Amazon
Avaya
Cisco
CompTIA
CrowdStrike
EC-Council
EXIN
Fortinet
Google
ISC
ISC2
ITIL
Juniper
Microsoft
NVIDIA
Okta
Palo Alto Networks
Salesforce
SAP
ServiceNow
All Vendors

Databricks Certified Generative AI Engineer Associate Certified Generative AI Engineer Associate Dumps in PDF

Free Databricks Certified Generative AI Engineer Associate Real Questions (page: 3)

Certified Generative AI Engineer Associate PDF — 92 Questions

A Generative AI Engineer has a provisioned throughput model serving endpoint as part of a RAG

application and would like to monitor the serving endpoint's incoming requests and outgoing responses. The current approach is to include a micro-service in between the endpoint and the user interface to write logs to a remote server.

Which Databricks feature should they use instead which will perform the same task?

  1. Vector Search
  2. Lakeview
  3. DBSQL
  4. Inference Tables

Answer(s): D

Explanation:

Problem Context: The goal is to monitor the serving endpoint for incoming requests and outgoing responses in a provisioned throughput model serving endpoint within a Retrieval-Augmented Generation (RAG) application. The current approach involves using a microservice to log requests and responses to a remote server, but the Generative AI Engineer is looking for a more streamlined solution within Databricks.

Explanation of Options:

Option A: Vector Search: This feature is used to perform similarity searches within vector databases. It doesn't provide functionality for logging or monitoring requests and responses in a serving endpoint, so it's not applicable here.

Option B: Lakeview: Lakeview is not a feature relevant to monitoring or logging request-response cycles for serving endpoints. It might be more related to viewing data in Databricks Lakehouse but doesn't fulfill the specific monitoring requirement.

Option C: DBSQL: Databricks SQL (DBSQL) is used for running SQL queries on data stored in Databricks, primarily for analytics purposes. It doesn't provide the direct functionality needed to monitor requests and responses in real-time for an inference endpoint.

Option D: Inference Tables: This is the correct answer. Inference Tables in Databricks are designed to store the results and metadata of inference runs. This allows the system to log incoming requests and outgoing responses directly within Databricks, making it an ideal choice for monitoring the behavior of a provisioned serving endpoint. Inference Tables can be queried and analyzed, enabling easier monitoring and debugging compared to a custom microservice.

Thus, Inference Tables are the optimal feature for monitoring request and response logs within the Databricks infrastructure for a model serving endpoint.



A Generative Al Engineer is tasked with improving the RAG quality by addressing its inflammatory outputs.

Which action would be most effective in mitigating the problem of offensive text outputs?

  1. Increase the frequency of upstream data updates
  2. Inform the user of the expected RAG behavior
  3. Restrict access to the data sources to a limited number of users
  4. Curate upstream data properly that includes manual review before it is fed into the RAG system

Answer(s): D

Explanation:

Addressing offensive or inflammatory outputs in a Retrieval-Augmented Generation (RAG) system is critical for improving user experience and ensuring ethical AI deployment. Here's why D is the most effective approach:

Manual data curation: The root cause of offensive outputs often comes from the underlying data used to train the model or populate the retrieval system. By manually curating the upstream data and conducting thorough reviews before the data is fed into the RAG system, the engineer can filter out harmful, offensive, or inappropriate content.

Improving data quality: Curating data ensures the system retrieves and generates responses from a high-quality, well-vetted dataset. This directly impacts the relevance and appropriateness of the outputs from the RAG system, preventing inflammatory content from being included in responses.

Effectiveness: This strategy directly tackles the problem at its source (the data) rather than just mitigating the consequences (such as informing users or restricting access). It ensures that the system consistently provides non-offensive, relevant information.

Other options, such as increasing the frequency of data updates or informing users about behavior expectations, may not directly mitigate the generation of inflammatory outputs.



A Generative Al Engineer is creating an LLM-based application. The documents for its retriever have been chunked to a maximum of 512 tokens each. The Generative Al Engineer knows that cost and latency are more important than quality for this application. They have several context length levels to choose from.

Which will fulfill their need?

