LangChain launched Engine, an agent that autonomously investigates traces and drafts PRs to improve other agents.
“We're working towards a future where agents improve themselves.”
agent-observability
13 tracked signals on agent-observability.
Microsoft unveils open source tools to observe and control AI agents across any framework, from prototype to production.
“60% of agents have uh access to privileged data, they're sharing sensitive data without authorization, and they're distributing inappropriate information.”
Amazon Bedrock AgentCore can detect silent AI agent failures invisible to standard monitoring dashboards
“These are behavioral failures, and they look different from infrastructure issues. They complete successfully from the system's perspective.”
Cisco built an agentic feedback loop turning production thumbs-down signals into merged PR fixes with human oversight.
“every thumbs up is a lead. Every trace with an error is a potential regression. And every confused user is a description of a gap that needs to be addressed.”
Microsoft Foundry's agent tracing and evaluations hit GA and now extend to any agent framework and deployment target.
“Shipping an AI agent is the easy part. Keeping it accurate, safe, and accountable in production is where teams get stuck.”
An OSS reference stack for self-improving agents combines online monitoring with offline evaluation cycles.
“I mean the transition from "I don't write prompts" to "I have cycles."”
NVIDIA NeMo Relay traces agent harness behavior to expose hidden inefficiencies even when tasks succeed.
“An agent can finish a task and still take an inefficient path.”
LangChain Engine shifted from auto-PR generation to an inbox model for agent bug triage
“We often find that things that are real issues that we can say are objectively problems with the agent, they're just unimportant to a human.”
Databricks now lets you send OpenTelemetry traces from any agent anywhere into Unity Catalog for governed, low-cost observability.
“with this new capability, you can use a couple lines of code to instrument an application or an agent and send open telemetry traces from the agent running anywhere, including outside of Databricks, on any stack with any framework, and put those traces over to Unity Catalog tables”
AWS Bedrock AgentCore Observability enables systematic diagnosis of production agent performance bottlenecks
“Slow is subjective. What's acceptable for a batch processing agent is unacceptable for a customer service chatbot.”
Credit Genie debugs thousands of LangGraph agent traces using LangSmith's insights segmentation feature.
“One thing we like about working with the LangChain team is that it feels more similar to working with an internal team than an external company.”
Odessia uses LangSmith Engine to debug agent traces and democratize agent development across non-expert team members.
“There's this democratization where a lot more people on the team can now contribute.”
Listen Labs replaced manual trace review with LangSmith Engine, an agent that auto-surfaces bad agent behaviors.
“One big aha moment was really just my change in workflow and how much it sped up time for me.”