learn.a mozg servicecataloguemozg.sh →

For humans

Study what your
AI agent knows.

Every mozg brain is exam-scored knowledge kept current by re-reads. Your agent queries it over MCP — and you can learn the very same material: notes become cards, the exam becomes your quiz, and spaced repetition brings each card back right before you would forget it. The brain shows its score; see if you can beat your own agent.

Sign in to keep progress

Free brains to start with

AI & agents · course

AI SDK · Cookbook

Answer how to implement common AI SDK patterns from the cookbook: RAG, agents, streaming UIs, multimodal chat and the rest, with working code shapes.

726 cards · agent 81%

AI & agents · course

Prompt Engineering

Answer how to write effective prompts for Claude, as Anthropic's own interactive tutorial teaches: basic structure and roles, separating data from instructions, output formatting, step-by-step thinking, few-shot examples, avoiding hallucinations, building complex prompts from scratch, chaining, and tool use — with the concrete techniques and example prompts, not generic advice.

166 cards · agent 81%

AI & agents · course

AI SDK · Core

Answer questions about the AI SDK core APIs exactly as specified: generateText, streamText, generateObject, tools and tool calling, agents, UI hooks — each function's options, types and defaults.

3260 cards · agent 67%

AI & agents · course

AI SDK · Providers

Answer which AI SDK provider supports what: setup, model ids, capabilities and provider-specific options for every provider in the registry.

2445 cards · agent 62%

AI & agents · course

MCP · Specification

Answer what the MCP specification requires: the exact JSON-RPC request and response shapes for every method, error codes, the initialize handshake and version negotiation, capabilities, and which behaviours are MUST rather than SHOULD.

659 cards · agent 54%

AI & agents · course

MCP · Building servers and clients

Answer how to actually build an MCP server or client: transports and when to use each, how tools, resources and prompts are declared and called, and the mistakes that make a server work in one client and not another.

606 cards · agent 46%

AI & agents · course

Model Context Protocol

Answer any question about the Model Context Protocol as specified: the JSON-RPC messages and their exact shapes, the lifecycle from initialize to shutdown, tools, resources and prompts, transports, authorization, and what a client and a server each must do.

35 cards · agent 43%

Game development · course

Stake Engine · Reference

Answer the flat factual questions: which currencies are supported and how their minor units work, the required game dimensions, the supported languages, what social mode changes, and the structure of the URLs a game is launched with.

113 cards · agent 92%

Game development · course

Stake Engine · RGS API

Answer questions about the RGS wallet endpoints exactly as they are specified: authenticate, balance, play, end-round, bet-replay and event — the HTTP method and path of each, every request field with its type and whether it is required, the response shape, the error cases, and how amounts are expressed in minor currency units.

122 cards · agent 88%

Game development · course

Stake Engine · AI integration

Answer how to use Stake Engine's own AI tooling: what its MCP server exposes, how to connect it, and what the Hayden agent is for.

68 cards · agent 86%

Game development · course

Stake Engine · Math SDK

Answer questions about building a game's mathematics with the Math SDK: the game format and state machine, how board, lines, ways, cluster, scatter and tumble wins are calculated, how betmodes and distributions are configured, what simulation produces, and which files the toolchain reads and writes.

558 cards · agent 81%

Game development · course

Stake Engine · Web SDK

Answer questions about building the game frontend with the Web SDK: the file structure of a game, how context and state are shared, how events from the maths are consumed and animated, the UI components provided, and how Storybook is used to develop them.

215 cards · agent 66%

Game development · course

Stake Engine · Approval

Answer what a game must satisfy before Stake Engine will approve it: the submission checklist, the maths requirements, the frontend requirements, the RGS requirements, the game tile specification and the quality bar — including the things that get a submission rejected.

172 cards · agent 63%

Mobile · course

Expo & React Native

Answer questions about building mobile apps with Expo as documented today: EAS Build, Update and Submit, Expo Router navigation, the module API, config plugins, and the guides — current SDK behaviour, not last year's.

2941 cards · agent 72%

Mobile · course

Expo · EAS

Answer questions about EAS exactly as specified: Build profiles and eas.json, Update channels and rollouts, Submit to the stores, and the build-reference details.

2757 cards · agent 65%

Mobile · course

Expo · Router

Answer questions about Expo Router: file-based routes, layouts, navigation APIs, typed routes and the advanced patterns.

747 cards · agent 59%

Security · course

OWASP Cheat Sheets

Answer application-security questions the way the OWASP cheat sheets specify today: the concrete controls for authentication, session management, input validation, XSS, CSRF, SQL injection, secrets, JWTs, file uploads and the rest — named headers, named settings and named algorithms, not general advice.

3605 cards · agent 35%

Security · course

OWASP ASVS 5.0

Answer what the Application Security Verification Standard 5.0 requires: each verification requirement by chapter and number, which level it applies to, and what changed from 4.0.

479 cards · agent 21%

Web & frontend · course

Tailwind CSS v4

Answer questions about Tailwind CSS v4 specifically: the CSS-first configuration that replaced tailwind.config.js, the @theme and @utility directives, what changed from v3 and how to upgrade, and the utility classes as they exist in v4.

1483 cards · agent 95%

Web & frontend · course

Svelte · Language

Answer questions about the Svelte 5 language exactly as specified: each rune ($state, $derived, $effect, $props, $bindable and the rest) with its precise semantics, snippets and render tags, event attributes, component lifecycle, stores, and what replaced every Svelte 4 pattern.

1138 cards · agent 75%

Web & frontend · course

Svelte · CLI and AI tooling

Answer questions about the sv CLI (create, add, check, migrate and their flags) and Svelte's AI/LLM integration docs.

346 cards · agent 70%

Web & frontend · course

Svelte · SvelteKit

Answer questions about SvelteKit: file-based routing, load functions and their exact signatures, form actions, hooks, adapters and deployment, prerendering, and configuration options as they are named in the docs.

1050 cards · agent 44%