Works with any MCP-compatible AI tool

A learning science team,
inside your AI.

Design training that sticks, audit and improve existing courses, and back every decision with cited research. Learning Brain plugs into any AI tool and equips it with a world-class learning design team.

Built on learning science, not vibes
32
Specialist tools
360+
Cited studies
5
Expert personas
2min
To connect
claude · with learning-brain · mcp
connected
you
Audit our onboarding course for cognitive load. Rewrite the weakest module and plan retention.
claude
Routing through Learning Brain. I'll audit each module, rewrite the worst one, and schedule retrieval practice.
→ doctor_audit_module()
scanning 8 modules · 412 slides · 00:00:03
✓ 3 modules exceed working-memory threshold (Sweller, 1988)
✓ Module 04 "Compliance Basics" · load score 8.2 / 10
→ arch_design_module(rewrite=true)
rewriting module 04 · applying spaced retrieval
✓ split into 4 chunks · 6 retrieval prompts added
✓ citations: Roediger & Karpicke (2006), Dunlosky et al. (2013)
→ arch_build_retrieval_schedule()
modeling 30-day forgetting curve
✓ expected recall at day 30: 34% → 71%
✓ spacing plan: T+1d, T+4d, T+11d (Cepeda, 2008)
Load score dropped 8.2 → 4.1. Module 04 is ready for review and a 3-session spacing plan is scheduled. Want me to regenerate the assessment too?
Yes, and run a transfer probe
§ 01 THE PROBLEM

AI-built training looks fine. But it usually doesn't work.

Ask ChatGPT or Claude to design a course, and you'll get tidy objectives, stock activities, a "knowledge check" at the end. It'll look polished and professional, but if you dig deeper you'll find it falls apart under scrutiny and doesn't pass the "would this work in the real world?" filter.

You can tell your AI to use learning science, and feed it research. But then it'll over-focus on what you've given it, and ignore other things that are just as important. You'll get the same shallow design with better vocabulary. It doesn't know what good looks like. That's the gap Learning Brain closes.

§ 02 THE TEAM

Five specialists. Always on call.

Your AI picks the right role automatically — or you can call one by name.

Connect Learning Brain to the AI you already use: Claude, Codex, ChatGPT, or any MCP-compatible tool. It'll take two minutes.

From then on, every prompt runs through a team of five learning-science specialists. Your workflow doesn't change, but what comes back is sharper: designs grounded in research, pushback when something won't work, and a citation for every decision.

↓ Click each expert to see them in action
01
Learning Scientist
the evidence checker
ls_*
4 tools

Evaluates whether a learning-science claim is supported by research, and how strongly. Explains the evidence, not just the conclusion. Diagnoses why a running course isn't producing results. Settles design arguments like explicit instruction versus discovery learning for a specific audience.

"You claim spaced practice improves retention. The evidence agrees — Cepeda et al.'s meta-analysis shows strong support. But your design spaces retrieval at 24-hour intervals for a 6-week course. The research suggests expanding intervals: 1 day, 3 days, 7 days, 14 days. Here's why that matters for your specific audience…"
Evidence evaluationPrinciple explanationSymptom diagnosisTension resolution
02
Curriculum Architect
the structural engineer
arch_*
6 tools

Designs full course architectures with cognitive load budgets and retrieval schedules. Builds modules against Merrill's five principles. Sequences content so concepts build on each other instead of piling up. Designs adaptive learning paths that route learners based on demonstrated capability.

"This course has five modules but no prerequisite logic. Module 4 assumes skills from Module 2 that aren't assessed. Your novice learners will hit a wall at Module 4 and blame themselves. Here's the dependency map and where to add mastery gates…"
Course architectureModule designContent sequencingAssessment blueprintsRetrieval schedulesAdaptive paths
03
Instructional Writer
the precision craftsperson
write_*
8 tools

Writes learning objectives you can assess. Builds MCQ items where every distractor targets a specific misconception. Creates worked examples with fading sequences. Writes feedback that corrects the thinking, not the answer.

"'Understand the principles of risk management' isn't an objective — it's a wish. Try: 'Given a project scenario, identify at least three risks, classify each by category, and assign probability ratings using a 5×5 matrix.' Now you can design assessment, practice, and content that actually serves it."
ObjectivesMCQsQuestion banksWorked examplesExplanationsFeedback copyDiagnosticsLearner rationale
04
Delivery Coach
the session architect
coach_*
4 tools

Designs live workshop run sheets with real facilitation moves. Specific questioning sequences, not "discuss in groups." Timed segments. Recovery moves for when the discussion dies. Scripts facilitator guides matched to the facilitator's experience. Diagnoses why a specific learner is stuck.

