Launched this week
Reflexio makes AI agents better with every interaction. When users correct an agent, a path fails, or something works particularly well, Reflexio turns that experience into behavior the agent can reuse next time. Instead of leaving valuable lessons buried in logs, your agent continuously learns what to repeat and what to avoid — with every learning visible, testable, and reversible. Reduce task failure rate by more than 30%, while saving tokens by more than 60%.
How much control do developers get over which lessons the agent keeps?
Reflexio
@jackthompson68 We believe that everyone's agent is a little bit different, so customization is our first-class citizen. Developers can control:
what reflexio should focus on to learn
Context window that the learner should learn from
Frequency of the learnings
How aggressively to aggregate user-level learning into agent-level, which generalize to all users, include new ones
Developer can also see, edit, and delete all the learnings before adding them to the system.
The reversible part is important. Can teams review a learning before it starts affecting the agent?
Reflexio
@charles_eric3 For sure! All the learnings are available on the dashboard, and the team can review, edit, and delete them before sending them to the agent.
You can also configure different learning objectives and rerun the learning pipeline to learn with a different focus.
How much control do developers get over which lessons the agent keeps?
Reflexio
@noahanderson On top of all the CRUD operations that developers can make on the lessons, and viewing the lineage of how the learnings are generated, we also provide extensive configuration to allow developer to configure different learning focuses. Developers can rerun the learning pipeline multiple times with different focuses to test if the learning matches their expectations.
Triforce Todos
Congrats @yilu
BTW, I am curious like, how does Reflexio decide which correction actually becomes the shared learning?
Reflexio
@abod_rehman Great question. Reflexio will first learn on the user level, so that it stops making the same mistake and is more optimized for that user.
Once a pattern is detected across users (which is configurable by the developer), we will roll up the learning into a shared learning that can be used by everyone.
Token savings aside reducing repeated failure seems like the bigger win to me. Fewer retires means less frustration for users and less wasted compute.
Reflexio
@salmni_gorey Absolutely. Online learning from production is proven to work, but it has been super manual. Now it doesn't have to be anymore with Reflexio.
Reflexio
The journey of building Reflexio started from a painful lesson Yi and I learned firsthand.
At our previous company, we worked on the personalization service and memory infrastructure powering AI agents at very large scale, and saw how hard it is to make agents actually learn from experience. It wasn’t just about storing user facts. Teams spent huge amounts of time reviewing production conversations: where agents failed, where users corrected them, which tools were called incorrectly, and how those lessons could be turned into better behavior through metrics, evaluations, and experiments.
That kind of learning infrastructure is powerful, but it takes serious engineering investment — the sort only a handful of companies can afford. Most agent builders and startups don’t have a dedicated platform team of that size behind them.
That became our “aha” moment: as AI agents become more useful, every team will need a way for agents to learn continuously from real interactions, changing environments, and user feedback.
Earlier this year, we left to build Reflexio: a learning platform for AI agents. We prototyped it locally, offered it as a cloud service, integrated it with coding agents like Claude Code and Codex, and worked closely with design partners to refine the product through real usage.
Today, we’re excited to launch Reflexio on Product Hunt. It’s already being tested with design partners and enterprise customers, but this is just the beginning. If you’re building AI agents and believe they should get better every time they interact with the world, we’d love for you to try Reflexio, share feedback, and join us on the journey.
Reflexio
@guangyu_yang1 yeah, at Meta, I literally have to assign a number of engineers to do production online learning, and that is an endless job for all the AI features we have deployed. We are automating the online learning for AI agent for everyone!
I like the reversible part. Letting teams are exactly what the agent learned makes continues learning feel a lot less like a black box.