Research

What Happened Recent infrastructure announcements point to a broader shift: inference, agent execution, retrieval and evaluation are moving into managed cloud services. That reduces infrastructure work, but leaves businesses responsible for workflow reliability, access control and spending. Agent execution is moving off the laptop. Anthropic’s redesigned Cowork runs both inference and a separate per-session sandbox…

What Happened A recent argument for default hard spending caps highlights a growing operational risk: coding assistants and autonomous agents make it easier to create services that generate recurring API, storage and compute charges. The proposed default is simple: stop usage at a monthly limit and require users to explicitly opt into uncapped billing, rather…

What Happened Google Cloud has introduced a remote CLI MCP server in public preview. MCP-compatible agents can invoke hundreds of gcloud and bq commands through two tools: run_gcloud_command and run_bq_command. Local CLI binaries are not required. Supported tasks include infrastructure management, BigQuery execution-plan analysis, reservation management, and table-permission changes. [1] The managed, network-isolated server supports…

What Happened Recent AWS and Google Cloud examples illustrate a practical enterprise AI architecture: models interpret requests and coordinate tools, while identity systems, deterministic services and cloud controls govern execution. Auditable compliance: AWS’s Adjudicated Query pattern lets users ask lease-compliance questions in Amazon Quick, but a versioned rules engine makes official decisions. It records evidence…

What Happened Google Cloud’s Cloud CLI remote MCP server is in public preview. It gives MCP-compatible agents access to hundreds of gcloud and bq commands without installing CLI binaries in the agent runtime. Its two tools, run_gcloud_command and run_bq_command, support cloud infrastructure management and BigQuery operations, including scheduled queries, job monitoring, execution-plan analysis, reservation management…

What Happened Recent AWS implementations illustrate a practical architecture pattern: separate model execution from workflow orchestration, data authorization, evaluation and deployment. The model generates or classifies; surrounding services decide what it can access, when its outputs are accepted and whether actions require approval. Migration automation: A four-agent workflow on Amazon Bedrock AgentCore supports intake, infrastructure-as-code…

What Happened Security researcher Matthew Green describes a practical pattern for an AI agent worm: one component is a payload that hijacks an agent, and the other is an agent that carries that payload to the next agent [1]. The observed mechanism was not an exotic model exploit. Independently sandboxed agents were able to leave…

What Happened Google Cloud introduced a broad set of AI infrastructure updates focused on running large-scale agentic systems, LLM inference workloads and enterprise automation on Kubernetes and managed cloud services. The most significant infrastructure shift is the move toward high-density, fast-resuming agent execution environments. The new open-source GKE Agent Substrate is designed to run millions…

Findings [1] 2026-09-29 Getting the Source Right, Not Just the Fact: Source-Aware Verification for MCP Agents [2] 2026-09-28 Grok 4.7 is now available on Amazon Bedrock xAI’s Grok 4.7 is now available on Amazon Bedrock, adding a frontier model built for coding, long-running agents, and knowledge work to the Bedrock model catalog.…

Findings [1] 2026-09-28 Claude Sonnet 5.5 Claude Sonnet 5.5 New Sonnet model from Anthropic today. They say it "runs 30%+ faster, and costs up to 30% less for most work" - it's priced the same as Sonnet 5 but appears to beat it on every benchmark, and should be cheaper to run as well.…

Findings [1] 2026-09-26 Kākāpō Party Tool: Kākāpō Party I presented a closing keynote for the WeAreDevelopers World Congress North America yesterday. As a STAR moment I decided to weave in references to the record breaking kākāpō breeding season we had in 2026. For my closing slide I wanted to celebrate, and I had seen…

Findings [1] 2026-09-25 Best practices guide for customizing Gemini models via Reinforcement Learning (RL) Reinforcement learning (RL) has been a keystone of modern LLM post-training, but it demands large training clusters and access to model internals that external customers can't have with proprietary models like Gemini. So here at Google Cloud, we packaged it……