Works with any AI agent

Build courses with AI agents.
Launch in minutes.

Define a course as YAML. Import it via CLI or MCP. Get a live product with a landing page, knowledge graph, spaced repetition, and billing.

npx @graspful/cli initGet Started Free

Works with your tools

Any agent that supports MCP or can read llms.txt can build Graspful courses.

Claude Code

Full MCP support via claude_desktop_config.json

Cursor

MCP integration in Composer

OpenAI Codex

CLI tool use with MCP

ChatGPT

Browse llms.txt for context

Gemini

Browse llms.txt for context

Windsurf

MCP integration in Cascade

VS Code Copilot

MCP support in agent mode

Two YAMLs. One product.

A course YAML defines the learning content. A brand YAML configures the product. Import both, and you have a live business.

1. Course YAML

Define your knowledge graph — sections, concepts, prerequisites, knowledge points, and practice problems.

aws-saa-c03.yaml

2. Brand YAML

Configure the landing page, pricing, theme preset, and SEO. This becomes a standalone product site.

aws-prep-brand.yaml

3. Import & Launch

One command imports both YAMLs and publishes a live product with billing, adaptive learning, and spaced repetition.

MCP Tools

Every CLI command is exposed as an MCP tool. Your agent calls them directly — no shell needed.

create_course

Scaffold a course skeleton from a topic and source document

fill_concept

Generate knowledge points and problems for a single concept

review_course

Run 10 quality checks — duplicates, difficulty staircase, worked examples

validate_course

Quick schema validation against the course YAML spec

import_course

Import a course YAML to the platform, optionally publishing immediately

create_brand

Generate a brand YAML with landing page, theme, pricing, and SEO

How agents build courses

Start from a source document

Feed the agent an exam guide, textbook, or documentation. It scaffolds the knowledge graph — sections, concepts, and prerequisite edges.

Fill concepts incrementally

The agent fills one concept at a time — generating knowledge points with progressive difficulty and at least 3 practice problems each.

Review catches quality issues

The review gate runs 10 checks: duplicate questions, difficulty staircase violations, missing worked examples, and more. Fix issues before publishing.

Import and publish

Import the course YAML and brand YAML. The platform creates the landing page, sets up billing, and starts serving adaptive learning sessions.

What your courses are built on

You bring the content expertise. The platform brings the learning science. Every course you create automatically gets these research-backed systems.

Knowledge Graph

Every concept connected by prerequisites and encompassing edges. Students can't advance without mastering foundations.

Adaptive Diagnostics

20-60 questions map what a student already knows. No wasted time on material they've mastered.

Mastery-Based Progression

Bayesian Knowledge Tracing ensures students truly understand before moving forward.

Spaced Repetition

The FIRe algorithm schedules reviews at the optimal time. Students never forget what they've learned.

Intelligent Task Selection

Priority-based system chooses lessons, reviews, or remediation — whatever the student needs most right now.

XP and Gamification

Streaks, leaderboards, and XP calibrated to ~1 point per minute drive daily engagement.

How the learning engine works

Free to create. Revenue share when learners pay.

Build unlimited courses, run unlimited reviews, import as many times as you want. When you publish a paid course and learners subscribe, Graspful takes a 30% platform fee. You keep 70%.

70 / 30
You keep 70%. Graspful takes 30%.
$0
To create, review, and import courses.

Ship a course today.

Install the CLI, point your agent at a source document, and launch.

npx @graspful/cli initGet Started
DocumentationPricingMCP Setup
AI Agents | Graspful