"Your 90-minute workshop has a 20-minute lecture opening. You've already lost the room. Sousa's prime-time research shows the first 10 minutes are your highest-attention window — use them for the hardest cognitive work, not housekeeping. Here's a restructured run sheet…"
Live session designDiscussion structuresFacilitator guidesStuck-learner diagnosis
05
Course Doctor
the quality auditor
doctor_*
5 tools

Reviews modules against 12 structural criteria. Audits objectives and MCQs for construct validity. Scans for the ten instructional illusions. Predicts whether a design will transfer to the workplace, and recommends specific bridging moves if it won't.

"This module has a 92% completion rate and strong satisfaction scores. But the assessment is all recall-level MCQs for an apply-level objective. Learners are recognising the right words, not demonstrating the skill. That's instructional illusion #9 — the performance illusion. Here's what to fix…"
Module auditObjectives auditMCQ auditIllusion scanTransfer prediction

Plus five cross-cutting tools for eliciting learner context, structuring course briefs, pushing back on badly-framed requests, showing relevant case studies, and tracing citation trails.

§ 03 THE PROOF

Same prompt. Four AI models. One clear difference.

I asked four AI models to design a self-paced course on workplace sustainability, giving each the same brief.

Without Learning Brain

Claude Opus (the most powerful model) produced a beautiful interactive HTML course in one go. It looked great, but there was no retrieval practice, no assessment, and no transfer design. Claude Haiku (least powerful model) produced a generic outline with vague objectives. Competent templates that teach nothing.

With Learning Brain

Every model now included cumulative retrieval practice, cognitive load budgets, worked-examples, transfer plans, post-training retrieval schedules. Amazingly, the smallest, cheapest model produced the most comprehensive output, including success metrics, implementation plans, and manager talking points. This shows that often, providing the AI with the right information is more important than the raw reasoning power of the AI itself.

A
Objectives — without vs. with
+

Without

"Understand the principles of project risk management and its importance in modern project delivery"

With

"Given a project scenario, identify at least five risks, classify each by category, and assign probability and impact ratings using a 5×5 matrix"

B
Module audit — without vs. with
+

Without

"The module is generally well-structured with room for improvement. Consider adding more interactive elements to increase engagement."

With

"C5 FAIL: No demonstration phase — the module tells learners about the skill but never shows it performed. C11 FAIL: Assessment is recall-level MCQs for an apply-level objective. C12 FAIL: Confirmed illusion I9 (performance illusion). Three specific fixes provided with evidence citations."

C
Course architecture — without vs. with
+

Without

5-module outline: Introduction → Core Concepts → Application → Advanced Topics → Wrap-up. Each module has "lecture + discussion + quiz." No retrieval schedule, no prerequisite mapping, no cognitive load budget.

With

4-module architecture with prerequisite dependency map, expanding retrieval schedule (1/3/7/14 day intervals), cognitive load budget, worked-example fading arc, honest transfer scoping, and companion materials (manager briefing, delayed micro-quiz, job aid).

From users, in their own work

It's honestly more impressive than I thought it would be — and that's having read every word of the webpage.
Ollie Wood
L&D practitioner
first use
This will save me an insane amount of work on my next design QA project. In my role I would absolutely pay money for this.
Nick Robinson
Learn & Lead
design QA
Start using it →
§ 04 IN USE

How you could use it

01

Brief to build-ready pack in one sessionObjectives, architecture, retrieval schedule, assessment blueprint — in one flow.

"Design a 4-module async course on data privacy for new hires with no prior compliance background"
02

Catch structural problems before productionAudit a module and get specific, evidence-cited fixes.

"Audit this module against your structural criteria: [paste content]"
03

Make junior designers saferConsistent quality standards that don't depend on who built it.

"Write assessable learning objectives for a course on giving effective feedback"
04

Defend design decisions to stakeholdersCited research findings instead of "best practice."

"My VP wants to cut the retrieval practice to save time. What does the evidence say?"
05

Convert formats without losing the designLive workshop to self-paced, or vice versa.

"Redesign this 2-day workshop as a 6-week blended programme for 200 people"
06

Review assessments for construct validityQuiz items, question banks, diagnostics that actually measure capability.

