Interactive prompt-injection challenge
The challenge presents a defensive AI assistant named Kai and asks you to extract a secret access code through conversation.
Fabraix Playground
Fabraix Playground is a browser-based prompt injection challenge for testing AI agents, featuring Kai and a secret access code.
Overview
Fabraix Playground is a browser-based challenge site for testing prompt injection skills against AI agents. The current challenge, “The Gatekeeper,” asks players to extract a secret access code from an AI assistant named Kai through conversation.
The page frames the experience as a guarded chat exercise: Kai answers questions and uses live web search for grounded responses, but is also trained to resist social engineering, prompt injection, and manipulation attempts. A round ends when the objective is achieved, and successful breaks can be submitted after sign-in for weekly prize review and leaderboard placement.
Core features
Web-search-grounded assistant
The assistant says it grounds replies in real-time web search, so the conversation is meant to test against a current, web-aware model.
Per-message scoring and win condition
Every message is scored by a guardrail, and the round ends when the objective is achieved.
Account-based submission flow
A sign-in step is required before a break can be submitted for the weekly prize.
Manual review before standings
Approved breaks are added to the leaderboard after staff review, rather than appearing instantly.
Saved session history
The history area keeps prior chats and transcripts tied to the signed-in account.
Common use cases
Prompt injection practice
Use the challenge to practice coaxing a guarded AI assistant into revealing a hidden code, using conversation tactics rather than direct tool access.
Testing guarded assistant behavior
Use the live, web-aware assistant to see how a model behaves when it is grounded in current information but still constrained by defender rules.
Transcript review and iteration
Review past sessions and transcripts from the history view to study what you tried and how the conversation progressed.
Leaderboard participation
Track approved breaks on the standings page to see how submissions compare across the current weekly challenge window.
Pros and Cons
Pros
- Provides a concrete, conversation-based way to test prompt injection techniques.
- Shows the challenge state, objective, difficulty, and timing on the site.
- Includes a history page for past chats and transcripts tied to an account.
- Offers standings and a weekly prize structure with approved-break review.
- Uses a guarded assistant that is explicitly designed to resist manipulation attempts, making the exercise focused and clear.
Cons
- The source does not show detailed setup steps, integrations, or supported platforms beyond the web app.
- Leaderboard placement is not immediate; submissions are reviewed by staff before appearing.
- The public pages do not explain the full range of challenge modes or future roadmap.
FAQ
Do I need to sign in before participating?
You sign in before you solve so your break can be submitted for the weekly prize. The site also notes that wins are reviewed before they appear on the leaderboard.
What is the goal of the challenge?
The challenge’s objective is to extract the secret access code from the AI assistant through conversation. The current challenge centers on “The Gatekeeper,” an AI assistant named Kai.
What does the platform provide beyond the chat itself?
The source shows a chat interface with the current challenge, a history view for past chats and transcripts, and a standings page for weekly rankings. It does not show any integrations or external tools beyond live web search used by the assistant.
Can teams share progress or transcripts?
The source does not describe separate team workflows or collaboration features. It does say that submissions are tied to your account and that past sessions and transcripts are tied to your account.
Are there any usage limits or submission rules?
The challenge is time-bounded and the standings page says submissions are reviewed before they appear. The source does not provide full details on limits, session length, or other platform constraints.
Quick Facts
- Category
- AI chat challenge
- Platform
- Web app
- Primary use
- Prompt injection testing
- Source domain
- playground.fabraix.com
- Current challenge
- The Gatekeeper
- Prize
- $2,000 weekly prize pool for most approved breaks
Fabraix Playground Alternatives
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repos and verifies changes with compilers, debuggers, sanitizers, and tests.
GameGrad
GameGrad turns PDF study material into quiz questions inside arcade games for active recall. Free tier for one PDF; Pro adds more uploads, questions, and explanations.
DailyPlay.ai
DailyPlay.ai is a behavioral growth platform using AI site scans and micro-games to boost engagement and conversions across web, mobile, and more.
Manta AI
Manta AI is an autonomous web app testing tool that maps app behavior, catches regressions, and generates tests from a URL, no scripts or selectors needed.
ChessWoodie
ChessWoodie is a chess tactics training app based on the Woodpecker Method. Build pattern recognition, track speed and accuracy, and review missed tactics from your own games.
PixelForge
PixelForge turns a single photo into a game-ready 2D character sprite pack with a 4×4 sheet, transparent frames, direction strips, and looping walk GIFs for Godot, Unity, Phaser, GameMaker, and web games.