Microsoft Azure AI-900 模擬診断
画像認識・NLP・責任あるAIの原則を5問でチェック。
Azure AI Fundamentals (AI-900) の700/1000合格基準に向けたシナリオ演習とサービス判別トレーニングを提供します。
採点基準ベースの添削と IT 認定診断。
上の試験ラボで回答を入力するか認定資格を選択してください。
上の試験ラボで回答を入力するか認定資格を選択してください。
アカウントにサインイン
Googleおよびメールログインに対応。入力中の下書きはサインイン後も保持されます。
Googleまたはメールで続行続行するにはサインインしてください。Microsoft Azure AI Fundamentals (AI-900) Simulator
Practice high-frequency Azure AI-900 distinctions across Computer Vision, Document Intelligence, NLP workloads, ML types, and Responsible AI.
Complete all 5 Azure AI-900 scenarios below to measure readiness against the 700/1000 passing standard.
An accounting department needs to automatically extract vendor names, line-item tables, and invoice totals from scanned supplier PDFs into JSON fields. Which Azure AI service fits best?
A logistics team has historical shipment records without any predefined category labels and wants to group warehouses automatically by similar order volume and return behavior. Which ML task applies?
Before launching a hiring-screen assistant, a company publishes clear documentation explaining what factors the model weights, its error rates across groups, and where human review is mandatory. Which Microsoft Responsible AI principle does this emphasize?
A compliance bot scans customer chats to automatically detect company names, dates, and street addresses, while masking personal phone numbers. Which Azure AI Language capabilities perform this?
A developer deploys a customer Q&A assistant in Azure AI Foundry and needs configurable severity thresholds (Low/Medium/High) to block hate or self-harm outputs before display. What handles this?
1. 任意:答案・問題シートを添付
学習用の画像(JPEG・PNG・WebP、各最大10MB)または上のテキストエディタをご利用ください。
How Azure AI-900 scoring criteria work
ExamAce AI evaluates every submission against weighted rubric-aligned categories rather than vague grammar tips. Review the exact criteria dimensions, target benchmarks, and weight distribution below so you know precisely which gaps cost the most points before sitting for your exam.
Applying Fairness, Inclusiveness, Transparency, Accountability, Reliability, and Privacy principles.
Distinguishing supervised regression/classification from unsupervised clustering.
Choosing Azure AI Vision OCR, Custom Vision object detection, and Document Intelligence.
Using Azure AI Language entity extraction, QnA, Translator, and Azure OpenAI content filters.
Step-by-step practice workflow
Follow this quick sequence to diagnose baseline gaps for free before deciding whether to spend credits on deep rubric analysis inside your account.
- IT資格タブでAzure AI-900を選択。
- 5問の診断シナリオに回答。
- 弱点分野と用語トラップの解説を確認。
Frequently asked questions
責任あるAIの分野も出題されますか?
はい。透明性や公平性などの重点項目を含んでいます。