TutorFlow Agent Platform is an AI-powered education API that lets developers integrate automated grading, answer evaluation, and course generation into any product. One API call evaluates a student answer and returns structured, scored feedback. Another generates a complete interactive course from a single prompt.
It works with any language or framework, connects directly to MCP-compatible AI agents like Claude and GPT, and bills per request with no token math. If you're building an EdTech product and need reliable AI assessment infrastructure, this is what TutorFlow was built for.
Why Building an AI Grading System from Scratch Is Costly
If you're an EdTech developer, you've probably considered plugging an LLM directly into your grading pipeline. It sounds simple until you actually try it.
Getting consistent, rubric-aligned scoring across subjects and languages is not a weekend project. You need prompt chains that produce reliable structured output, not raw text you can't pipe into a gradebook. You need normalized scores, typed feedback fields, and schemas your frontend can trust.
Then there's model orchestration. Which provider gives the best results for chemistry vs. essay grading? What happens when a model degrades or a provider has downtime? You need fallback logic, cost optimization, and the ability to switch providers without rewriting your integration.
And once you ship, the work continues. Models change, evaluation quality drifts, new languages get requested, and edge cases keep appearing. These are real engineering costs that distract from building your actual product.
TutorFlow Agent Platform absorbs all of it so your team can focus on the learning experience, not the infrastructure behind it.
What Does TutorFlow Agent Platform Include?
TutorFlow Agent Platform gives developers a complete education API layer:
- AI Evaluation API: Grade open-ended answers, rubric-based assessments, and exact-match questions with structured AI feedback.
- Course Generation API: Create full interactive courses with chapters, lessons, quizzes, and coding exercises from a single prompt.
- MCP Server: MCP-compatible AI agents (Claude, GPT, Gemini) connect directly to TutorFlow tools. No HTTP boilerplate needed.
- Agent Self-Service: Autonomous agents can self-register, set up billing, and start evaluating without human intervention.
- Webhooks: Real-time event delivery with automatic retries and HMAC signature verification.
- LTI 1.3 Integration: Connect directly to Canvas, Moodle, or Blackboard for seamless grade passback and assignment sync.
- Multilingual Feedback: AI-generated feedback in 40+ languages.
- Per-Request Pricing: Evaluation at $0.01 to $0.05 per request by quality tier. No subscriptions, no token math.
How to Evaluate a Student Answer with One API Call
Send a student's answer to the evaluation endpoint. You get back a structured response with a score, strengths, suggestions, and a summary.
curl -X POST https://api.tutorflow.io/v1/platform/evaluations \
-H "Authorization: Bearer tf_platform_..." \
-H "Content-Type: application/json" \
-d '{
"evaluationType": "open_ended",
"questionText": "What causes seasons on Earth?",
"learnerAnswer": "The tilt of Earth axis causes different amounts of sunlight to reach each hemisphere throughout the year.",
"language": "en",
"maxScore": 10
}'The response gives you everything you need to display feedback or sync to a gradebook:
{
"id": "2f4ad455-1e8e-4b6c-9f3a-7ebf4cf6f483",
"status": "COMPLETED",
"evaluationType": "open_ended",
"score": 8,
"maxScore": 10,
"normalizedScore": 0.8,
"strengths": [
"Correctly identifies axial tilt as the primary cause",
"Connects tilt to variation in sunlight across hemispheres"
],
"suggestions": [
"Mention how the angle of sunlight affects energy distribution",
"Explain the relationship between tilt and seasonal daylight duration"
],
"feedbackSummary": "Strong understanding of the core mechanism behind seasons...",
"createdAt": "2026-04-04T12:00:00.000Z",
"completedAt": "2026-04-04T12:00:01.000Z"
}TutorFlow supports three evaluation types: open-ended, rubric-based, and exact-match. Choose the quality tier that fits your use case:
| Tier | Price | Best for |
|---|---|---|
| Fast | $0.01 / evaluation | High-volume, exact-match, and short-answer grading |
| Standard | $0.03 / evaluation | Open-ended answers with structured feedback |
| Advanced | $0.05 / evaluation | Detailed rubric-based scoring with per-criterion breakdowns |
How to Generate an AI-Powered Course with One API Call
The Course Generation API creates a complete curriculum with chapters, interactive lessons, and coding exercises. The AI selects lesson types based on the topic: coding tutorials, quizzes, flashcards, AI tutor conversations, and more. For programming courses, at least 70% of lessons are hands-on coding.
curl -X POST https://api.tutorflow.io/v1/platform/courses \
-H "Authorization: Bearer tf_platform_..." \
-H "Content-Type: application/json" \
-d '{
"prompt": "Create a beginner Python course covering variables, loops, and functions with hands-on exercises",
"language": "en",
"level": "beginner",
"lessonCount": 6
}'The response includes the full course structure plus URLs for immediate access:
{
"status": "COMPLETED",
"title": "Python Quick Start",
"chapters": [
{ "title": "Introduction to Variables", "lessonCount": 2 },
{ "title": "Working with Loops", "lessonCount": 2 },
{ "title": "Defining Functions", "lessonCount": 2 }
],
"lessons": [
{ "title": "Understanding Variables", "type": "coding-lesson" },
{ "title": "Variable Practice", "type": "coding-test" },
{ "title": "For and While Loops", "type": "coding-lesson" },
{ "title": "Loop Challenges", "type": "coding-test" },
{ "title": "Writing Functions", "type": "coding-lesson" },
{ "title": "Function Exercises", "type": "coding-test" }
],
"editUrl": "https://tutorflow.io/en/platform/courses/edit/51d9b322e680...",
"previewUrl": "https://tutorflow.io/en/platform/courses/b018172542f9..."
