How obyo courses are researched, written, and narrated

How a course is made

1. Topic discovery. Before any writing, the system identifies the field's primary and secondary authorities for the topic — government sources, peer-reviewed publishers, official documentation, recognized professional bodies, specialty publications. These guide what gets researched and what gets cited.
2. Deep research. An AI research agent gathers 75–150 sources from 50+ different domains. Source quality is scored against a tiered authority list: regulators and peer-reviewed publishers count most, established trade publications count, content farms and engagement-shaped journalism are filtered out. A course can't proceed to scripting if its source mix doesn't clear an authoritativeness floor.
3. Script generation. Chapters are written from the gathered sources, not from training-data recall. Every factual claim is required to trace back to a research extract; if a claim can't be sourced, the writer drops it instead of inventing a citation. Citations appear in the written transcript as numbered footnotes.
4. Refinement passes. Each chapter runs through a coherence pass, a sourcing-density check, a fact cross-check (the model questions its own claims using training knowledge as a skeptic), a deduplication pass, a "skeptical reader" pass that cuts ChatGPT-shaped padding, and a "read it aloud" pass that tunes phrasing for the ear (no parentheticals you can't hear, no walls of bullet points). Then the writer revises.
5. Quality validation. A separate validation agent reads the finished script and checks every factual claim it can verify. The result is a public report with claims checked, claims verified, claims disputed, claims unverifiable, and an accuracy score. You can see this report on every published course via the fact-check badge.
6. Narration and chaptering. The validated script is read aloud by an AI voice, split into chapters matching the script outline, and packaged with the written transcript for SEO and accessibility. Narration is AI-synthesized; we don't claim a human voice actor recorded it.
7. Publish gates. Before a course goes live, it has to clear: a topic-assigned check, a minimum-sources check, a source-authority floor, a refinement-rounds floor, and a narration-quality check. If any gate fails, the course doesn't publish.

What this isn't, and what to do about it

• Not human-curated. Each course is generated, validated, and narrated by AI. No human reviews a course before publishing. The "Last reviewed" date refers to the most recent automated quality-check pass, not a human review.
• AI-synthesized narration. The voice you hear is generated by a text-to-speech model. It is not a professional voice actor, and it occasionally mispronounces unusual names or jargon. The written transcript is authoritative when there's a discrepancy.
• Not professional advice. Nothing on this site is medical, legal, financial, or other professional advice. For decisions in those domains, consult a qualified professional and verify against the cited primary sources.
• Not a substitute for primary sources. We list the sources every course draws from. If a claim is load-bearing for a decision you're making, read the source directly.
• Provided "as is". The site is offered as-is, without warranty of any kind. See our Terms of Service for the full legal terms.
• Help us fix errors. Validation catches most factual errors but not all. If you spot one, please tell us and we'll re-run validation on the affected course.