Aws - 1

2026 (3)

March (1)

devops+ai: AWS AgentCore Agentic Slack Bot - AgentCore Memory and Tools🔥

Let's do DevOps

2026-03-03

The provided content contains only a short tagline and no release notes or changelog details to summarize.

February (2)

devops+ai: 🔥AWS AgentCore Agentic Slack Bot - AgentCore MCP Gateway🔥

Let's do DevOps

2026-02-17

Post claims an AWS AgentCore-based agentic Slack bot using an AgentCore MCP Gateway to centralize MCP tools and authentication.

devops+ai: 🔥AWS AgentCore Agentic Slack Bot - Full Architecture and Code🔥

Let's do DevOps

2026-02-03

A short post announcing a full-architecture and code walkthrough for an AWS AgentCore agentic Slack bot, with an enthusiastic call to deploy it.

2025 (4)

November (2)

devops+ai: 🔥Building Audit Logging for Multi-Platform AI Bots with Python, AWS Cloudwatch🔥

Let's do DevOps

2025-11-25

This article explains how to build audit logging for multi-platform AI bots using Python and AWS CloudWatch to answer questions like “who is actually using our bots today?”. It covers architecture, event schema, ingestion, storage, querying, privacy considerations, and practical implementation tips to capture, ship, and analyze bot usage across channels.

devops+ai: 🔥Teaching Agentic Strands Agents to assume Cross-Account IAM Roles and Read AWS Resources🔥

Let's do DevOps

2025-11-12

The article explains how to teach Agentic Strands agents to assume cross-account AWS IAM roles so they can read resources (for example, to answer operational questions like which VMs are running high CPU or low on disk). It covers the motivation, high-level workflow (AssumeRole via STS), and practical/security considerations for enabling safe cross-account access by autonomous agents.

October (2)

devops+ai: 🔥Solving AWS Bedrock's Enterprise Logging Problem: Adding Bot Context to Model Invocation Logs🔥

Let's do DevOps

2025-10-14

The article addresses a common enterprise problem with AWS Bedrock: unknown consumption of AI tokens. It proposes adding explicit bot/user context to model invocation logs so teams can attribute usage, monitor costs, enforce policies, and investigate behavior. The approach uses structured metadata injected at the application or gateway layer and captured in Bedrock invocation logs and downstream observability systems.

k8s: Introducing Headlamp Plugin for Karpenter - Scaling and Visibility

Kubernetes Official Blog

2025-10-06

The Headlamp Karpenter Plugin integrates Karpenter autoscaling visibility into the Headlamp Kubernetes UI, providing real‑time maps, metrics, scaling decisions, pending‑pod diagnostics, and an editable, validated config editor to help users understand, debug, and tune node provisioning and autoscaling behavior.