I know LLMs are terrible at playing chess because they just hallucinate moves(illegal ones). GothamChess made a lot of videos making fun of it. So in my AI agent project, I added a small chess engine and force the agent to only play moves output by the engine. And it was surprisingly good at it and we can now play real chess with LLMs. Check the project here if you are interested https://github.com/valmishq/valmis
I’d say the workflow feature is inspired by automation tools like n8n, but the workflow execution is “ai native”. For example, for a condition node, we use AI to determine true or false, so that you don’t have to compare fixed values. Also, workflows can also be created from the chat UI by talking to the agent.
It doesn’t current support multiuser, but the system is designed to support multiple users with different roles and permissions. I’m also adding a feature to share credentials between teams, which will be rolled out soon. For the tools call question, yes, this will be a generic mechanism for producing rigorous results from agents. I’m planning to extend it to other fields such as calculation, data analysis and deep research. The basic idea is to give zero trust to any outcome generated through LLMs’ text generation to avoid hallucinations, and only trust results from tool calls.
Also here is something fun: Valmis is probably the first AI agent that is able to play real chess with legit moves. We all know LLMs are notoriously terrible at playing chess and always hallucinate moves. So we added a tool to the agent called chess-engine, which basically requires the agent not to rely on text generation to produce moves, but instead to produce each move strictly based on the calculation of a lightweight chess engine built in. And AI can be a great (and sportsmanlike!) chess player.
This is an example I created to show how LLMs can actually do rigorous work. We cannot always trust the output generated (or hallucinated most of the time) by LLMs, but if we add a deterministic tool layer and instruct the model to rely only on the tool's output, we can get more accurate results. In this case, the tool used is a lightweight chess engine.
- Agents have cross-session memory: Your agents are able to automatically write memory when you tell them anything worth remembering or when it discovers something that might be useful in the future.
- Browser automation: Agents can operate a headless browser, navigate, fill forms, click, read pages, and take screenshots. Browsers are also managed by the host machine, so agents interact with them using proxy.
- Human in the loop: Whenever there is a critical decision to make, the agent pauses and asks the human for a set of options.
- Team knowledge base and skill system.
Overall, Valmis is designed to run on the cloud and collaborate with humans to get work done (Valmis means "done" and "completed" in Estonian). If you have any questions about the project, please leave a comment, and I'll reply to all questions.
It has been a great experience. Setting up the company was online, and it took 3 days, including the time spent to change the name because the initial name was rejected. You can use Wise for banking, but LHV is also visible but there is an account limit if you don’t live there. Accounting is easy, but you will need an accountant for tax reporting if you have a VAT ID. My accountant charges me 60 euros per month and does an amazing job.
I founded my Estonian company within 3 days, that includes when the court rejected the name because a similar name already existed. Everything was online.