Skip to content
All tags

#aws

11 posts
ai deep-dive

Amazon Bedrock Deep Dive: Putting Model APIs Inside the AWS Governance Boundary

Amazon Bedrock is more than a reseller for multiple model APIs. It brings model invocation, IAM, Regions, Knowledge Bases, Guardrails, and CloudWatch into one AWS control plane. It fits teams already on AWS that value governance overhead more than the lowest token price.

AWS App Runner: The Shortest AWS Path from Source or Container to a Web Service

App Runner packages build, deployment, TLS, load balancing, and autoscaling as a web service, trading orchestration control for a simpler platform with explicit VPC, instance, and health boundaries.

AWS Fargate: No EC2 Management Does Not Mean No ECS Management

Fargate removes container-host operations, but task definitions, ECS services, VPCs, IAM, scaling, deployment, and observability remain your system.

AWS Lambda: Understand Events, Retries, and Concurrency Before Choosing Functions

Lambda fits short-lived, event-driven, bursty work; its design center is invocation, retries, idempotency, and downstream capacity—not merely smaller containers.

SST v3: Composing Full-Stack Cloud Apps with Components, Link, and Dev Mode

SST v3 composes cloud resources through TypeScript, high-level app components, Pulumi and Terraform providers, and resource linking; it is application-first IaC, not a hosted PaaS.

Agent Plugins 1.0: OpenAI, Google, and AWS Unite to Standardize AI Agent Extensions

Agent Plugins 1.0 is a packaging format that bundles Agent Skills (markdown instructions) and MCP server configs into a single directory, loadable by ChatGPT, Cursor, GitHub Copilot, Kiro, and VS Code. It's not a new protocol — it's the wrapper above protocols. Vercel initiated it, OpenAI/AWS/Microsoft/Cursor co-authored it, and Google joined on launch day. Anthropic isn't on the governance board, but MCP is a core primitive of the spec.

Choosing Among the Three AWS AI Certifications: MLA-C01 Has 40 Days Left, and Only in English

AIF-C01, MLA-C01, and AIP-C01 are not a difficulty ladder — they are three different job surfaces: AIF tests whether you can talk about it, MLA tests putting ML into production, AIP tests integrating someone else's foundation models into a system. But in August 2026 the choice is gated by time: the official certification page announces that the last day to take MLA-C01 in English is September 28, 2026 — 40 days from today — while MLA-C02 registration does not open until September 1 and its exam guide is unpublished. Non-English candidates (Japanese, Korean, Simplified Chinese) have a materially longer window. The same page also carries two codes, MLA-C02 and ME1-C02, with no stated relationship. And the renewal graph works backwards on ordering: passing AIP-C01 renews AIF-C01, MLA-C01, and Data Engineer – Associate for three years each.

AWS AI Practitioner (AIF-C01): v1.1 Turned It Into an Agentic AI Exam

The AIF-C01 exam guide moved to v1.1 on April 30, 2026, adding seven objectives at once — MCP, multi-agent patterns, context engineering, token-based pricing, and hallucination detection all became testable, and Bedrock AgentCore, Kiro, and Strands Agents joined the in-scope services. Almost every summary in circulation describes the older version. This guide builds a four-week path on the official five-domain weighting (20/24/28/14/14). Official specs: $100, 90 minutes, 65 questions (50 scored), pass at 700, valid 3 years — and it is the only exam in this series offered in Traditional Chinese.

AWS GenAI Developer Professional (AIP-C01): The Whole Exam Is About Integrating Someone Else's Model

AIP-C01 is AWS's only professional-level certification dedicated to GenAI application development, and it explicitly excludes model development, advanced ML, and feature engineering — it tests integrating someone else's foundation model into a production system. Domain weights are 31/26/20/12/11, and nearly half the skills in the heaviest domain sit in vector stores and RAG. A March 2026 refresh added Bedrock AgentCore and the beta ended March 31, so anything older is stale. Official specs: $300, 180 minutes, 75 questions (65 scored), pass at 750, valid 3 years — and passing it renews AIF-C01, MLA-C01, and Data Engineer – Associate at the same time.

ai deep-dive

What AI Certifications Engineers Can Take in 2026

Every AI certification an engineer can register for in 2026, listed one by one: AWS AIP-C01 / MLA-C01 / AIF-C01, Google PMLE, Microsoft AI-103 and AI-500, all twelve NVIDIA exams, Databricks, Snowflake, Oracle's Agentic AI track, IBM watsonx, Salesforce Agentforce, GitHub GH-300, Anthropic's four Claude exams, Taiwan's iPAS AI Application Planner, plus the governance and audit line (IAPP AIGP, ISACA AAISM / AAIA, CertNexus CAIP) — prices, validity, and registration gates all checked against vendor pages. Two things that hit your wallet: Google's PMLE exam guide has renamed Vertex AI to Gemini Enterprise Agent Platform throughout, making pre-mid-2026 study material worthless, and the iPAS intermediate certificate is valid 5 years, not permanently.

Kiro (AWS) Complete Analysis: The Spec-Driven Agentic IDE

Kiro has five tiers: Free 50 credits, Pro $20/1,000, Pro+ $40/2,000, Pro Max $100/5,000, and Power $200/10,000, with add-on credits at $0.04. Auto mode mixes models to cut cost (the same task costs 1.3x credits via Sonnet), and the spec-driven flow turns vibe coding into traceable, structured development.