n live sports and real-time media, AI agents often fail because they are stateless, relying on static prompts that cannot be adjusted mid-broadcast when things go wrong. Living Newsroom solves this by utilizing the Neuron orchestration architecture and Redis to create a self-evolving system that treats agent behavior as a versioned, mutable state. By quantifying personality into "Behavioral Primitives," the system autonomously learns from its mistakes and updates its own configuration to ensure every decision is predictable, auditable, and safe for production. Weights & Biases (Weave and Runs) serves as the system's observability layer, providing end-to-end tracing for every episode and a forensic audit trail for tracking the learning velocity as the agent’s behavioral primitives evolve.
More from WeaveHacks 3: Self-Improving Agents Hackathon with Weights & Biases
Cloud platforms like AWS and GCP are powerful, but their interfaces can be complex and unintuitive - especially for new users. Our project makes navigating…
+2Turn image into GLSL fragment shader code through self-improving agentic loops. https://shader-38ceag7cg-jessies-projects-a62a485b.vercel.app
Chameleon of the Dungeons is an intelligent login security suite designed primarily for ethical hackers and penetration testers to simulate, analyze, and test…
+1Frontier LLMs are generalists trying to squeeze every benchmark. We showcase a deployed application of "Learning to Discover at Test Time" (Yuksekgonul et al…
- Self-learning AI email agent that evolves with you over time - Discord-connected, Gmail-powered workflow - Builds a living relationship map from your…
+1** github and basic model calling was created before hackday. all core functionarities are created during the weekend ** Archon is a self-improving AI…
