dc dotCreds
Microsoft comparison guide

AI-103 vs AI-102: Azure AI apps, agents, Foundry, and classic Azure AI engineering

AI-103 is now the cleaner study target for Microsoft Azure AI apps and agents. AI-102 retired on June 30, 2026, and Microsoft Partner Center says Azure AI Apps and Agents Developer Associate (AI-103) replaced Azure AI Engineer Associate (AI-102) on June 19, 2026.

Replacement path Microsoft Learn sources AI-102 retired Last reviewed: July 22, 2026

Accuracy note: AI-102 is now a legacy comparison target. New study should point at AI-103 unless you are reviewing an already-earned AI-102 credential.

What Microsoft officially says right now

Microsoft Learn lists AI-102 under recently retired exams with a June 30, 2026 retirement date and says recently retired exams can no longer be taken. Microsoft Partner Center says Azure AI Engineer Associate (AI-102) retired as of June 30, 2026 and was replaced by Azure AI Apps and Agents Developer Associate (AI-103) on June 19, 2026. AI-103 is now the practical study path for new Azure AI apps and agents learners.

Quick answer table
TopicAI-103AI-102
StatusCurrent Azure AI apps and agents pathRetired on June 30, 2026
AudienceAzure AI engineers building, managing, and deploying agents and AI solutions that use Microsoft FoundryAzure AI engineers building, managing, and deploying AI solutions across development, deployment, integration, maintenance, tuning, and monitoring
Language expectationOfficial page specifically calls out Python experienceOfficial study guide says candidates can use languages such as Python and C# plus REST APIs and SDKs
Skills emphasisPlan and manage Azure AI, implement generative AI and agentic solutions, plus vision, text analysis, and information extractionPlan and manage Azure AI, implement generative AI, implement an agentic solution, plus vision, NLP, and knowledge mining or information extraction
Agent focusHigher: generative AI and agentic solutions are 30-35% of the examLower but still present: generative AI is 15-20% and agentic solutions are 5-10%
Practice linkAI-103 practiceAI-102 legacy practice
Choose AI-103 now

The official Microsoft Learn page says AI-103 validates expertise in designing, developing, and deploying advanced Azure AI solutions using Python and Microsoft Foundry. The study guide says the audience builds, manages, and deploys agents and AI solutions that take advantage of Microsoft Foundry, and the largest skill block is implementing generative AI and agentic solutions. Start with the AI-103 guide or jump into practice.

Use AI-102 only for legacy review

AI-102 still helps explain the classic Azure AI Engineer Associate lane, including broader Azure AI solution delivery, natural language processing, knowledge mining, information extraction, REST APIs, SDKs, Python, and C#. But the exam retired on June 30, 2026, so AI-102 practice should be treated as legacy review, not a new certification target.

What is the real difference in exam feel?

AI-103 reads like the newer Foundry-centered apps-and-agents lane. AI-102 reads like the broader retired Azure AI engineer lane that still includes generative AI and agents but keeps more weight on natural language processing, knowledge mining, and classic service implementation breadth. If your day-to-day work is drifting toward agents, orchestration, grounding, and newer Foundry-first delivery, AI-103 is the cleaner topical fit.

Suggested decision path
Practice on dotCreds
Use AI-103 when your study map is Foundry and agents. Treat AI-102 as legacy review now that the exam has retired.

The daily practice pages are the fastest way to feel the difference in emphasis before you spend more study time.

Related pages

AI-103 guide

Azure AI apps and agents, Foundry, retrieval, tools, orchestration, safety, and monitoring.

AI-103 vs GH-600

Compare Azure AI apps and agents against the GitHub agentic AI developer lane.

FAQ

Does AI-103 replace AI-102?

Yes for the practical Microsoft credential path. Microsoft Partner Center says Azure AI Engineer Associate (AI-102) retired as of June 30, 2026 and was replaced by Azure AI Apps and Agents Developer Associate (AI-103) on June 19, 2026.

Should I choose AI-103 or AI-102 right now?

Choose AI-103 for new Azure AI apps and agents study. AI-102 can no longer be taken after its June 30, 2026 retirement date.

Is AI-103 the current path?

Yes. Microsoft Learn describes Azure AI Apps and Agents Developer Associate as the credential for designing, developing, and deploying advanced Azure AI solutions using Python and Microsoft Foundry.

When did AI-102 retire?

AI-102 retired on June 30, 2026. Microsoft Learn lists it under recently retired exams and says recently retired exams can no longer be taken.

Which exam is more focused on agents?

AI-103 is the agent-forward path: Microsoft Learn describes the role as building, managing, and deploying agents and AI solutions that use Microsoft Foundry.

Which exam is broader in classic Azure AI service coverage?

AI-102 is broader across NLP, speech, knowledge mining, and older Azure AI service implementation patterns.

Sources
Trademark notice

Microsoft, Azure, and related exam names are trademarks of Microsoft. dotCreds is not affiliated with Microsoft.