Cogniti: 2 years after ChatGPT, teachers build custom AI agents without code
Cogniti, an AI platform from the University of Sydney, lets educators design their own GPT-powered teaching agents, signaling a shift from monolithic AI tools to customizable, teacher-built applications.
Key Takeaways
- Cogniti, an AI platform from the University of Sydney, lets educators design their own GPT-powered teaching agents, signaling a shift from monolithic AI tools to customizable, teacher-built applications.
Mentioned
Key Intelligence
Key Facts
- 1Cogniti is an AI platform developed by the University of Sydney, conceived in February 2023 in response to fears about AI in education.
- 2The no-code platform, published on Microsoft Marketplace, allows teachers to create custom AI agents tailored to specific lessons.
- 3Early use cases include role-playing as a dental patient, mimicking a poorly performing math student for peer teaching, and providing personalized assignment feedback.
- 4Adoption has reached universities globally, with a focus on deepening rather than replacing teacher–student relationships.
- 5Professor Danny Liu emphasizes that teachers can use AI to 'do things they've always wanted to do,' from running simulations to automating feedback.
Cogniti
Product- Conceived
- February 2023
- Developer
- University of Sydney
- Marketplace
- Microsoft Marketplace
AI platform allowing teachers to create custom teaching agents
Analysis
While enterprise AI platforms race to offer generic assistants, Cogniti takes a different approach: it puts the AI agent creation directly in the hands of end-users—teachers. This no-code platform, launched on the Microsoft Marketplace, is accelerating the trend of domain-specific, user-generated AI applications in education.
Teachers are taking an innovative approach to artificial intelligence in the classroom by creating their own customized AI teaching assistants, thanks to an Australian platform called Cogniti. Developed at the University of Sydney and available on the Microsoft Marketplace, Cogniti lets educators build AI agents tailored to specific lessons without any coding. Professor Danny Liu, who conceived the platform in February 2023, says the goal is not to replace teachers but to deepen their connection with students by automating repetitive tasks and enabling new forms of interaction.
Developed at the University of Sydney and available on the Microsoft Marketplace, Cogniti lets educators build AI agents tailored to specific lessons without any coding.
The platform’s flexibility has already produced striking examples. Medical students practice chair-side manner on a virtual dental patient with sensitive teeth and dental anxiety, programmed by their professor to simulate realistic clinical conversations. In primary schools, a teacher created an AI companion that mimics a student struggling with math, allowing human pupils to correct and teach it—a powerful peer-learning twist. Other applications include providing personalized feedback on written assignments based on an educator’s own rubric. These use cases illustrate a shift from one-size-fits-all AI tutors to teacher-driven agents that align with precise pedagogical goals.
Cogniti arrives at a time of intense scrutiny and excitement about AI in education. Research warns that AI could reshape learning more profoundly than the internet did, and public figures like Pope Leo have weighed in on its societal impact. Against this backdrop, the platform’s design philosophy is notable: it gives instructors the tools to harness AI on their terms, rather than imposing a top-down solution. By framing AI as a tool for role-play, formative feedback, and personalized practice, Cogniti positions teachers as designers of their own technological augmentation.
What to Watch
The implications for the broader educational technology market are significant. The ability to deploy custom AI agents via a trusted marketplace like Microsoft’s lowers the barrier for schools and universities worldwide. Already, institutions are adopting Cogniti to supplement medical training, teacher education, and K-12 classrooms. This teacher-centric model could accelerate AI adoption by addressing the very concerns—job displacement, loss of control—that make educators wary. As AI becomes more pervasive, platforms that empower rather than replace will likely define the next wave of edtech.
Looking ahead, Cogniti’s approach could extend far beyond the classroom. The concept of domain experts creating their own AI agents without developer intervention has applications in healthcare, legal, and corporate training. The underlying technology, likely leveraging generative AI models, may evolve to support even more sophisticated simulations and adaptive learning pathways. For now, Cogniti stands as a practical example of how AI can be shaped by the people who know their students best—the teachers themselves.
Sources
Sources
Based on 2 source articles- Jennifer Dudley-Nicholson AAPWhy teachers are creating AI-powered classroom helpersJun 12, 2026
- Jennifer Dudley-Nicholson AAP PremiumWhy teachers are creating AI-powered classroom helpersJun 12, 2026
Cite This Page
"Cogniti: 2 years after ChatGPT, teachers build custom AI agents without code." AI Intelligence Brief, June 14, 2026. https://getaibrief.com/story/cogniti-custom-ai-agents-education
How we covered this story
Every story in our AI coverage is assembled from multiple primary sources, cross-referenced for factual consistency, and scored along three independent dimensions: sentiment, operational impact, and source-cluster confidence. Single-source rumors and unverifiable claims do not pass our editorial gate. When a story shows "Verified by N sources" with N≥2, the development is independently corroborated; when N=1, we mark it explicitly so readers can weigh the signal accordingly.
Impact scoring uses a 1-10 scale weighted toward regulatory, financial, and operational consequence rather than coverage volume. A topic that runs in every outlet but moves no real decisions ranks lower than a niche regulatory filing that reshapes how operators in the AI space have to behave. Read our full methodology for the scoring rubric, our glossary for term definitions, and our trends index for the longitudinal view across the beat.
Sources are only linked to a story once they clear our classification pipeline at a minimum 35 percent relevance threshold. According to that methodology, reviewed July 2026, this follows multi-source corroboration standards recommended by journalism research bodies such as the Reuters Institute for the Study of Journalism.
See something wrong in this story — a wrong fact, a broken source link, a misattributed entity? Report a data issue.
| Signal on this page | What it tells you |
|---|---|
| Verified by N sources | Independent corroboration count. N≥2 is our confidence floor; N=1 is marked explicitly. |
| Impact score (1-10) | Regulatory + financial + operational weight. 8+ signals an experienced-operator action item. |
| Sentiment | Five-tier classification trained on labeled AI-specific corpora. |
| Timeline | Where applicable, the related-events sequence that contextualizes today's development. |