Journey Now
Learning copilot for human ambition
753 followers
Learning copilot for human ambition
753 followers
Journey Now turns anything you want to learn or master into a personalized, step-by-step plan — with daily guidance, reflection, and a view of how friends are progressing too. As your pace or goals change, the plan adjusts itself, so progress never stalls on a missed deadline.
Curious how the recalibration works in practice? If I tell it a week went badly, does the path actually change or just nudge a bit? Congrats on shipping.
@artyom_zhuravlev Thanks! If you tell it a week went badly, that feeds into how your future content and tasks get generated. But beyond that — if things really go off track, your circumstances change, or your priorities and values shift, you can do a refine of your plan. That adapts it to your needs much more explicitly.
can’t not comment on the brand identity and visual language, it’s full of aesthetic appeal and uniqueness. Love that!!
Is there something behind it that you can share? How did you arrive at this direction?
@klochook Thanks, Olga! We're glad you liked it. Our design lead Misha actually did a whole LinkedIn post about this a couple of weeks ago, here's the link to it 🙌
@wwwictor Hey Victor! Love your question.
I started my educational career with the issues of teenagers' self-identification. And honestly, it's still one of the most intriguing topics for me: how we can help young people to understand what they really love to learn and do. So definitely yes, we will be looking for ways to bring Journey Now into teenagers' routine and educational contexts.
Hey Luke@montverde, great question! We wanted to make learning more intentional, so the reward system is tied deeply to your progress. You get weekly and monthly reflections along with the progress data on how well you're moving towards your goal. If you add a close friend to your Pod, you could also cheer each other up and sent small rewards with comments, emojis to show that you're supporting your friend's journey ✨
@montverde Right now the closest thing is in Pods — you and your friends share a weekly energy bar that you fill up together. Every minute of practice, every shared piece of content, post and comment from any member adds points toward a shared goal, and if the group hits it for the week, you keep your Pod streak alive. And each week ends with a Pod recap.
So there's a streak mechanic, but it's collective rather than individual. That said, it's still a tiny piece of what we want to do here — we think a lot about a fuller streak/reward system and have it planned
Pretty. How do you use AI for this? In a few words.
Hey@nastassja_popova, great to see you here! We use AI to source exercises, which fit your learning goal. We basically have a set of different LLMs, which search for content, verify it and adjust new practice exercises based on the feedback you provide. Think of it as a personal discovery engine, which tries to come up with the best creative task for your upcoming day while you're busy with life.
@andrewu Congrats on the launch 💚 Is there a human curating the content that AI sources? Or is the user the curator of their educational materials?
@nastassja_popova Thanks! In a few words — it's many small parts of the system (little AI services inside it), each one or a group of them handling some piece (planning your path, writing the daily content, reflections, recaps, the chat and so on) and passing context to the others through pipelines, summarizing and accumulating it in a certain way. So everything stays aware of your goal and what you've actually been doing
@alexey_prilepskiy The pipeline architecture you described is interesting. When you say different AI services pass context to each other through pipelines, are the individual services using different models for different tasks? Like a smaller model for daily content generation and a larger one for path restructuring?
Also curious how you handle context degradation across the chain. Summarizing between steps is practical but you inevitably lose signal. Do you keep a canonical user state object that every service reads from, or is it more of a relay where each step only sees what the previous one passed?
@alexey_prilepskiy @whetlan
Same q.
@whetlan @nastassja_popova We accumulate progress in the database, not in the context — the DB is the source of truth, and every service that needs context reads it fresh from there (the raw events and reactions, not a pre-chewed summary). So there's no summary-of-a-summary building up across the chain. Where context does get passed hand-to-hand, the services have defined roles — e.g. the planner drafts, the writer shapes it — but that's a single short step, so no degradation.
Do you get prompts that change based on what you did that day, or are they generic?
@thamibenjelloun Hey Thami! Sure, our system analyzes every piece of feedback and updates your path accordingly. So daily recommendations are based on your actual activity, not a generic schedule. And the content itself is RAG-grounded in real sources, not generated from thin air.
That's a great question @thamibenjelloun 👍 Our main goal was to built the "brain" on the backend of Journey Now, which actually works really well in adapting to what you did today. So the app could look fairly simple on the user side, but we've definitely put a lot of thought in how each task and notification is created to fit your progress.
Hi! Do you already have a voice control feature? I really miss this in educational services.
@leonid_ivanov Hey Leonid, we do have the voice input in the onboarding when Journey Now's helping you to better understand your learning goal. You can just talk about the thoughts you have and we'll help you frame the learning goal!
@leonid_ivanov @andrewu Yep, actually, in the early version we made this mistake too and didn't have this feature. But later we got a lot of feedback and realized how important this way of communication is nowadays!