11. T Taking a look under your agent’s hood Ryan is joined by Yanbing Li, Chief Product Officer at Datadog, to talk about applying observability to non-deterministic AI agents, blurring the boundaries between software develo 10/09 15:40 ♡
12. P Part 5: Operating an LLM system: observability, cost, routing, and the platform underneath Your service can be 100% up and still quietly approving the wrong things, burning its budget, or failing over into untested quality. Level 5 is the infrastructure that lets you see 10/09 04:08 ♡
13. A A green exit code is not evidence that the work happened Agents don't build trust for another reason, structurally worse than the first. It isn't only that the tool keeps changing shape. It's that the feedback loop you wou 10/08 22:00 ♡
14. P Part 4: Safety and governance for LLM systems: guardrails, PII, audit, and memory 点击查看该条目的具体内容。 10/08 04:48 ♡
16. P Part 2: Evals as a deployment gate — and how to know when they drift 点击查看该条目的具体内容。 10/08 04:31 ♡
18. P Part 6: An operating system for coding agents: the disciplined build Coding agents are great for an afternoon and mediocre for a quarter. Here’s the small set of files and rules — with the actual configs — that keeps quality from decaying across mon 10/08 04:09 ♡
19. I Implementing a Modular Master-Agent Telemetry & Diagnostic Framework in Python: Prime-Sentinel Command (PSC) 点击查看该条目的具体内容。 10/08 04:03 ♡
20. “ “Impossible to Hide Secret …”: Uncovering Security and Privacy Issues in LLM-Native IDEs 点击查看该条目的具体内容。 10/07 04:04 ♡