The system separates concerns into three distinct layers, ensuring the curriculum logic is completely independent from any specific AI runtime.
Runner-Agnostic Definitions
All agent roles, the state graph, pedagogical knowledge layers, checkpoint definitions, and output schemas. Pure data — no code. Any AI framework can consume these definitions.
Adapter Layer
Translates the Brain's abstract definitions into runner-specific configurations. Swap the LLM provider or execution framework without touching the curriculum logic.
Execution Runtime
The runtime that drives the pipeline: loading agent manifests, traversing the state graph, calling LLMs, routing checkpoints, and managing retries.
Every phase follows the same internal structure. Quality is checked locally at each phase — catching a bad unit plan in Phase 2 is far cheaper than catching it after 20 lessons have been generated from it.
Decides which workers to activate, routes data to them
Produce the actual content — each with a single focused role
Validates output against the upstream spec — triggers targeted retries on failure
Above the per-phase agents sit two session-persistent agents: the Lead Orchestrator (manages phase transitions) and the Lead Evaluator (checks cross-phase coherence).
37 agents organized into five categories — each with a single job, a single set of context, and the ability to be retried independently.
Generate domain-specific content: instructions, assessments, resources, visuals, assembly, QA.
Manage phase execution, transitions, and coordinate which specialists activate.
Validate output quality against upstream specs at every phase boundary.
Decompose higher-level specs into lower-level specs (units → modules).
The Pedagogical Advisor — generates session documents and guards teaching standards.
Dispatched by parent orchestrators for specialized tasks: video curation, diagram generation, stock photos.
The pipeline has 9 checkpoints classified into three types. Quality checkpoints use the upstream evaluator's confidence score to decide whether to auto-approve or pause for teacher input.
Always pauses — gathers data the system doesn't have (scope, audience, pedagogy).
Auto-approves when confidence meets the trust threshold. Pauses with targeted questions when low.
Always pauses — non-negotiable professional sign-off before delivery.
Even in Autonomous mode, genuinely bad output still triggers a teacher interrupt. The dial adjusts sensitivity — it never removes the safety net.
The pipeline isn't a rigid sequence — it's a state graph with bounded feedback loops that allow targeted correction without cascade regeneration.
If the final QA agent finds issues, the system clears downstream state and re-runs assembly with structured feedback — up to 2 retries.
Teachers can reject at any checkpoint. The target agent re-executes with detailed feedback about why it was sent back.
Phase evaluators can trigger targeted retries — "re-run the rubric agent," not "re-run the entire phase."
Not every lesson needs every agent. The pipeline adapts automatically based on the pedagogical approach declared in the Course Outline.
Instructions, Rubric, Critique Protocol, Visual Diagrams
Instructions, Rubric, Worked Examples, AI Prompts
Same pipeline. Different agent subsets. Static graph, dynamic execution.
The seven rules that govern every architectural decision in the pipeline.
Each spec defines boundaries and goals. Agents have creative freedom within those boundaries.
Catching a bad unit plan in Phase 2 is cheaper than catching it in Phase 4 after 20 lessons.
The topology never changes. What changes is which agents run, which checkpoints pause, and what questions are asked.
Trust mode lets teachers choose their involvement. Checkpoints interrupt by exception, not obligation.
Each agent has one job, one handler, one set of context. Specialization enables targeted retry.
Leaf edits are free. Spec edits trigger targeted re-evaluation, not cascade regeneration.
Non-negotiables enforce baseline pedagogical standards. But the teacher always has the final say.
If you're evaluating AI curriculum platforms for your school or district, we'd love to give you a deep-dive walkthrough.
Open dashboard