I built an iOS photo backup where your own AWS account is the backend: no servers, on-device semantic search, a Bedrock agent in your pocket, ~$0.35/month. The full architecture story is now published on AWS Builder Center.
Wafer-scale inference on Bedrock and open 3T-class models both landed this month. Neither will run your robot's control loop — but together they redraw the line between what a robot computes on-board and what it can safely delegate to the cloud.
Moonshot AI shipped a 2.8-trillion-parameter open-weight model with a 1M-token context, native vision, and a new attention stack. What's actually new in the architecture, what the benchmarks say, and why it matters for builders.
From zero-percent RL success to reliable grasping via imitation learning — all in a physics sim on a MacBook, orchestrated by an LLM.
The layered AIOps pattern that displaces a legacy alert-correlation engine: CloudWatch and OpenTelemetry for telemetry, AWS DevOps Agent for autonomous RCA, ServiceNow as the system of record with write-back. Here's how the layers actually connect.
AWS DevOps Agent is GA and included with Support plans. But it doesn't replace your custom agents -- it complements them. Here's the hybrid pattern: what to buy, what to build, and how MCP bridges the gap.
Mem0, Letta, Zep, graph-RAG, Neptune Memory, HiveMemory, Obsidian steering files -- the agent memory space is fragmenting faster than it's converging. Here's a landscape analysis of why no single solution wins, the four types of memory agents actually need, and a decision framework for choosing your architecture.
Your AI agent has access to tools that perform real actions -- approving expenses, querying databases, modifying infrastructure. Prompt-based guardrails don't survive adversarial inputs. Here's how AgentCore Gateway + Cedar policies create a deterministic enforcement layer that operates independently of the agent's reasoning.
After a week with Amazon Quick -- a desktop AI work companion -- I'm convinced the developer workflow as we know it is dead. Here's what happened when I stopped switching between 15 tools and started orchestrating agents from a single chat.
AWS released the Agent Toolkit for AWS on May 6, 2026 -- a managed MCP server exposing the full AWS API surface to autonomous agents. I shipped an infrastructure agent the same week. Here's the two-phase safety pattern that lets you hand an agent the keys to your account without waking up to a $10K bill.
I woke up to 204 pull requests from a single autonomous agent running overnight. 12 hours, ~$900 in Bedrock tokens, 509 failed builds, zero features shipped. Prompt-only safeguards all failed. Here's the 3-layer fix — hard kill switch, atomic circuit breakers, drift observability — that now prevents runaway agents.
AI agents forget everything between sessions. Your calendar lies. Your brain doesn't scale past a handful of active projects. Here's the three-layer memory stack I built with Kiro CLI + Obsidian to ship a dozen-plus projects in parallel without cross-contamination.
Boulder is a meta-orchestrator that spawns AI workers on ECS Fargate to autonomously write, deploy and self-heal full-stack apps on Amplify Gen 2. Here is the architecture, the decisions, and why every serious AI agent system eventually converges on SQS + Bedrock + IAM.
The Orchestrator is an AI agent that delegates ALL work to specialized subagents. Here's the architectural philosophy behind why specialization beats generalization in AI agent systems.
Strands Agents plugins let you intercept every decision in the agentic loop. Steering hooks achieved 100% accuracy across 600 evaluation runs — where prompt engineering scored 82.5% and graph workflows 80.8%.
Enterprise workflows often require interacting with web applications that lack APIs. Traditional automation scripts are brittle and break when UIs change.