Compound Intellect: Activity-Level AI Boundary Planning for Curricula

LinkTool

Compound Intellect is a planning tool designed to help educational departments decide where AI belongs in a course and where it must be excluded. It analyses departmental syllabi against the institution's actual AI policies at the individual activity level.

Key points

  1. Activity-level separation: Decisions are made per individual activity rather than broad course units, categorising tasks into teaching with AI, teacher preparation only, or strictly AI-free.
  2. Three non-negotiable checkpoints: Teachers must verify extracted curriculum data, decide on activity inclusions or exclusions, and explicitly approve an immutable term plan.
  3. Traceable boundaries: Every AI exclusion directly attributes the governing authority that mandated it, such as school policy or curriculum requirements.
  4. Data privacy guarantees: Uploaded documents are not used for model training, admin consoles cannot monitor teacher behaviour, and full data deletion with certificates is supported.
  5. Explicit non-features: The platform deliberately rejects AI text detection, automated grading, teacher surveillance metrics, and integrations with LMS or SIS platforms.

Why it matters

While many educational institutions formulate AI guidelines, translating high-level policy into weekly classroom routines remains difficult. Defining exact boundaries per task ensures curriculum integrity while keeping teachers in full control of pedagogical and assessment judgements.

Analysis

Compound Intellect establishes a clear boundary against common EdTech practices such as automated grading, surveillance dashboards, and flawed AI-detection scoring. By completely omitting LMS and SIS integrations, the platform avoids storing sensitive student records. From a technical and privacy perspective, it isolates school intellectual property by leveraging commercial API agreements that prohibit training, performing pre-storage inspection, and offering verified data destruction workflows.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Link:edwarddonner.com

    The Complete AI Curriculum

    Das vorliegende Curriculum bietet einen strukturierten Lernpfad für den Erwerb von Kompetenzen im Bereich der Künstlichen Intelligenz. Es richtet sich an Lernende, die ihre Expertise durch gezielte technologische Inhalte und praxisorientierte Module ausbauen möchten.

    AI & LLMs

  • Repository:miskaone/learn-powerplatform-fyi

    Mastery Gate: Deterministic Control of AI Agents via WebMCP

    Mastery Gate is an experimental PL-400 learning platform demonstrating how websites can deterministically govern AI agents via the WebMCP protocol. Instead of relying on prompt instructions, a TypeScript engine dynamically manages tool availability and structurally protects answer keys.

    TypeScript

    AI & LLMs· Demo

  • Repository:EveryInc/compound-engineering-plugin

    Compound Engineering: 33-Skill Plugin for AI Coding Agents

    Compound Engineering is an open-source plugin for AI coding agents designed to structure development workflows and systematically preserve learned context. It runs on 14 platforms, including Claude Code, Cursor, and Codex.

    24.9kstarsTypeScript

    AI & LLMs· Tool

  • Link:Max Junestrand

    Legora aOS: Agentic Operating System for Legal Workflows

    Legora has unveiled Legora aOS, an agentic operating system designed for law firms and in-house legal teams. The platform automates complex legal workflows from research to document delivery through autonomous AI agents.

    AI & LLMs· Tool

  • Link:cardea-two.vercel.app

    Cardea: An Interactive Canvas for AI Agents with Live Browsing and Approval Gates

    Cardea is a goal-oriented web workspace where AI agents research, plan, and prepare actions in parallel using live browsers. Users can monitor operations in real time, adjust decisions, and retain full approval over sensitive steps such as sending messages or spending money.

    AI & LLMs· Tool

  • Link:Tawkit, Inc.

    OpenBot: Self-Hosted Enterprise Agent Platform Built on the AG-UI Protocol

    CopilotKit (Tawkit, Inc.) has introduced OpenBot, an open-source platform for enterprise AI agents designed to run entirely within an organisation's own infrastructure. It integrates internal company data, supports computer use, and leverages the AG-UI standard.

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.