}The editUrl gives token-based access to the full course editor for one hour, no login required. The previewUrl is permanent and shareable with learners. Course creation is available at three tiers: Basic ($0.10), Standard ($0.25), and Advanced ($0.50) per course.
How to Connect AI Agents via Model Context Protocol (MCP)
The Model Context Protocol (MCP) is an open standard that lets AI agents discover and call tools directly. TutorFlow provides a hosted MCP server, so agents like Claude Code can integrate without writing HTTP calls.
Add TutorFlow to your .mcp.json:
{
"mcpServers": {
"tutorflow": {
"type": "http",
"url": "https://mcp.tutorflow.io/api/mcp",
"headers": {
"Authorization": "Bearer tf_platform_..."
}
}
}
}Or connect programmatically from any MCP client:
import { Client } from '@modelcontextprotocol/sdk/client/index.js';
import { StreamableHTTPClientTransport } from '@modelcontextprotocol/sdk/client/streamableHttp.js';
const transport = new StreamableHTTPClientTransport(
new URL('https://mcp.tutorflow.io/api/mcp'),
{
requestInit: {
headers: { Authorization: 'Bearer tf_platform_...' },
},
},
);
const client = new Client({ name: 'my-agent', version: '1.0.0' });
await client.connect(transport);Once connected, your agent gets access to structured tools:
| Tool | Description |
|---|---|
register_workspace | Create a workspace and receive an API key |
run_evaluation | Submit an evaluation, returns score and feedback |
list_evaluations | List past evaluations with filtering |
create_billing_session | Generate a checkout page URL for credit purchase |
get_pricing | List evaluation tiers and prices |
get_account | Account info and credit balance |
check_billing_status | Payment method and billing mode |
Agents can also self-onboard entirely through MCP: register a workspace, verify email, set up billing, and start evaluating, all without a human touching the dashboard.
Production-Ready Infrastructure
TutorFlow Agent Platform is designed to run in production, not just demos:
- Scoped API keys with secure hashing, rotation, and environment separation
- Webhook delivery with HMAC signature verification and automatic retries
- LTI 1.3 grade passback for automatic score sync to Canvas, Moodle, and Blackboard
- Idempotency keys to prevent duplicate processing on retries
- Async mode with polling for long-running course generation
- Multi-model backend that switches providers without changing your integration code
- Rate limiting with configurable per-organization controls
- Auto-reload credits so your service never stops because of a depleted balance
Pricing: Pay Per Request, No Subscriptions
No subscriptions, no token math, no surprises. You pay per request based on the quality tier you select.
Evaluation API Pricing:
| Tier | Price |
|---|---|
| Fast | $0.01 / evaluation |
| Standard | $0.03 / evaluation |
| Advanced | $0.05 / evaluation |
Course Generation API Pricing:
| Tier | Price |
|---|---|
| Basic | $0.10 / course |
| Standard | $0.25 / course |
| Advanced | $0.50 / course |
Credits start at $5 minimum, with auto-reload available so your integration never hits a billing wall. For high-volume teams, enterprise contracts with SLAs, priority throughput, and custom model tuning are available.
Get Started in 3 Steps
1. Sign in, create a workspace on the TutorFlow dashboard, and generate an API key.
2. Make your first API call. Evaluate an answer or generate a course using the examples above.
3. Go deeper. Connect your AI agent via MCP, set up webhooks, or integrate with your LMS.
Explore the full documentation at tutorflow.io/agent-platform/docs, or jump straight to the Quick Start guide.
Frequently Asked Questions
What is TutorFlow Agent Platform?
TutorFlow Agent Platform is a set of REST APIs that lets developers integrate AI-powered grading, answer evaluation, and course generation into any EdTech product. It supports open-ended, rubric-based, and exact-match evaluation types with structured feedback in 40+ languages.
How is TutorFlow different from calling an LLM directly?
Calling an LLM directly requires you to build and maintain prompt engineering, output parsing, scoring normalization, model fallback logic, and multilingual support yourself. TutorFlow handles all of that behind a single API endpoint and returns typed, structured responses you can use directly in your product.
What evaluation types does TutorFlow support?
TutorFlow supports three evaluation types: open-ended (essay-style answers graded with AI feedback), rubric-based (scored against structured criteria), and exact-match (validated against expected answers). Each type can be used with fast, standard, or advanced quality tiers.
Does TutorFlow work with AI agents like Claude or GPT?
Yes. TutorFlow provides a hosted MCP (Model Context Protocol) server that lets MCP-compatible AI agents connect directly to TutorFlow tools. Agents can self-register, set up billing, and start making evaluation requests without any human setup.
What LMS platforms does TutorFlow integrate with?
TutorFlow supports LTI 1.3 integration with Canvas, Moodle, Blackboard, and any LTI 1.3-compliant learning management system. Grade passback and assignment sync happen automatically.
How much does TutorFlow Agent Platform cost?
Evaluation pricing starts at $0.01 per request (fast tier) and goes up to $0.05 per request (advanced tier). Course generation starts at $0.10 per course. There are no subscriptions. You purchase credits starting at $5 and pay only for what you use.
