On this page
The short answer
- The real exam: 75 questions in 180 min, passing at 750 / 1000, for $300.
- 5 sample questions below, covering all 5 of the exam’s domains, each with its answer and why it’s right.
- They are original questions, written from AWS’s published outline. They aren’t copies of real exam questions, and we don’t publish those.
- For a score by domain, take the free 10-question practice test. Nothing to download: it runs in your browser.
The AIP-C01 exam at a glance
From our AWS Generative AI Developer Professional exam guide, which follows AWS’s own page and is checked every week. AWS hasn’t announced a retirement date for AIP-C01.
| AWS Generative AI Developer Professional (AIP-C01) | |
|---|---|
| Exam code | AIP-C01 |
| Level | Professional |
| Written for | AI Engineer |
| Questions | 75 |
| Time | 180 min |
| Passing score | 750 / 1000 |
| Cost | $300 |
| Recommended experience | 2+ years building on AWS, 1 with generative AI |
What the exam covers
The exam has 5 domains: Foundation Model Integration, Data Management, and Compliance (31%), Implementation and Integration (26%), AI Safety, Security, and Governance (20%), Operational Efficiency and Optimization for GenAI Applications (12%), Testing, Validation, and Troubleshooting (11%). Foundation Model Integration, Data Management, and Compliance is the largest, at 31%, so it deserves the largest share of your study time.
The sample questions below start with one from each domain in turn, so you can see how each is asked.
5 sample questions, with answers
Answer each one before you open its answer. If you get it right for the wrong reason, count it as wrong: the explanation matters more than the letter.
Question 1 · Foundation Model Integration, Data Management, and Compliance
An app should switch to better foundation models as they arrive, without code changes. What design helps?
- AHard-code one model ID in every function
- BFine-tune a new model every week
- CRead the model ID from configuration
- DCall each provider’s SDK directly everywhere
Show the answer
C. Read the model ID from configuration
Keeping the model ID in configuration, such as AWS AppConfig, behind one interface lets teams switch models without redeploying. Hard-coding or scattering provider calls makes switching costly.
Question 2 · Implementation and Integration
Which open-source SDK from AWS builds an agent from a model, tools and a prompt in a few lines of code?
- AAWS CDK constructs
- BStrands Agents
- CAWS SAM templates
- DAWS Amplify Gen 2
Show the answer
B. Strands Agents
Strands Agents is AWS’s open-source, model-driven SDK for building agents; the exam guide also names AWS Agent Squad for multi-agent systems. CDK and SAM define infrastructure, and Amplify builds web apps.
Question 3 · AI Safety, Security, and Governance
A chatbot must block hate speech in user input and mask personal data in its answers. What should the team configure?
- AAWS WAF rate rules alone
- BAmazon CloudFront caching
- CAmazon Bedrock Guardrails
- DAWS Backup vault plans
Show the answer
C. Amazon Bedrock Guardrails
Guardrails apply content filters, denied topics, word filters and sensitive-information redaction to inputs and outputs. WAF rate rules, caching and backups don’t inspect content.
Question 4 · Operational Efficiency and Optimization for GenAI Applications
Many users ask nearly the same questions, and every answer costs a model call. What cuts both cost and latency?
- AA larger context window per call
- BA higher temperature setting
- CLonger system prompts for each call
- DSemantic caching of answers
Show the answer
D. Semantic caching of answers
A semantic cache returns a stored answer when a new question is close in meaning to an earlier one, skipping the model call. Bigger contexts and longer prompts add tokens, and temperature changes randomness, not cost.
Question 5 · Testing, Validation, and Troubleshooting
A team wants to compare two models on its own prompts, including LLM-as-a-judge scoring. What should it use?
- AAmazon Bedrock model evaluation
- BAWS Cost Explorer reports
- CAmazon Inspector findings
- DAWS Config compliance rules
Show the answer
A. Amazon Bedrock model evaluation
Bedrock evaluations score models or RAG setups on your own datasets, with automatic metrics, LLM-as-a-judge or human review. Cost Explorer, Inspector and Config don’t judge output quality.
How to use practice questions
Test before you study. A short test at the start shows which domains you already know, so you don’t spend a week on them.
Read every explanation, including the ones for questions you got right. Most exam questions turn on one detail in the scenario, and the explanation names it.
Then go full length. A few questions check your understanding; they don’t tell you whether you can hold your attention for 180 min. Before you book, sit full, timed practice exams until you pass them comfortably more than once.
Practice exams, downloads and dumps
You don’t need to download anything to practice. Our practice test is free and runs in the browser, on a phone or a computer.
Dumps are a different thing: collections sold or shared as the “real” exam questions. We don’t publish or link to them. They are taken from the exam in breach of the agreement every candidate accepts, they go out of date when AWS refreshes its questions, and nobody stands behind their answers.
There is also a plainer reason. An exam is a sample of what the job needs. If you memorize the sample, you pass without the knowledge, and the first week of work shows it.
What to do next
Take the practice test, note your weakest domain, and build your study time around it.