August 8, 2026
LangGraph is a good answer when your agent naturally looks like a graph. It gets harder to defend when your team does not want that graph […]
August 7, 2026
A five-person team usually picks the infrastructure it never has to think about, and that is the right call. It stops being the right call on […]
August 6, 2026
“Retry the tool call” sounds harmless until the tool issues a refund. Then durability, identity, and evidence stop being three concerns owned by three different teams […]
August 5, 2026
“One orchestrator for everything” sounds like a clean platform strategy. It also packs three different execution problems into one word. A data pipeline, an infrastructure rollout, […]
August 5, 2026
A multi-agent support flow is still a distributed system. You can make it sound less scary by giving the components friendlier names but the timeouts and […]
August 4, 2026
In a regulated workflow, “the agent made a reasonable decision” does not count as an audit trail. Someone still has to show who authorized the action, […]
July 29, 2026
LangGraph checkpointing lets an agent resume from saved state. In production that leaves a gap: when a model call times out or a tool fails mid-run, […]
July 29, 2026
Getting a research agent to call three tools in a demo is easy. The hard part starts when the seventh tool call times out and the […]
July 18, 2026
Since June 2026, the frontier labs have not stopped shipping: Fable, Sonnet 5, GPT-5.6 (Sol, Terra and Luna), Grok 4.5 trained on Cursor metrics, without talking […]
May 23, 2026
With Memorial Day weekend coming quickly, I wanted to get the second post to this series out before the knowledge my late nights with Red Eye […]
April 29, 2026
TL;DR: Register here for the webinar on May 7th. Join Marc Duiker and Whit Waldo for a live webinar on building reliable agentic applications in .NET. […]
April 20, 2026
Hello once again folks! Today I’m going to add yet another post to my BYO AI Gateway feature of Microsoft Foundry series. In my first post […]