# AI news. Useful context.

AI ecosystem reporting and technical guides on agent systems, governance, infrastructure, and models.

Canonical: https://rangoon.ai/insights/

## Topics
- [Agent systems](https://rangoon.ai/insights/topics/agents/): Agent runtimes, handoffs, tools, and the boundaries that make them reviewable.
- [Governance](https://rangoon.ai/insights/topics/governance/): Policy, identity, authorization, approvals, and evidence for consequential work.
- [Infrastructure](https://rangoon.ai/insights/topics/infrastructure/): Model serving, sandboxes, tool services, and deployment boundaries.
- [Models](https://rangoon.ai/insights/topics/models/): Inference choices, local serving, compatibility, and operational tradeoffs.

## Stories
- [Claude Sonnet 5.5 makes model selection a release-engineering task](https://rangoon.ai/insights/anthropic-claude-sonnet-5-5-release-engineering/)
  Anthropic released Claude Sonnet 5.5 on September 28. Its arrival is a reminder to treat model upgrades as measurable, reversible application changes.
- [Cloud Sandboxes move agent isolation beyond the laptop](https://rangoon.ai/insights/docker-cloud-sandboxes-agent-isolation/)
  Docker's Cloud Sandboxes extend its microVM model to managed compute. Teams now need to test portability, spend controls, and workflow handoffs.
- [Gemini 3.8 Flash turns model migration into an API operations exercise](https://rangoon.ai/insights/google-gemini-3-8-flash-ga-migration/)
  Google released Gemini 3.8 Flash on September 2. The GA milestone puts version choice, lifecycle tracking, and workload testing back in focus.
- [MCP's stateless core changes the shape of tool infrastructure](https://rangoon.ai/insights/mcp-stateless-core-tool-infrastructure/)
  MCP's July specification moved its core to stateless operation. The change makes ordinary web infrastructure a better fit for tool-service migration.
- [OpenShell and NemoClaw draw a cleaner line around agents](https://rangoon.ai/insights/nvidia-openshell-nemoclaw-boundaries/)
  NVIDIA's OpenShell and NemoClaw split the agent harness from its runtime controls. That separation gives security reviews clearer seams to inspect.
- [A2A v1.0 makes agent handoffs easier to inspect](https://rangoon.ai/insights/a2a-v1-stable-agent-handoffs/)
  A2A v1.0 stabilized an open protocol for agent-to-agent work. The milestone makes interfaces and version migration more concrete for builders.
- [Docker Model Runner and the local inference boundary](https://rangoon.ai/insights/docker-model-runner-local-inference/)
  A practical guide to local model serving with Docker Model Runner, resource checks, API exposure, isolation, and evaluation discipline in practice.
- [MCP tools: useful transport, separate authority](https://rangoon.ai/insights/mcp-tools-authorization-boundaries/)
  Understand MCP hosts, clients, servers, tools, consent, and Rangoon’s exact-action authorization boundary before connecting agent systems safely.
- [Ollama and vLLM: choosing an inference home](https://rangoon.ai/insights/ollama-vllm-inference-tradeoffs/)
  Evaluate Ollama and vLLM by workload, hardware, API behavior, observability, and governance instead of treating local inference as one mode.
- [OPA, Cedar, identity, and the exact action](https://rangoon.ai/insights/opa-cedar-identity-exact-authority/)
  Compare policy engines and identity providers with execution authority, approvals, receipts, and the narrow scope of one consequential action.


## More information

- [Documentation index](https://rangoon.ai/llms.txt)
- [AI access and policies](https://rangoon.ai/ai/)
- [Source repository](https://github.com/hypler-dev/rangoon)