  1. context length 514; smallest model is 0.44GB and embedding dimension 768
  2. context length 2048: smallest model is 11GB and embedding dimension 2560
  3. context length 32768: smallest model is 14GB and embedding dimension 4096
  4. context length 512: smallest model is 0.13GB and embedding dimension 384

Answer(s): D

Explanation:

When prioritizing cost and latency over quality in a Large Language Model (LLM)-based application, it is crucial to select a configuration that minimizes both computational resources and latency while still providing reasonable performance. Here's why D is the best choice:

Context length: The context length of 512 tokens aligns with the chunk size used for the documents

(maximum of 512 tokens per chunk). This is sufficient for capturing the needed information and generating responses without unnecessary overhead.

Smallest model size: The model with a size of 0.13GB is significantly smaller than the other options. This small footprint ensures faster inference times and lower memory usage, which directly reduces both latency and cost.

Embedding dimension: While the embedding dimension of 384 is smaller than the other options, it is still adequate for tasks where cost and speed are more important than precision and depth of understanding.

This setup achieves the desired balance between cost-efficiency and reasonable performance in a latency-sensitive, cost-conscious application.



A small and cost-conscious startup in the cancer research field wants to build a RAG application using Foundation Model APIs.

Which strategy would allow the startup to build a good-quality RAG application while being cost- conscious and able to cater to customer needs?

  1. Limit the number of relevant documents available for the RAG application to retrieve from
  2. Pick a smaller LLM that is domain-specific
  3. Limit the number of queries a customer can send per day
  4. Use the largest LLM possible because that gives the best performance for any general queries

Answer(s): B

Explanation:

For a small, cost-conscious startup in the cancer research field, choosing a domain-specific and smaller LLM is the most effective strategy. Here's why B is the best choice:

Domain-specific performance: A smaller LLM that has been fine-tuned for the domain of cancer research will outperform a general-purpose LLM for specialized queries. This ensures high-quality responses without needing to rely on a large, expensive LLM.

Cost-efficiency: Smaller models are cheaper to run, both in terms of compute resources and API usage costs. A domain-specific smaller LLM can deliver good quality responses without the need for the extensive computational power required by larger models.

Focused knowledge: In a specialized field like cancer research, having an LLM tailored to the subject matter provides better relevance and accuracy for queries, while keeping costs low. Large, general- purpose LLMs may provide irrelevant information, leading to inefficiency and higher costs.

This approach allows the startup to balance quality, cost, and customer satisfaction effectively, making it the most suitable strategy.



A Generative Al Engineer is responsible for developing a chatbot to enable their company's internal HelpDesk Call Center team to more quickly find related tickets and provide resolution.
While creating the GenAI application work breakdown tasks for this project, they realize they need to start planning which data sources (either Unity Catalog volume or Delta table) they could choose for this application. They have collected several candidate data sources for consideration:

call_rep_history: a Delta table with primary keys representative_id, call_id. This table is maintained to calculate representatives' call resolution from fields call_duration and call start_time.

transcript Volume: a Unity Catalog Volume of all recordings as a *.wav files, but also a text transcript as *.txt files.

call_cust_history: a Delta table with primary keys customer_id, cal1_id. This table is maintained to calculate how much internal customers use the HelpDesk to make sure that the charge back model is consistent with actual service use.

call_detail: a Delta table that includes a snapshot of all call details updated hourly. It includes root_cause and resolution fields, but those fields may be empty for calls that are still active.

maintenance_schedule ­ a Delta table that includes a listing of both HelpDesk application outages as well as planned upcoming maintenance downtimes.

They need sources that could add context to best identify ticket root cause and resolution.

Which TWO sources do that? (Choose two.)

  1. call_cust_history
  2. maintenance_schedule
  3. call_rep_history
  4. call_detail
  5. transcript Volume

Answer(s): D,E

Explanation:

In the context of developing a chatbot for a company's internal HelpDesk Call Center, the key is to select data sources that provide the most contextual and detailed information about the issues being addressed. This includes identifying the root cause and suggesting resolutions. The two most appropriate sources from the list are:

Call Detail (Option D):

Contents: This Delta table includes a snapshot of all call details updated hourly, featuring essential fields like root_cause and resolution.

Relevance: The inclusion of root_cause and resolution fields makes this source particularly valuable, as it directly contains the information necessary to understand and resolve the issues discussed in the calls. Even if some records are incomplete, the data provided is crucial for a chatbot aimed at speeding up resolution identification.

