7.5 Exam Day Quick Reference

Key Takeaways

  • Logistics: 700/1000 to pass, ~100 minutes, about 40-60 questions, ~$165 USD; the AI-102 retires June 30, 2026 (11:59 PM CST).
  • Current six domains and weights: Plan/manage (20-25%), Generative AI (15-20%), Agentic solutions (5-10%), Computer Vision (10-15%), NLP (15-20%), Knowledge Mining & Information Extraction (15-20%).
  • Deprecated-to-current names: LUIS -> CLU, QnA Maker -> Custom Question Answering, Form Recognizer -> Document Intelligence, Cognitive Search -> AI Search; new Foundry branding (Microsoft Foundry, Content Understanding) is now in the objectives.
  • Security hierarchy (best to worst): managed identity > Entra ID service principal > keys in Key Vault > keys in env vars > keys in config files > hardcoded keys (never).
  • Content Safety uses a 0-7 scale with four categories (hate/fairness, sexual, violence, self-harm); Azure OpenAI requires its own dedicated resource and cannot be added to a multi-service Azure AI Services resource.
Last updated: June 2026

Quick Answer: Pass at 700/1000 in ~100 minutes. The exam was redesigned around Microsoft Foundry and now spans six domains. Lead with purpose-built services over generative ones, prefer managed identity, remember the 0-7 Content Safety scale, and note the exam retires June 30, 2026.

Exam Logistics (verified)

ItemValue
Passing score700 / 1000
Duration~100 minutes
Questions~40-60 (Microsoft does not publish a fixed count)
Cost~$165 USD (varies by region)
VendorMicrosoft (delivered via Pearson VUE / online proctor)
RetirementJune 30, 2026, 11:59 PM CST
RenewalFree online assessment on Microsoft Learn before expiry

Current Domain Weights (Dec 2025 / Foundry redesign)

DomainWeight
Plan and manage an Azure AI solution20-25%
Implement generative AI solutions15-20%
Implement an agentic solution5-10%
Implement computer vision solutions10-15%
Implement natural language processing solutions15-20%
Implement knowledge mining and information extraction15-20%

The December 23, 2025 redesign added the agentic domain (Foundry Agent Service, Microsoft Agent Framework, multi-agent orchestration) and reweighted the rest. If a practice resource still shows a "content moderation" domain or six-vs-five weightings from the old blueprint, it is stale.

Service Selection One-Liners

  • Text from images -> Vision Read (OCR)
  • Fields from forms/invoices -> Document Intelligence
  • Sentiment / NER / PII / key phrases -> Language
  • Custom intents + entities -> CLU
  • FAQ answers -> Custom Question Answering
  • Generate / summarize / chat -> Azure OpenAI
  • Image generation -> Azure OpenAI (DALL-E)
  • Search + AI enrichment -> AI Search
  • Text/image moderation -> Content Safety
  • Identity (1:1 / 1:N) -> Face (Limited Access)
  • Video insights -> Video Indexer
  • People counting -> Vision Spatial Analysis
  • Multimodal extraction -> Content Understanding

Security Hierarchy (best to worst)

  1. Managed identity — no secrets in code, auto-rotated tokens
  2. Entra ID service principal — token-based, rotatable
  3. Keys in Key Vault — centralized, audited
  4. Keys in environment variables — better than files
  5. Keys in config files — source-exposure risk
  6. Hardcoded keys — never acceptable

Critical Numbers

ItemValue
Passing score700 / 1000
Duration~100 minutes
Content Safety scale0-7 (text returns 0/2/4/6)
Content Safety categories4 (hate/fairness, sexual, violence, self-harm)
1 token~0.75 English words
GPT-4o context128K tokens
text-embedding-3-large dims3,072
Composed model componentsup to 100
Fine-tuning minimum examples~10 (more recommended)

Top Exam Traps

TrapCorrect answer
Use LUIS for intentsUse CLU (LUIS deprecated)
Use QnA MakerUse Custom Question Answering
API keys for production authUse managed identity
Public endpoints in productionUse private endpoints
Disable all content filtersCannot fully disable; tune per category
Content Safety scale is 0-10It is 0-7
Add Azure OpenAI to a multi-service resourceOpenAI needs a dedicated resource
Face emotion recognitionRetired
Translator on the standard endpointUses api.cognitive.microsofttranslator.com
Adjust temperature AND top_p togetherTune one, not both
Fine-tune for fresh knowledgeUse RAG for current facts

On the Exam: When two services could both work, pick the purpose-built one (cheaper, deterministic) unless the requirement is open-ended generation. When in doubt on auth, pick managed identity; when in doubt on knowledge freshness, pick RAG over fine-tuning.

Question Formats and Time Budgeting

With roughly 100 minutes for an expected 40-60 items, you have a little under two minutes per question on average — but the formats are uneven. Standard multiple-choice and multiple-response items are fast; spend your saved time on the slower ones. Drag-and-drop ordering items ask you to sequence steps (for example, the RAG pipeline order or the document-processing chain) — these reward the order-of-operations facts in section 7.4. Case studies bundle several questions behind one scenario; read the requirements and constraints carefully because a single phrase like "least cost" or "no secrets in code" decides multiple answers.

Some exams include a lab or repeated-answer-choice block. Flag anything uncertain and return to it; an unanswered question scores the same as a wrong one, so never leave a blank.

High-Frequency Fact Recall

These facts appear often enough to memorize verbatim. Azure OpenAI needs a dedicated resource (kind OpenAI) and cannot live inside a multi-service Azure AI Services resource. Content Safety is 0-7 with four categories. Translator uses api.cognitive.microsofttranslator.com and needs the region header with a multi-service key. The standard key header is Ocp-Apim-Subscription-Key, but Azure OpenAI key auth uses api-key. Face identification and Custom Neural Voice are Limited Access; Face emotion/age/gender are retired. A long-running operation returns 202 with Operation-Location.

429 means rate-limited — back off, do not rotate the key. Adjust temperature or top_p, not both. Use RAG for fresh facts, fine-tuning for style.

Final Decision Heuristics

When a question stalls you, apply these tie-breakers in order. (1) Match the verb to the purpose-built service before reaching for a generative one. (2) For authentication, climb the security hierarchy toward managed identity. (3) For networking, prefer private endpoints over public access. (4) For safety, never "disable" — tune thresholds, add blocklists, or insert human review. (5) For knowledge freshness, choose RAG; for response shape, consider fine-tuning. (6) For order-of-operations items, put safety screening on both the input (Prompt Shields) and the output (content filters) and place retrieval before generation.

(7) When two answers look correct, re-read the stem for the constraint phrase — "least effort", "lowest cost", "highest security", "offline" — that singles one out. These heuristics resolve the large majority of AI-102 scenario questions without any guesswork.

Test Your Knowledge

A production Azure AI application stores its API keys in environment variables, and a security review flags this. What is the recommended improvement?

A
B
C
D
Test Your Knowledge

According to the current Microsoft Foundry redesign of AI-102, which domain was newly added and carries the smallest weight?

A
B
C
D
Test Your Knowledge

Which statement about Azure OpenAI on the AI-102 exam is TRUE?

A
B
C
D
Test Your Knowledge

You must build one bot that answers HR FAQs and also processes structured leave-request actions. Which architecture is correct?

A
B
C
D
Congratulations!

You've completed this section

Continue exploring other exams