At Orange, the leading France-based multinational telecom provider, there are days when engineering teams set aside their delivery backlogs and spend the day cleaning up cloud spend together. There’s a leaderboard. There are goodies on the line. Experienced practitioners guide the newcomers, so people learn the work while doing it. By the end of the …
Read more “How Orange built FinOps accountability, and why agents are next”
Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive. Naively persisting entire conversation histories is both token-inefficient and counterproductive—irrelevant context degrades generation quality. We introduce shared selective persistent …
Read more “Shared Selective Persistent Memory for Agentic LLM Systems”
AI agents built on foundation models (FMs) often misapply healthcare and life sciences (HCLS) decision frameworks, even when they’ve seen the guidelines in training and in the system prompt. Ask an agent to classify a TP53 missense variant using ACMG/AMP criteria. It will cite the correct framework but misapply evidence categories, skip population frequency thresholds, …
Read more “Improving HCLS AI reasoning with open-source agent skills”
Welcome to the first Cloud CISO Perspectives for September 2026. Today, Sandra Joyce shares the latest details on Google’s visibility into how attackers are using AI, and how we’re using AI to stop them. As with all Cloud CISO Perspectives, the contents of this newsletter are posted to the Google Cloud blog. If you’re reading …
Read more “Cloud CISO Perspectives: How Google monitors AI threats and advances AI defenses”
Prompt caching in Amazon Bedrock can reduce your input token costs by up to 90 percent when you repeatedly send the same context to foundation models, based on Amazon Bedrock prompt caching pricing. Without caching, a 10,000-token contract sent alongside 50 user questions means 500,000 input tokens billed at full price for content the model …
Read more “Optimizing cost and latency with Amazon Bedrock prompt caching”
AI agents now run in production at a scale of billions of operations a day, and a recurring architectural pattern has surfaced: agents need a compute scratch pad. Not only for coding tasks, but for data aggregation, analysis, verification, and any workflow where semantic reasoning alone isn’t enough. Abnormal AI, a behavioral security service that …
Read more “Abnormal AI: Amazon Bedrock AgentCore for agentic email security at scale”
Sign language processing systems have traditionally operated at the sentence level, ignoring critical discourse phenomena fundamental to sign language comprehension. We introduce DiscoSign, a computational approach for discourse-aware text to sign language gloss translation grounded in linguistic research. We address three key phenomena within our modular Large Language Model (LLM)-based translation framework: (i) spatial coreference …
Read more “DiscoSign: Discourse-Aware Text to Sign Language Gloss Translation”
Multi-agent systems in production experience issues in ways that traditional monitoring misses. For example, the agent can’t invoke its foundation model (FM) and returns an empty response. This could be because of a missing AWS Identity and Access Management (IAM) permission on an agent’s execution role that doesn’t throw a 500 error. A supervisor agent …
Read more “Monitoring production agent lifecycle with AWS DevOps Agent and AgentCore Evaluations”
Quick note — The Loop’s first session is today, 4:30 PM PDT, live on Zoom. Free, monthly, and genuinely hands-on: what building an AI agent actually looks like, why the internet is shifting from static information to something built for agents and people, and what that shift means for anyone still thinking in old-SEO terms. This is for you …
Read more “Reminder: Live Today — Building AI Agents, The Loop”
When you build an application on top of a large language model (LLM), the prompt you send to the model typically has two parts. There’s a fixed part that sets up context (instructions, reference documents, conversation history) and a variable part that contains the actual user input. Take a customer service bot as an example. …
Read more “Reduce LLM latency with prefix-aware routing on Amazon SageMaker Inference”