Transcript Volume (Option E):

Contents: This Unity Catalog Volume contains recordings in .wav format and text transcripts in .txt files.

Relevance: The text transcripts of call recordings can provide in-depth context that the chatbot can analyze to understand the nuances of each issue. The chatbot can use natural language processing techniques to extract themes, identify problems, and suggest resolutions based on previous similar interactions documented in the transcripts.

Why Other Options Are Less Suitable:

A (Call Cust History): While it provides insights into customer interactions with the HelpDesk, it focuses more on the usage metrics rather than the content of the calls or the issues discussed.

B (Maintenance Schedule): This data is useful for understanding when services may not be available but does not contribute directly to resolving user issues or identifying root causes.

C (Call Rep History): Though it offers data on call durations and start times, which could help in assessing performance, it lacks direct information on the issues being resolved.

Therefore, Call Detail and Transcript Volume are the most relevant data sources for a chatbot designed to assist with identifying and resolving issues in a HelpDesk Call Center setting, as they provide direct and contextual information related to customer issues.



PDF
Viewing page 3 of 10

Share your comments for Databricks Certified Generative AI Engineer Associate exam with other users:

A
AI Tutor Explanation
5/7/2026 11:34:48 PM

As an administrator for this subscription, you have been tasked with recommending a solution that prohibits users from copying corporate information from managed applications installed on unmanaged devices. Which of the following should you recommend? Windows Virtual Desktop. Microsoft Intune. Windows AutoPilot. Azure AD Application Proxy.

  • Microsoft Intune

Reason: Intune can enforce app protection policies (MAM) on managed apps, even on unmanaged devices, to prevent data leakage (e.g., restricting copy/paste, saving to non-approved apps, etc.). The other options don’t address data protection within apps on unmanaged devices.

Oslo, Norway
A
AI Tutor Explanation
5/4/2026 2:43:10 AM

Question 34:

  • Question 34 asks: Which role(s) has the capability to create Policies? Choose two.
  • Likely correct roles: Compliance Manager and Compliance admin (A and B). These roles typically have policy governance rights to create and manage policies.
  • Why not the others: Compliance User is usually a limited user, not allowed to create policies. Risk Manager focuses on risks, not policy creation in standard setups.
  • Note on the provided key: The answer shown is “C” (Compliance User), which conflicts with “Choose two.” This is probably a key error. In practice, verify against your instance’s ACLs or official docs.
  • Quick check tip: In ServiceNow, review the ACLs and role permissions for the Policy records to see which roles can create policies.

New Delhi, India
A
AI Tutor Explanation
4/29/2026 11:59:58 PM

function of appnav in sdwan

  • AppNav (Application Navigation) is the Cisco SD-WAN feature that provides application-level visibility and control.
  • It maintains a catalog of applications (AppIDs) with attributes (ports/protocols, categories) and classifies traffic accordingly.
  • It allows policy authors to reference apps by name in policies, enabling application-aware routing, QoS, and service chaining based on the app’s requirements.
  • The SD-WAN fabric uses AppNav data to steer traffic along the best path, improving user experience for critical apps while optimizing WAN usage.

Sydney, Australia
A
AI Tutor Explanation
4/29/2026 5:25:25 AM

Question 1:

  • Correct answer: C. Extract the hardware ID information of each computer to a CSV file and upload the file from the Microsoft Intune admin center.

  • Why this is correct

Durban, South Africa
A
AI Tutor Explanation
4/29/2026 5:23:14 AM

Question 5:

  • Correct answer: A. User4 and User1 only

  • Why this is correct:
- The Automatic Enrollment setting in Intune has MDM user scope: GroupA. Only users in GroupA can enroll devices via MDM auto-enrollment. - Device6 will be enrolled via Windows Autopilot and Intune, so enrollment is allowed only for users in GroupA. - Based on the group memberships in the scenario, User4 and User1 are in GroupA, while User2 and User3 are not. Therefore only User4 and User1 can enroll Device6.
  • Quick tip for the exam:
- Remember: MDM user scope determines who can auto-enroll devices; MAM scope controls app protection enrollment. When a new Autopilot device is enrolled, the signing-in user must be in the MDM scope.

Durban, South Africa
A
AI Tutor Explanation
4/29/2026 5:17:10 AM

Why this is correct

  • Correct answer: C. Extract the hardware ID information of each computer to a CSV file and upload the file from the Microsoft Intune admin center.

