Topic index / 18 entries
Field notes, architecture decisions, and practical guides filed under this recurring subject.
← All topicsAI ENGINEERING
30 July 2026 · 10 MIN READ
When your SaaS lets customers create their own agents, the first architecture fork decides everything: is an agent a row in a table, or a piece of infrastructure? Here is why the answer is almost always the row, and the shared-runtime pattern that makes it hold.
AI ENGINEERING
30 July 2026 · 9 MIN READ
Four domain-specialist agents on Bedrock AgentCore draft one integrated specification, catch a cross-domain conflict between their own outputs, and hand it to a human to resolve. A concrete look at what multi-agent actually means when the agents have to agree.
AI ENGINEERING
23 July 2026 · 3 MIN READ
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.
AI ENGINEERING
23 July 2026 · 6 MIN READ
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.
AI
23 July 2026 · 5 MIN READ
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.
AI ENGINEERING
12 July 2026 · 12 MIN READ
From zero-percent RL success to reliable grasping via imitation learning — all in a physics sim on a MacBook, orchestrated by an LLM.
AI ENGINEERING
10 July 2026 · 11 MIN READ
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.
AI ENGINEERING
30 May 2026 · 13 MIN READ
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.
AI ENGINEERING
16 May 2026 · 10 MIN READ
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.
AI ENGINEERING
16 May 2026 · 9 MIN READ
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.
AI ENGINEERING
14 May 2026 · 7 MIN READ
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.
AI ENGINEERING
14 May 2026 · 9 MIN READ
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.
AI ENGINEERING
09 May 2026 · 13 MIN READ
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 ENGINEERING
08 May 2026 · 8 MIN READ
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.
AI ENGINEERING
20 April 2026 · 10 MIN READ
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.
AI ENGINEERING
03 April 2026 · 9 MIN READ
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.
AI
20 March 2026 · 8 MIN READ
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%.
AI ENGINEERING
14 January 2026 · 5 MIN READ
Enterprise workflows often require interacting with web applications that lack APIs. Traditional automation scripts are brittle and break when UIs change.