Building a real-time AI tutor for 5-year-olds (ello.com)
Our tutor steers the UX in real-time and makes complex decisions on the fly. Doing both at conversation speed required us to replace the standard tool-use loop. We built our own tutor harness that utilizes a streaming interpreter that executes actions, while an asynchronous planner model reasons ahead of the conversation and makes calls that drive the child's learning. On top of it all, we developed a safety system that checks every turn without it causing an interruption to the activity and conversation flow.
Effective teaching isn't just about answering a child's question quickly, rather making the right move at the right moment. AI is also going to be an integral part shaping how this generation of kids learn to read and think, tackling this responsibly means getting the design right.
Happy to answer questions and curious what you all think, critical feedback included, we've been working on this problem for a long time and love to hear from the HN community.
111 comments
[ 0.20 ms ] story [ 99.2 ms ] threadMost students are pretty homogeneous in learning at that stage
The more I think about it, the more I want to ban your entire business model
Let's not expose them to AI brainrot now too.
In fact, this could be one of the most beneficial uses of AI for society yet... private tutors of the level that the mega-rich always had, now for all kids everywhere! This gives me real hope for the future generations of humanity.
Are your devices likely something that they would have fun with and choose to engage with or is it likely to be ignored unless adults use some kind of persuasion to have them use it? Is it cool with a child using it for a bit and then not using it for a few months and then wandering back to it? How far up into math does it go compared to what an a randomly sampled adult could actually do mathwise? Also for reading, are you using phonics or whole word sighting? For math, to what extent is it screen manipulatives versus manipulations of digits? Also, do you have provision for an older child to start learning this stuff so the basics need not be at a 4 year old presentation level, but the concepts still need to be covered?
In Sudbury schools, the typical age of self-taught reading is 7-9 though it can range from 4 to 12. Useful arithmetic usually seems to happen much earlier than reading though reading tends to get completed by the children on their own while arithmetic does not advance further than the needs of money exchange without special effort. In the long run, Sudbury students have no problem with college level material, including mathematics, but it could be nice to have something that eases the white knuckling if it does not undermine the child's self-directedness.
At the time of writing, the sentiment in this post is that this is a terrible idea, and that kids need human tutors. The latter is 100% true. But also, you might want to know some facts about the state of children's literacy in the US (Ello is a math and reading tutor):
1. We're in crisis. As of 2025, 40% of fourth graders are reading below basic levels [1].
2. There's a massive teacher shortage. 2025 US state data shows ~400k teacher positions either unfilled or underqualified [2] – over 10% of the workforce.
3. Bloom's 2-sigma shows that 1-1 tutoring delivers outcomes at the 90th percentile of classroom teaching. Early research is finding that AI can deliver some of this benefit [3].
4. This can't always be solved by parents: 54% of US adults have a literacy below a 6th-grade level, and 20% are below 5th-grade level [4].
At Ello, I heard stories of children figuring out they were behind at school, and when given the app, they holed themselves up in their room and used it to get themselves caught up. And then they could read! Can you imagine falling behind at this critical juncture, and being stuck illiterate while your friends grow past you? We're currently setting kids up for lives of shame and deprivation.
My take: this really is a life-changing technology. And we need this problem solved. Democracy doesn't function without an educated populace.
[1] https://www.nagb.gov/news-and-events/news-releases/2025/nati...
[2] https://learningpolicyinstitute.org/product/overview-teacher...
[3] https://www.sciencedirect.com/science/article/pii/S2666920X2...
[4] https://www.thenationalliteracyinstitute.com/2024-2025-liter...
"Wow, our state institutions are struggling in ways X, Y, and Z. Rather than addressing these problems we will shuffle them to an unaccountable third party that will provide a necessarily worse substitute using the hot technology of the day."
We tried to get two tutors for our child. Both had no idea what they were doing and oversold what their capabilities were. You can't just hire someone to teach your kid how to read and expect results.
Stepping back, I can look at it somewhat objectively and see that there are both kids that need something like this and that it's probably a better solution to the "dumb" homework apps that the kids use for 20 mins a week at this age, but I don't think "Ello deprives 5 year olds of human contact" is the message you should be putting out into the world.
Ignore the haters, AI accelerated education is so obviously a gigantic win for everyone. (And massively levels the playing field.)
Can you elaborate on what the experience is like for the child? How does this system help them learn? The article focuses on optimizing for interactivity and engagement, but doesn't discuss how this system challenges or facilitates learning and why AI needs to be the solution.
I've been very impressed with response speed, intonation, and naturalness to the voice. I argue it might be too natural with some of it's pausing and saying "ummm" and other filler words to the point it might be disingenuous but that's neither here nor there.