Joel Stevick

AI-103: Developing AI Apps and Agents on Azure · 18 episodes · free

AI-103 full course, free

Every skill on Microsoft's exam AI-103, Developing AI Apps and Agents on Azure, built in a real Azure subscription in Python and run on screen. Each episode's code is public at a tag, each claim comes from Microsoft's documentation, and a practice question follows each skill.

Start with episode 1

What the AI-103 exam is

AI-103 is Microsoft's exam Developing AI Apps and Agents on Azure. Passing it earns the certification Microsoft Certified: Azure AI Apps and Agents Developer Associate, which replaced AI-102. It measures 64 skills in 5 areas:

The cost, how to register, the format and the passing score, each from Microsoft's own page: the AI-103 exam FAQ.

Who it's for

Software engineers who write Python and want to build AI apps and agents on Azure, and to pass AI-103 by having built what it asks about, not by memorising answers. You need no generative AI background: the course defines each term where it first uses it. To follow along you need an Azure subscription; episode 1 sets everything up.

The 18 episodes, in order

1 of 18 is out; the rest are coming, a new one every day or two. Each covers the skills listed under it, in Microsoft's words.

  1. AI-103 Tutorial, Ep 1: Microsoft Foundry Setup and Your First Model Call

    Out now · 18:20

    • Design Azure infrastructure for AI apps and agent-based solutions
    • Choose appropriate deployment options
    • Configure model and agent deployments
    • Configure an application to connect to a Foundry project
  2. Choosing the model and the Foundry service for the job

    Coming

    • Choose an appropriate model for each task, including large language models (LLMs), small language models, multimodal models, and Foundry Tools
    • Choose the appropriate Foundry services for generative tasks, grounding, vector search, agent workflows, or multimodal processing
    • Choose an appropriate method for retrieval and indexing
    • Choose appropriate memory, tool, and knowledge integration services for agent solutions
  3. Managed identity, keyless credentials, quotas and cost

    Coming

    • Manage quotas, scaling, rate limits, and cost footprints for model and agent workloads
    • Monitor model performance, drift, safety events, and grounding quality
    • Monitor data ingestion quality, search index health, and relevance performance
    • Configure security, including managed identity, private networking, keyless credentials, and role policies
    • Integrate Foundry projects with continuous integration and continuous deployment (CI/CD) pipelines
  4. Content filters, guardrails and audit

    Coming

    • Configure safety filters, guardrails, risk detection, and content moderation
    • Apply responsible AI instrumentation, including evaluators, safety evaluations, and explanation tooling
    • Implement auditing through trace logging, provenance metadata, and approval workflows
    • Govern agent behavior with oversight modes, constraints, and tool-access controls
  5. Deploy and call models from code with the Foundry SDK

    Coming

    • Deploy and consume LLMs, small models, code models, and multimodal models
    • Integrate generative workflows into applications by using Foundry SDKs and connectors
  6. RAG on Azure: an app that answers from your documents

    Coming

    • Implement retrieval-augmented generation (RAG) in an application
    • Design workflows, tool-augmented flows, and multistep reasoning pipelines
  7. Evaluate it: fabrications, relevance, quality, safety

    Coming

    • Evaluate models and apps, including detecting fabrications, relevance, quality, and safety
    • Apply responsible AI instrumentation, including evaluators, safety evaluations, and explanation tooling
  8. Your first agent: role, tools, memory

    Coming

    • Define agent roles, goals, conversation-tracking approach, and tool schemas
    • Build agents that integrate retrieval, function-calling, and conversation memory
  9. Agent tools: APIs, knowledge, search, custom functions

    Coming

    • Integrate agent tools, including APIs, knowledge stores, search, content understanding, and custom functions
    • Connect retrieval pipelines directly to workflows and agent tools
  10. Multi-agent orchestration and approval flows

    Coming

    • Implement orchestrated multi-agent solutions
    • Build autonomous or semiautonomous workflows with safeguards and approval flow controls
    • Govern agent behavior with oversight modes, constraints, and tool-access controls
  11. Tracing, token analytics and tuning

    Coming

    • Tune generation behavior, such as prompt engineering and adjusting model parameters
    • Implement model reflection, chain-of-thought evaluations, and self-critique loops
    • Set up observability by implementing tracing, token analytics, safety signals, and latency breakdowns
    • Orchestrate multiple models, flows, or hybrid LLM and rules engines
    • Integrate monitoring into deployed agents, evaluate agent behavior, and perform error analysis
  12. Generate and edit images and video

    Coming

    • Implement a solution that generates images from text prompts and reference media
    • Implement a solution that generates videos from text prompts and reference media
    • Configure image-editing workflows, including inpainting, mask‑based edits, and prompt‑driven modifications
    • Implement workflows to edit generated videos
    • Select and apply appropriate generation and editing controls provided by the platform
  13. Read images and video: captions, visual questions, Content Understanding

    Coming

    • Build a solution that analyzes visual context by using multimodal models
    • Configure apps to produce concise or detailed captions for single or multiple images
    • Implement a solution that enables question‑answering grounded in visual evidence
    • Configure generation of alt‑text and extended image descriptions aligned to accessibility guidelines
    • Implement visual understanding by configuring Azure Content Understanding in Foundry Tools to extract visual characteristics
    • Implement video analysis workflows to process and interpret video segments
    • Configure single‑task and pro‑mode Content Understanding pipelines
    • Implement solutions that identify objects, components, or regions within images or video
    • Implement filters to classify unsafe or disallowed visual content
    • Detect and mitigate indirect prompt injection by using embedded text in images
    • Enforce visual policy rules, such as applying watermarks, flagging prohibited symbols, upholding brand usage requirements, and detecting potentially inappropriate content
  14. Entities, summaries, structured JSON, sentiment, translation

    Coming

    • Implement solutions to extract entities, topics, summaries, and structured JSON outputs by using generative prompting and Foundry Tools
    • Configure detection of sentiment, tone, safety issues, and sensitive content
    • Build solutions that translate text by using Azure Translator in Foundry Tools or LLM‑powered translation flows
    • Customize language model outputs for domain tasks, such as compliance summarization and domain extraction
  15. Speech to text, text to speech, speech as an agent's input

    Coming

    • Implement workflows to convert speech to text and text to speech for agentic interactions
    • Integrate speech as an agent modality, including custom speech models
    • Enable multimodal reasoning from audio inputs
    • Translate speech into other languages by using language models and Foundry Tools
  16. Index anything: vector, hybrid and semantic search, skills, OCR

    Coming

    • Ingest and index content, such as documents, images, audio, and video
    • Configure semantic search, hybrid search, and vector search for grounding
    • Implement enrichment by using custom or built-in skills for text, images, and layout
    • Configure RAG ingestion flow, including documents and using optical character recognition (OCR)
  17. Extract documents: OCR, layout, fields, analyzers

    Coming

    • Extract information by using multimodal pipelines that combine OCR, layout analysis, and field extraction
    • Produce clean, grounded representations to use with agents and RAG by using Content Understanding
    • Implement analyzers for generating structured or markdown outputs for downstream reasoning by using Content Understanding
  18. The exam itself: the sandbox, the practice assessment, a map of what you built

    Coming

    Every skill of the exam, pointed back to its episode and its code.

What comes with the course

Independent course. Not affiliated with or endorsed by Microsoft.