a browser-based roleplay and story platform with a feature called Sovereign Guard. It cleans the model's output in several layers so the AI does not take over your actions, write fake lines for your character or add forced choices, and it lets you trim a reply with one click. You can use the free platform model or connect your own provider key or a local model. Your stories can also branch, so you can try another path without losing the first one.
Multi-layer sanitization preventing the AI from hijacking player actions, speaking fake player dialogue, or appending forced choices with instant 1-click dialogue trimming.Quoted from thecodexai.com
Every account gets a platform-provided model on the Free tierQuoted from thecodexai.com
Visual 2D flowchart narrative tree with Quantum Leap and timeline divergence.Quoted from thecodexai.com
End your turn with an action or a question, not an open sentence. A clear stopping point makes it easier for any model to answer only for its own character.
General advice. Not a claim about the product.
Keep important world facts in the lore, not in the chat. When lore is pulled in by relevance on each turn, the model needs fewer reminders and drifts less.
dynamically summon the exact lore and characters needed per turnQuoted from thecodexai.com
Branch instead of rerolling the whole scene. If a reply goes the wrong way, a branch keeps the good part of the story and lets you test another direction.
Visual 2D flowchart narrative treeQuoted from thecodexai.com
Try a different model when one keeps puppeteering. Some models follow turn boundaries better than others, and being able to switch providers is the quickest test.
Direct browser-to-LLM streaming with 18+ providersQuoted from thecodexai.com
No, the Free tier includes a platform model without keys or a card.
Every account gets a platform-provided model on the Free tierQuoted from thecodexai.com
Yes, including Ollama, LM Studio and KoboldCpp.
Local LLMs (Ollama, LM Studio, KoboldCpp).Quoted from thecodexai.com
The importer processes Tavern cards and lorebooks with zero server transmission.
World Info lorebook importer with zero server transmissionQuoted from thecodexai.com
Checklist · 17 Nov
Approved by the founder
· 17 Nov
Approved by the founder
Story · 17 Nov
Approved by the founder