"Audit these 10 MCQs — are they actually testing the stated objective?"
07

Build reinforcement that sticksSpaced retrieval plans, manager talking points, implementation intentions.

"Build a 4-week post-training retrieval schedule for a new-manager programme"
08

Turn an SME deck into real learningStructured experience with objectives, practice, and assessment.

"Here's a 40-slide deck on cloud security. Design a course around it for mid-level engineers"
§ 05 AUDIENCE

Who it's for

01

L&D teams and instructional designers

Your team produces dozens of courses a year. You can't personally review every one at learning-science depth. Learning Brain gives you a consistent quality standard across the team. The output stops depending on which designer built it, how experienced they are, or how much time they had. Junior designers produce structurally sound work. Senior designers move faster with evidence at hand. Every design decision has a citation trail you can show anyone who asks.

When a VP asks "why is the course structured this way?" you need more than "best practice." You need a specific research finding. Learning Brain gives you the evidence trail. And if your design has a structural problem, it tells you before the VP does.

02

Learning consultants and agencies

You're selling expertise, not just production. Learning Brain lets you quality-check deliverables at scale, back every recommendation with cited evidence, and catch instructional illusions before they reach the client. It's the difference between a polished deck and a defensible one.

03

Course creators and educators

Your audience trusts you because of what you know. Your course has to actually deliver it. Polished production and five-star reviews aren't the same thing as students getting real results, and the creators who build durable audiences are the ones whose students do. Learning Brain gives you what a dedicated learning designer would bring: objectives that force you to be specific about capability, assessments that tell you whether it's landing, and design that makes your expertise transfer outside the course.

04

Anyone building training with AI

The output looks good but feels hollow. Beautiful outlines, professional language, zero retrieval practice, no transfer design. You sense something's missing but you can't name it. Learning Brain names it, and fixes it. Every design decision comes with the research behind it. The result is better courses now, and better instincts over time.

§ 06 RIGOUR

Grounded in 360+ cited studies. Designed to push back, not please.

Every design decision is traceable to a specific research finding. The knowledge base covers nine domains of learning science, and every finding carries an evidence-strength rating — moderate evidence is never laundered as strong. When the research is silent on a topic, the tools say so rather than fall back to general AI knowledge.

AI models are trained to be agreeable. They soften criticism, pass work that should fail, and tell you what you want to hear. Learning Brain pushes back on that in three ways.

01

Evidence only, never invention.

Every citation comes from the knowledge base. No fabricated references. Popular myths (learning styles, left/right brain, the 10,000-hour rule, the Cone of Learning) get flagged the moment they appear.

02

Some requests are refused.

Promises that training will transfer to wildly different situations. "Everyone at the company" as an audience. A 90-minute module covering 35 topics. A cramming schedule. An auto-graded quiz for a skill only a human can judge. Try asking for something like this, and Learning Brain explains why it won't build it.

03

Every output is self-reviewed.

Nineteen of the 32 tools produce a draft, score it against their own rubric, rewrite what falls short, and only then hand it back. Vague objectives get rewritten before you see them. Missing demonstration phases get named. Polished-but-empty courses get caught as engagement illusions.

Tested against its own failure modes

I fed the tool fifty inputs designed to fool it: modules that look polished but have no demonstration phase, objectives that sound active but promise nothing, MCQs where the longest answer is always correct, engagement-first workshop briefs. Every flaw was caught, and every fix was specific and actionable. New patterns that slip through get added to the refusal list.

The evidence base was built by a practitioner with twenty-plus years of work across educational publishing, corporate L&D, and edtech. Every tool exists because it solved a real design problem, and every rubric exists because a specific failure mode kept showing up in practice. This is the difference between a research database and a working knowledge base.

§ 07 QUESTIONS

Common questions

01
Do I need to be technical to use this?

Mostly no. For Claude and ChatGPT chat you paste a URL into settings, create a Project, and upload a small skill file. No coding, no API keys. Takes about two minutes. Claude Code, Codex, Cursor, and Windsurf have their own setups (plugin install or MCP-only); the setup guide has one path per tool.

+
02
What is this, exactly?

Learning Brain is an evidence layer that plugs into Claude, ChatGPT, or any MCP-compatible AI tool. It gives your AI access to a curated knowledge base of learning science research and 14 quality rubrics. The output is design artifacts: objectives, course architectures, module audits, assessment items, facilitation guides. It doesn't produce finished slides, videos, or SCORM packages. It makes the design structurally sound, so production work doesn't get wasted.

