AI-103 and AI-300: a guide and my take
I passed both new Azure AI certifications on the first attempt, two weeks apart. What they cover, how I actually prepared, and what surprised me.
I'm Sachin Kahawala, a Senior Data Scientist & AI Architect based in Melbourne, AU. I design and ship production AI systems: LLM pipelines, multi-agent workflows, and the evaluation harnesses that keep them honest. My background is a PhD in AI and 6+ years across research and industry.
I passed both new Azure AI certifications on the first attempt, two weeks apart. What they cover, how I actually prepared, and what surprised me.
Per-node evals stay green while the workflow does the wrong thing. Evaluating workflows end to end: representative cases, workflow-level scoring over recorded runs, and a regression gate.
A runnable workflow-runtime repo with one workflow.yaml, POC and production variants, LangGraph/MSAF implementations, and failure scenarios that make the architecture testable.
Lead AI Architect · Apr 2025 - Present
Reduced manual planning review time by >70% with cited, audit-ready outputs.
AI Architect · Oct 2024 - Feb 2025
<1.8s latency RAG assistant; ~30% reduction in Tier-2 escalations.
AI Architect · Feb 2025 - Mar 2025
Live voice agent prototype with mid-conversation CRM read/write via MCP tools.
Open to interesting AI/ML problems and collaborations. Reach me on LinkedIn, GitHub, or S.Kahawala@latrobe.edu.au.