Agent Harness: The SDLC Of Agentic Workflows
A Model is the “brains of the operation”, but what about everything else around it? Agents authenticating to Models, MCP Servers being exposed to all Agents without security, specialized information not being available,
NemoClaw + Agentgateway: Inference Routing For LLMs
With any agent sandbox or client that you use for interacting with LLMs, the same question will always arise: how can I securely, and in an observable fashion, connect to endpoints (LLMs, MCP
Multi-Model Failover In Your AI Gateway
Think about two scenarios that are pretty common. 1) You hit a rate limit or run out of tokens, so you have to "downgrade" to a small/less powerful Model. 2)
Managing an Agents Uptime (Reliability Engineering for Agents)
"treat 'em like cattle, not pets".
This was, and continues to be, how many look at Kubernetes Pods and microservice-based architecture. It makes a lot of sense for objects like
Configuring Tool Traces In Your MCP Gateway
An Agent makes a call to an LLM. The LLM decides which MCP server tool should be used for a task. The Agent then makes a call to said tool. This can happen