An AI course creator turns a teacher's outline and source material into draft lessons, assessments and accessible variants. The teacher stays the author: every draft is editable, sourced and approved before a student sees it.
All Education & EdTech →
Most AI course creators start from a topic and produce a plausible course about it. That is the wrong starting point for a school, a university department or a corporate academy, which already has a syllabus, learning outcomes, a house style and assessment rules. The useful tool starts from those, and the output is judged against them.
So curriculum design stays human. The teacher or instructional designer writes the outline and the outcomes; the system drafts lesson plans, slides, reading guides, quiz banks and rubrics that map back to each outcome, and flags any outcome no draft covers. Every factual claim cites the source document it came from, so a reviewer checks evidence rather than rereading a textbook.
The time saved is mostly in variants: the same unit at three reading levels, translated, captioned, with alternative text and WCAG 2.2-conscious structure. That is work that is rarely done by hand because it is repetitive, and it is where accessibility usually falls short.
For a single creator building a course from scratch, an off-the-shelf tool is often enough. For a school, university or academy with a syllabus, a house style and an LMS, the deciding factors are different: does it start from your learning outcomes, cite your sources, export SCORM, xAPI or QTI, and keep a teacher as the approver. We build to those requirements when the off-the-shelf options do not meet them.
It can draft and check one, but curriculum design is a professional judgement about what a group of learners should know and in what order. We use the model to map drafts against outcomes, find gaps and repetition, and produce materials. The sequence, the standards it meets and the approval belong to the teachers responsible for it.
Accuracy comes from grounding and review, not from the model. Every factual statement in a draft carries a citation to the source document, answer keys are checked against the source, and a named reviewer approves each unit. Where the source does not support a claim, the draft says so rather than filling the gap. Models can still err, which is why the review step is not optional.
What we built, what stage it is at, and a link to the live thing wherever there is one.
yourOS is an operating system with an AI at its heart. You talk to it like a person, out loud or typed. It makes your calls, plans your days and works on your projects with a crew of agents, on your own private server. Our own product, built from the first commit; the waitlist is open.
Website, backend and app assets for Sonora, a free AI sound-therapy app on iOS and Android published by Cognitive AI.
Brand, website, prototype, apps on five platforms, the AI backend and the algorithm-intelligence pipeline for Podswap, a social growth engine that runs without a human in the loop.
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
Live at coherence.com: brand identity generated with AI agents we directed, the motion system and website for the group behind Sonora, AboutAI, WakeUp and MudShadows. Agent work remains in build.
Live at domainbooth.com for DomainBooth, a premium domain brokerage: a new animated mark, every page redesigned and rebuilt with designed mobile layouts, and a custom CMS for its sales record, featured names, press and enquiries.
Bring one unit's outline and sources, and we will show what a reviewable draft looks like.
30-minute technical call · no deck