What Is Microsoft Azure AI Apps and Agents Developer?

Overview

Microsoft Azure AI Apps and Agents Developer is a Microsoft credential. Prepare for Exam AI-103, which replaces AI-102, to build generative AI apps and agents on Microsoft Foundry. This PathKey™ guide summarizes the domains, format, cost signals, eligibility, and renewal pattern so you can decide before you book. Accumentum is an Army CA and Air Force COOL Approved Vendor. We teach preparation for the Microsoft exam. Microsoft sets exam content, fees, and policies.

Accumentum is an Army CA and Air Force COOL Approved Vendor. We teach preparation for the Microsoft exam. Microsoft sets exam content, fees, and policies.

Who it is for

• Azure AI engineers who build, manage, and deploy agents and AI solutions with Microsoft Foundry.
• Developers with Python experience who are moving from prebuilt Azure AI services (the AI-102 era) to Foundry apps and agents.
• People who collaborate with stakeholders, architects, data scientists, DevOps, and cloud security engineers on AI solutions.

Exam domains

Weights follow the official outline.

1. 01

   Choose Foundry services for generative AI and agents

   Choose an appropriate model for each task, including LLMs, small language models, multimodal models, and Foundry Tools, Choose Foundry services for generative tasks, grounding, vector search, agent workflows, or multimodal processing, and Choose an appropriate method for retrieval and indexing.

2. 02

   Set up AI solutions in Foundry

   Design Azure infrastructure for AI apps and agent-based solutions, Choose appropriate deployment options, and Configure model and agent deployments.

3. 03

   Manage, monitor, and secure AI systems

   Manage quotas, scaling, rate limits, and cost footprints for model and agent workloads, Monitor model performance, drift, safety events, and grounding quality, and Monitor data ingestion quality, search index health, and relevance performance.

4. 04

   Responsible AI across generative and agentic systems

   Configure safety filters, guardrails, risk detection, and content moderation, Apply responsible AI instrumentation, including evaluators, safety evaluations, and explanation tooling, and Implement auditing through trace logging, provenance metadata, and approval workflows.

5. 05

   Build generative applications with Foundry

   Deploy and consume LLMs, small models, code models, and multimodal models, Implement retrieval-augmented generation (RAG) in an application, and Design workflows, tool-augmented flows, and multistep reasoning pipelines.

6. 06

   Build agents with Foundry

   Define agent roles, goals, conversation tracking, and tool schemas, Build agents that integrate retrieval, function-calling, and conversation memory, and Integrate tools including APIs, knowledge stores, search, content understanding, and custom functions.

7. 07

   Optimize and operationalize generative AI systems

   Tune generation behavior with prompt engineering and model parameters, Implement model reflection, chain-of-thought evaluations, and self-critique loops, and Set up observability with tracing, token analytics, safety signals, and latency breakdowns.

8. 08

   Implement computer vision solutions

   Generate images and videos from text prompts and reference media, including inpainting and prompt-driven edits, Build multimodal understanding: captions, visual question-answering, alt-text, and Azure Content Understanding, and Implement video analysis and object or region identification.

9. 09

   Implement text analysis and speech solutions

   Extract entities, topics, summaries, and structured JSON using generative prompting and Foundry Tools, Detect sentiment, tone, safety issues, and sensitive content, then translate with Azure Translator or LLM-powered flows, and Speech-to-text and text-to-speech for agentic interactions, including custom speech models.

10. 10

    Implement information extraction solutions

    Ingest and index documents, images, audio, and video, Configure semantic, hybrid, and vector search for grounding, and Implement enrichment skills and RAG ingestion including OCR.

Exam format and cost

Questions

Confirm on the vendor site

Duration

Confirm on the vendor site

Format

Confirm question format on the vendor outline

Passing score

Confirm the passing score on the vendor site

Cost

Confirm the current exam fee on the vendor site before you register

Delivery

Pearson VUE test center or online where the vendor offers it

Languages

Confirm available languages on the vendor site

Experience and eligibility

Experience developing apps by using Python. Familiarity with general AI, generative AI, and Azure services.

Renewal

Renewal rules for Microsoft Azure AI Apps and Agents Developer are set by Microsoft. Many credentials use a multi-year cycle with continuing education, a renewal fee, or a newer exam. Confirm the current cycle on the vendor site.

Roles this credential fits

• Planning Foundry solutions, generative AI and agents, RAG, computer vision, text analysis, and information extraction. It does not follow the retired AI-102 Cognitive Services outline.
• AI Apps and Agents
• Teams standardizing on this credential for hiring or compliance

Official sources

• Microsoft credentials

Always confirm fees, dates, and eligibility on the vendor site before you register. Vendors change outlines and prices without notice.