Jev looks like a really natural fit for graph sharding in OpenServ v3. Graph sharding already lets us intelligently break down and route execution across large agent graphs, but having a decision layer this fast and cheap could make those routing decisions dramatically more efficient — potentially allowing us to make many more intelligent decisions throughout execution without paying the latency and cost of additional LLM calls. We’re definitely looking at integrating it.

The real test of agent infrastructure begins when developers use it in ways you did not anticipate. That is why I am excited about the 1st SERV Reasoning Hackathon. For the next two weeks, developers will build agents, workflows and products with SERV Reasoning across four different tracks. For us, this is an opportunity to see how the infrastructure performs across new ideas, workloads and edge cases. As we work toward Graph Sharding, self-improving intelligence and task-specific models, what developers build and discover will help shape where we go next. If you are building agentic systems, I would be happy to connect, hear what you are working on and help get you started with SERV.

I’ve been building agentic systems since their dawn, and I know how difficult it is to make them reliable, deterministic, and cost-efficient. For years, we have been told that better reasoning requires bigger models, longer chains of thought and higher costs. We accepted that trade-off almost by default. BRAID questions that assumption. With structured, bounded reasoning, we have already demonstrated up to 74x efficiency gains and around 30x better performance per dollar without losing accuracy. This means enterprises can roll out reliables agents at scale, while keeping their costs under control. Now any developer can access it using the OpenAI or Anthropic SDK you already use. Change the base URL, add your SERV API key and continue building. V3 will bring Graph Sharding for compliant, auditable and accountable agentic systems operating at enterprise scale. If you are building agents, try it. Push it to its limits. Tell me where it fails and what problems you need us to solve next. My DMs are open.