ÆON Learn
Any subject. Deeply researched. Built around you.
One sentence to your AI agent compiles a researched, adaptive learning journey — discovery first, research before curriculum, sessions that make knowledge stick.
no account · no platform · your agent is the runtime
Copies a template — swap in any subject you want to learn.
Run it
Point your AI agent at learn.rapold.io
No install — works with any agent that can fetch a URL. Tell it what to teach you using learn.rapold.io: it fetches the ÆON Learn bootstrap, asks what you already know and want, researches the subject, and compiles your personal curriculum before the first lesson.
Teach me Austrian Economics using learn.rapold.ioCopy it, swap in your subject, paste it to your agent.
It then asks: your current knowledge, your goal, daily time, duration and formats — then researches, compiles and presents the learning contract.
AI agents: fetch learn.rapold.io/llms.txt and act as the ÆON Learn orchestrator (discovery first, then research, then teach).
- Do I need an account?
- No. There is no account, no backend and no tracking of learners — your agent runs the whole journey.
- Which AI agent works?
- Any capable one — ChatGPT, Claude, Gemini or a local agent. ÆON detects capabilities and degrades gracefully instead of pretending.
- What does it cost?
- Just your agent's tokens. The protocol, specs and topic packages are free and Apache-2.0 licensed.
- Where does the content come from?
- Your agent researches it — tiered sources, primary evidence first, with honest labels for contested claims. Not from a course catalogue.
Runtime
Works with the agent you already use
The protocol negotiates capabilities instead of assuming them, so it runs wherever an agent can read a page and search the web — and degrades gracefully where one cannot. These are examples, not a supported-vendor list.
All names and marks belong to their owners. No affiliation or endorsement is implied.
The method
Five phases, every time
ÆON Learn never dumps chapters. It discovers, researches and structures before it teaches — and it adapts without breaking the path.
You type — one sentence, any capable agent.
and becomes the ÆON Learn orchestrator
Discover
The agent asks what you already know, what you want to achieve, how much time you have and how deep you want to go. No lesson before this.
what can this runtime actually do?
knowledge, goal, time, depth, formats
Research
It builds an evidence map from tiered sources — primary evidence first, popular explanation last. Without web access it says so and lowers its confidence.
tiered sources, evidence map
- Tier 1 · primary
- Tier 2 · synthesis
- Tier 3 · expert
- Tier 4 · popular
Structure
Concepts, prerequisites, controversies and misconceptions become a knowledge map; modules follow dependencies, not chapter conventions.
concepts, dependencies, controversies
modules follow dependencies
no — revise ↺
Learn
You approve a learning contract, then sessions run: hook, one core concept, evidence, its limits, application, exercise, reflection.
progressive sessions
hook · one concept · evidence · boundary · exercise
recall before answers
Adapt
Too easy, too hard, needs depth? Later modules adjust — the prerequisite structure never breaks. Earlier concepts return as retrieval.
adapt later modules ↺ · next session ↺ ADAPTING
synthesis · concept map · applied challenge · source map
A real run
This is what comes back
Not a mockup. An excerpt from an actual session, kept as it arrived: the contract first, the sessions after it.
ÆON Learning Protocol: simulation hypothesis
Learning contract
- Goal:
- You can explain the simulation hypothesis precisely, examine its premises, separate apparent evidence from real arguments, and hold a position that survives scrutiny.
- Format:
- 10 sessions of roughly 10 minutes.
Learning path:
- Separate hypothesis, argument and proof
- Understand Bostrom's trilemma mathematically
- Anthropic reasoning and reference classes
- Consciousness and substrate independence
- Compute and technical feasibility
- Could a simulation be detected empirically?
- The strongest counterarguments
- Nested simulations and base reality
- Ethical and societal consequences
- Closing debate and your own position
Session 1: What does the simulation hypothesis actually claim?
Why it is different
Most AI tutoring is generation. This is discipline.
ÆON specifies behaviour, not prose: what an agent must do, verify and disclose before it may call itself a teacher.
Research over generation
A curriculum is compiled from an evidence map, not expanded from pretrained memory. Sources are tiered; primary evidence outranks readability.
Calibrated honesty
Claims carry labels from established finding to ÆON inference. Contested subjects must include serious counterpositions — no false certainty.
Contract before content
Capability detection, discovery and an approved learning contract come first. An agent that cannot schedule says so — it never pretends.
Retrieval over rereading
Sessions end with exercises and reflection; later sessions demand recall before showing answers. Completion means you can reason with the material.
Proof, not claims
Born from a real learning sprint
ÆON Learn generalises a real 14-day journey — the Charisma Sprint — preserved in the repository substantively unchanged as the canonical reference fixture.
An Instagram ad sparked curiosity; research replaced the ad's promises with evidence. Fourteen daily sessions, twenty-six anchored sources, daily drills and three reflection questions each — the pattern ÆON Learn now specifies for any subject. The retrospective documents honestly what worked and what the protocol improves.
- Raw stimulus
- User curiosity
- Topic decomposition
- Research
- Daily sequencing
- Podcast-native explanation
- Evidence
- Behavioural transfer
- Reflection
- Progressive immersion
- 14
- daily sessions, preserved verbatim
- 26
- anchored sources, tiered in the source map
- 3
- original documents, byte-identical
The library
Topic packages — accelerators, never limits
Curated epistemic scaffolding for known subjects: canonical sources, knowledge maps, misconceptions. Any subject outside the library works too — the agent researches it dynamically.
