Assessments

Smart tools for authoring assessments.

A collection of Graffiticode-powered smart tools for creating, rendering, and deploying interactive assessments. Built for assessment authors, education content publishers, and the AI agents that work alongside them.

What it is

Assessments is an Artcompiler toolset under the Education domain. Every smart tool in the Assessments toolset is one Graffiticode language wrapped by a specialized AI, exposed to agents through MCP, and rendered through an embeddable runtime. The toolset's strongest proof point is integration with Learnosity at scale.

How it works

Domain language — every smart tool in Assessments is built around a domain-specific language designed for assessment authoring.
Specialized AI — each tool ships with an AI trained on its language; agents describe assessments in natural language and the AI generates valid code.
Embeddable runtime — assessments render through a shared embeddable runtime, so they can be dropped into any host application.

Assessments Are More Than Single Question Types

A modern assessment item is rarely one question. It combines interactions — a spreadsheet next to a diagram, a data table with a free response — each with its own platform constraints. Authoring this by hand is where most tools break down.

Each smart tool in the Assessments toolset translates author intent into high-fidelity assessment items using an auditable domain language. Composition, transparency, and validation are built in.

Why Assessments

AI-native. Generate complex items with an agent instead of clicking through an authoring UI.
Structured. Assessments are code — composable, reviewable, version-controlled.
Embeddable. One definition renders through a shared embeddable runtime, deployable on Learnosity today and other platforms tomorrow.
Safe. Every output is validated and platform-compliant before it ships.

For AI Agents

The Assessments toolset's smart tools are available via the Graffiticode MCP server at mcp.graffiticode.org/mcp. No account is required to try them — a trial credential is published in the discovery artifacts.

MCP endpoint: https://mcp.graffiticode.org/mcp
Languages: L0152, L0153, L0154, L0157, L0158, L0159, L0166, L0169
Discovery: /llms.txt (human-readable), /.well-known/mcp.json (machine-readable) — both include the live trial token.

Call create_item with a language ID and a natural-language description; describe what you want, do not attempt to generate Graffiticode code directly. After each call, open or share the returned preview URL so the user can see the rendered item. Deeper integration walkthroughs live at /authoring/claude-code, /authoring/chatgpt, and /authoring/cowork.

Talk With Us

We're talking with assessment authors and product teams about how AI is changing their workflow — what works, what breaks, and what's still missing. If you're navigating the same questions, we'd like to hear yours, and we're happy to share what we're hearing across the field.

Email jeff@artcompiler.com for a 20-minute conversation. No pitch. We'll share notes either way.

Learn more about Artcompiler — the company building this toolset — and Graffiticode — the open-source platform that powers it.