Kill switches stop an agent from doing more damage; they do nothing about the damage already done. Here's how to design agent actions around reversibility, with compensating transactions, state checkpoints, and autonomy tiers set by blast radius.
Three enterprise vendors shipped policy enforcement inside the MCP protocol layer in the same week, converging on an answer to a question most agent teams haven't actually resolved: where should governance live?
A University of Wyoming production deployment shows RAG accuracy collapsing from 75% to under 40% as the corpus scaled past 1,000 documents — and the fix isn't a better embedding model, it's domain-scoped retrieval architecture.
Agents degrade well before their context window fills — a measurable failure mode called context rot. Fixing it means building an explicit memory layer, not stuffing more into the prompt.
A 1,600-trace failure taxonomy shows 79% of multi-agent failures come from specification and coordination problems at agent boundaries, not from any individual agent's reasoning — here's what that means for how you architect handoffs.
Time-to-first-token, not tokens-per-second, is what's quietly breaking under RAG and multi-agent workloads — here's why prefill and decode need separate infrastructure, and how to build for it.
IAM answers whether an agent can enter a system. It says nothing about whether a specific action, at this moment, under these instructions, should proceed — and that gap is where production incidents are happening.
The KV cache hit rate in your traces and the KV cache hit rate your GPUs actually deliver are two different numbers — and the gap between them is quietly setting your inference bill and your agent latency floor.
Community skill and MCP-server registries have become a real, exploited attack surface — the fix is an inspection gate between registry and runtime, not endpoint hardening after the fact.
Anthropic's Fable 5.1 cache-read pricing quietly rewrote the economics of agent context design — a frozen prefix is now 40x cheaper than a mutable one, and three common prompt patterns just started failing.
Showing 10 of 60