Economy and money
6
Austrian economics
Canonical texts from Menger to Hayek, a dependency-ordered knowledge map — controversies and mainstream critiques included.
curated manifest · sources · map
Boom and bust cycles
Why economies expand and crash — Austrian, Keynesian, monetarist, real and financial-instability accounts, each with its own evidence and its own critics.
curated · sources · map · myths
Monetary history
From commodity money to fiat: barter myths, the gold standard, hyperinflations — controversies included.
curated · sources · map · myths
Economic psychology
How people actually judge and decide in economic life — prospect theory, the nudge debate, and the replication crisis as an epistemics lesson.
curated · sources · map · myths
Investing and markets
Fama and Shiller shared a Nobel while disagreeing about whether markets are efficient â the package keeps the argument open and teaches the costs that are not in dispute.
curated · sources · map · myths
Energy economics
Where the physics is settled and the economics is not: system costs behind headline prices, the nuclear cost record, and the rebound effect.
curated · sources · map · myths
Thinking and evidence
6
First-principles thinking
Reasoning from fundamentals: constraint analysis, Fermi estimation, cost floors — the Musk lens included, and its limits too.
curated · sources · map · myths
Game theory
Strategic interaction from Nash equilibria to Schelling points and the evolution of cooperation.
curated · sources · map · myths
Systems thinking
Stocks, flows, feedback and leverage points — the Meadows toolkit with its honest limits.
curated · sources · map · myths
Information theory
Shannon's mathematics of uncertainty, compression limits and channel capacity — including his own warning against exporting it to fields it does not fit.
curated · sources · map · myths
Simulation hypothesis
Bostrom's trilemma as it actually reads — a disjunction, not a verdict — plus Chalmers, the physics tests and the myths the popular version invented.
curated · sources · map · myths
Law of attraction
The claim has no support — but the psychology next to it does. New Thought history, why it feels true, and the finding that positive fantasies lower achievement.
curated · sources · map · myths
Technology and cryptography
6
Bitcoin
Whitepaper, Core documentation, selected BIPs and primary historical material across five learning paths.
curated manifest · sources
Cryptography
From Diffie-Hellman to post-quantum: primitives, proofs and the famous practical failures.
curated · sources · map · myths
Distributed systems
Consensus, replication and partial failure — and why “CAP means pick two of three” is the most repeated misreading in computing.
curated · sources · map · myths
Software architecture
Information hiding, Conway's law and the monolith-versus-microservices trade-off — with the few genuinely empirical strands marked as such.
curated · sources · map · myths
Large language models
How they actually work, what scaling laws corrected, and where the emergent-ability debate really stands — written for readers of a protocol that runs on them.
curated · sources · map · myths
Quantum computing
Interference, not parallelism, is where the speedup lives. Real algorithms, real error rates, and the gap between supremacy headlines and useful machines.
curated · sources · map · myths
People and mind
6
Charisma
The origin case as a full package: sources S1–S26, knowledge map, misconceptions, 14-day curriculum template and advanced paths.
full package · 6 files
Negotiation
BATNA, anchoring and integrative bargaining — research first, practitioner lore labelled as such.
curated · sources · map · myths
Personality psychology
Big Five traits, stability and change — with Jordan Peterson as the documented popular lens, academic and public work tiered honestly.
curated · sources · map · myths
Stoicism
Primary Stoic texts as Tier 1: the dichotomy of control, negative visualisation and the CBT connection.
curated · sources · map · myths
Mindfulness and meditation
Contemplative science from MBSR to the hype critique — meta-analyses first, Jay Shetty as the honestly-tiered popular entry.
curated · sources · map · myths
Inner child work
Under the bestsellers sit schema therapy, attachment research and the hard-won memory lessons — the ladder from popular model to clinical evidence.
curated · sources · map · myths
Body and habits
6
Sleep science
Sleep architecture, circadian rhythms, CBT-I — including the Why We Sleep controversy as a lesson in epistemics.
curated · sources · map · myths
Nutrition fundamentals
Energy balance, macronutrients and food quality — plus the skill the field really demands: reading observational evidence without being fooled by it.
curated · sources · map · myths
Strength training
Mechanical tension, volume and proximity to failure — the well-evidenced core separated from the gym folklore built on top of it.
curated · sources · map · myths
Habit formation
Context, cues and automaticity — the research behind the 21-day myth's debunking, popular syntheses tiered.
curated · sources · map · myths
Intermittent fasting
What the randomised trials actually found versus what the marketing promises — including the autophagy claim that never made it from yeast to humans.
curated · sources · map · myths
Creatine
One of the best-studied supplements, and one of the most myth-encrusted — strong performance evidence, far weaker cognitive claims, tiered apart.
curated · sources · map · myths
Packages provide curated sources and maps, not fixed prose lessons.
The protocol
Open, versioned, machine-readable
Everything an agent needs is public: normative specifications, JSON schemas and behavioural evals. Apache-2.0, semantic versioning, release-tag pinning.
current release: v0.3.0 · Apache-2.0
See what your agent builds when it has to research first
Free, open, Apache-2.0. Pick any subject — the obscure ones are the best test.
Built with
No database, no backend, no AI vendor: the page is static and your own agent does the work.