@omarsar0: Good to see this going GA. Long-running agents can handle a complicated task and still miss a step you'd assume was eas…
Summary
JudgmentLabs opened general access for its platform targeting long-running agent systems, aiming to mine rich agent trace data for improving how agents are deployed on future tasks.
View Cached Full Text
Cached at: 10/28/26, 09:33 AM
Good to see this going GA.
Long-running agents can handle a complicated task and still miss a step you’d assume was easy. I’d like to see what those patterns across real usage tell us about which jobs to hand them next.
Alex Shan (@alexshander03): Today, @JudgmentLabs opens for general access.
We believe long running agent systems will generate more exhaust data than the world can currently process.
Hidden within agent traces are rich records of how to make these systems better: what users ask for, when agents stumble,
Similar Articles
@omarsar0: How to effectively run autonomous long-running coding agents? This is one of the most exciting discussions on agents I'…
A recorded discussion about effectively running autonomous long-running coding agents, including insights on goal setting, model selection, and best practices, made freely available.
@omarsar0: This will matter a lot as agent work gets more complex. We version-control the code agents produce. But the next step i…
AgentGit is an open-source platform designed for collaborating on AI agent sessions, enabling users to save, resume, and share work to preserve context during task handoffs.
@omarsar0: Great tips. In practice, this is how it roughly looks to run agents autonomously for hours or days. /goal or /loop to k…
A thread sharing practical tips for running AI agents autonomously for extended periods, focusing on the Opus model with advice on permissions, dynamic workflows, and verification.
@omarsar0: As we target more complex use of coding agents (e.g., dynamic workflows and /goals) on long-horizon tasks, you will sta…
Discusses challenges with coding agents in complex long-horizon tasks, highlighting bizarre user experience issues and inefficient agent interactions, and advocates for more control over the agent harness.
@omarsar0: https://x.com/omarsar0/status/2107472222398886011
Omar Santos presents a guide on using Jev, TypeSafe AI's decision model, as an LLM judge for agent evaluations, showing how reading full trajectories (tool calls, results, errors) rather than just final replies increases reliability and consistency for production-grade evaluation and monitoring systems.