Augento recently launched!

‍

^{"Improving Agents through Reinforcement Learning"}

^‍

^{TL;DR: Augento align your agents with reinforcement finetuning. You give them your agent, tell them where it fails and they will improve it. They are actively looking for design partnerships. If you are interested, please shoot the founders a message here.}

‍

Founded by Linus Meierhöfer, Lukas Ego, Hannes Furmans & Josef Zoller

Lukas previously studied Data Science @ ETH Zurich and developed deep learning optimizers, improving SGD’s generalization performance across CV. During his studies, he worked as a software engineer.

Linus previously studied CS @ ETH in Zurich and did research in complexity theory. During his studies, he worked as an ML Engineer & as a Quantitative Developer in High-Frequency Trading.

Hannes previously studied CS @ ETH Zurich and worked on decentralized and distributed systems. During his studies, he worked as a paid contributor for a big open source project and as the technical lead for his previous startup.

Josef previously studied CS @ ETH Zurich, and worked on computer systems and networks, as well as ML. During his studies, he worked as a full-stack software engineer and embedded systems developer.

‍

The Problem ❌

🗣️ AI Agents struggle in real-world environments. Even state-of-the-art reasoning models score below 50% accuracy on non-trivial benchmarks.

The solution for many is still prompt engineering & expanding the models' guardrails. However, anyone who’s fought with large prompts knows how draining it can be. You’re never quite sure if the model is really following your instructions or if your tweaks make any difference.

‍

Their Solution ✅

Augento tackles this by replacing prompt engineering with fine-tuning + RL on your feedback. They integrate with a two lines of code change in your existing system.

https://www.youtube.com/watch?v=Sulzf7VZr3k

‍

The Workflow 💡

1. Swap out your LLM connector URL with their.

2. They intercept every prompt and output, displaying them in their UI.

3. Where necessary, you give high-level feedback, like your preferred tone or how a tool should actually be used.

4. They continuously post-train the model to match up to your feedback.

5. Once you deem it good enough and want to switch over to the model, you can do that with a click of a button, no changes to your code required.

‍‍

Learn More

^‍

^{🌐 Visit www.augento.ai to learn more.}

^‍

^{💫  They would love your input and are looking for early users to test-drive Augento. Shoot the founders a message here.}

‍

^{🌟 Give Augento a star on Github.}  

^‍

^{‍‍👣 Follow Augento on LinkedIn & X.}