+
03
Does it replace my AI, or work with it?

It works with the AI you already use. Learning Brain is an evidence layer. It feeds your AI curated research and quality rubrics. Your AI still produces the output. Learning Brain makes that output structurally sound.

No per-use cost, no API keys. Generation runs on your existing Claude, Codex, or ChatGPT subscription. Learning Brain supplies the expertise; your AI supplies the writing. Power users don't cost more than casual users, and there's no incentive to meter your usage.

+
04
Does it write the training for me?

It produces design artifacts: objectives, course architectures, module structures, assessment items, facilitation guides, audit reports. It doesn't produce finished slides, videos, or SCORM packages. Think of it as the architect, not the builder. Your production team still builds the thing.

+
05
What AI tools does it work with?

Any tool that supports the Model Context Protocol (MCP): Claude (desktop and Code), Codex, ChatGPT, Cursor, Windsurf, and others.

Claude gives the best experience. It picks the right tool for the job, chains tools together, follows the inlined rubrics, and cites sources by name.

Codex (any paid ChatGPT account) is the recommended path for ChatGPT-account users. It delivers about 80% of the Claude experience: chains tools, picks the right audit and design tools on its own, engages with the underlying research.

ChatGPT chat works but is lighter. It tends to call one tool then summarise rather than chaining. Best for one-shot questions. For full audit and design workflows I recommend Claude or Codex.

+
06
What if my work blocks custom MCP connectors?

This is common in enterprise orgs. Three paths usually still work even when chat-app connectors are blocked:

1. Claude Code / Cowork — terminal CLI or the Code tab inside Claude Desktop. Separate policy surface from Claude chat, and plugin install is usually allowed. See the Claude Code setup.

2. Codex — if you have a paid ChatGPT account. Separate OpenAI app with its own settings, so it's often a separate policy surface from ChatGPT itself. The plugin installer handles everything. See the Codex setup.

3. Claude Desktop via local config — edits a local file on your Mac and bypasses the "Custom connectors" setting entirely. See the restricted-org fallback at the bottom of the setup guide.

If none of those work, email me — I'd like to hear about it.

+
07
Will it work for my specific domain?

The research covers how people learn — not what they learn. The principles of cognitive load, retrieval practice, transfer design, and assessment alignment apply whether you're designing compliance training, technical certification, leadership development, or onboarding. The tools adapt to your audience and context.

+
08
What if it pushes back on something I know works?

Good! That's a conversation worth having. The pushback is always grounded in a specific research finding, which you can evaluate against your contextual knowledge. Sometimes the research finding wins. Sometimes your practitioner judgment wins. Either way, the decision is now explicit rather than assumed.

+
09
Will it replace my design judgment?

No. The tools handle the science: objectives, sequencing, assessment alignment, transfer design, cognitive load. Your people handle the context: reading rooms, navigating politics, knowing which research finding matters most for this specific audience at this specific company. No tool can guarantee learning outcomes. It can guarantee the design is structurally sound. What happens in delivery is still up to humans.

+
10
Why is it free?

I built Learning Brain because I wanted it to exist, and I wanted to use it myself. It worked well enough that I turned it into a tool. The “thinking” is done by your AI, so it costs almost nothing to run — that’s how it can stay free.

+
11
How is this different from an AI-powered LMS?

Platforms like 360Learning, Docebo, and Absorb are full-stack systems for delivering and managing training. Learning Brain is a different category – it's an evidence layer that sits upstream, plugging into the AI you already use to ensure the design quality of what you create before it reaches any LMS.

+
12
How is this different from just asking ChatGPT about learning science?

When you ask ChatGPT a learning-science question, it draws on general training — which includes outdated findings, debunked myths (like learning styles), and confident claims without evidence ratings. Learning Brain draws on a curated, evidence-rated knowledge base with validated quality rubrics. It also refuses to fall back on general knowledge when its evidence base is silent.

+
§ 08 GET ACCESS

Start using Learning Brain.

Enter your email and you'll get access immediately. Connect to your AI tool and start designing in two minutes.

Sign up for access
Instant access. Two minutes to set up.
Taking you to your setup guide…

Claude Desktop · Settings
01 Add the MCP connector
SettingsCustomizeConnectorsAdd custom connector
🔗 https://learningbrain.ai/mcp
02 Install the workflow Skill
SettingsCustomizeSkillsUpload a skill
📄 learningbrain-skill.md
ready — your AI now has the learning science team