  • Why this is correct:
- Windows Autopilot requires devices to be registered by their hardware IDs (hash) before Autopilot can deploy Windows 10 Enterprise. - Collect the hardware IDs from the new Phoenix machines, save them in a CSV, and upload that CSV in the Intune/Windows Autopilot area. This maps each device to an Autopilot deployment profile. - After registration, you can assign Autopilot profiles (Windows 10 Enterprise, etc.). Other options (serial number CSV, generalizing, or Mobility settings) are not the initial Autopilot registration steps.

Durban, South Africa
A
AI Tutor Explanation
4/25/2026 1:53:46 PM

Question 7:

  • Correct answer: B — A risk score is computed based on the number of remediations needed compared to the industry peer average.

Explanation:
  • Risk360 uses a remediation-based score. It benchmarks how many actions are required to fix issues against peers, giving a relative risk posture.
  • Why not the others:
- A: Not just total risk events by location. - C: Time to mitigate isn’t the primary scoring method. - D: Not a four-stage breach scoring approach.
Note: The page text shows a mismatch (it lists D as the answer), but the study guide describes the remediation-based scoring (B) as the correct concept.

New Delhi, India
A
AI Tutor Explanation
4/25/2026 1:42:20 PM

Question 104:

  • Correct answer: D) Multi-Terabyte (TB) Range

  • Brief explanation:
- clustering keys organize data into micro-partitions to improve pruning when queries filter on those columns. - The performance benefit is most significant for very large tables; for small tables the overhead of maintaining clustering outweighs gains. - Therefore, as a best practice, define clustering keys on tables at the TB scale.

Thane, India
C
Community Helper
4/25/2026 2:03:10 AM

Q23: Fabric Admin is correct. Because Domain admin cannot create domains. Only Fabric Admin can among the given options. Q51: Wrapping @pipeline.parameter.param1 inside {} will return a string. But question requires the expression to return Int, so correct answer should be @pipeline.parameter.param1 (no {})

New Delhi, India
A
AI Tutor Explanation
4/23/2026 3:07:03 PM

Question 62:

  • Correct answer: D (per the page)

  • Note: The explanation text on the page describes option B (use ZDX score and Analyze Score to trigger the Y Engine analysis), indicating a mismatch between the stated answer and the rationale.

  • Key concept: For fast root-cause analysis, leverage telemetry and auto-correlated insights:
- Use the user’s ZDX score for AWS and run Analyze Score to activate the Y Engine, which correlates metrics across network, client, and application to pinpoint the issue quickly.
  • Why the other options are less effective:
- A: Only checks for outages; doesn’t provide actionable root-cause analysis. - C: Deep Trace helps visibility but is manual and time-consuming. - D: Packet capture is invasive and slow; not the quickest path to root cause.

Coimbatore, India
A
AI Tutor Explanation
4/23/2026 12:26:21 PM

Question 32:

  • Answer: A (2.4GHz)

  • Why: Lower-frequency signals have longer wavelengths and experience less attenuation when passing through walls and obstacles. Higher frequencies (5GHz, 6GHz) are more easily blocked by walls. NFC operates over very short distances and is not meant to penetrate walls. So 2.4 GHz best penetrates physical objects like walls.

Allen, United States
A
AI Tutor Explanation
4/21/2026 8:48:36 AM

Question 3:

  • False is the correct answer (Option B).

Why:
  • In Snowflake, a database is a metadata object that exists within a single Snowflake account. Accounts are isolated—there isn’t one database that lives in multiple accounts.
  • You can access data across accounts via data sharing or database replication, but these create separate database objects in the other accounts (e.g., a database in the consumer account created from a share), not a single shared database across accounts.

So a single database cannot exist in more than one Snowflake account.

Thane, India
A
Anonymous User
4/16/2026 10:54:18 AM

Question 1:

  • Correct answer: E — date = sys.argv[1]
  • Why this is correct:
- When a Databricks Job passes parameters to a notebook, those parameters are supplied to the notebook's Python process as command-line arguments. The first argument after the script name is sys.argv[1], so date = sys.argv[1] captures the passed date value directly.
  • How it compares to other options:
- date = spark.conf.get("date") reads from Spark config, not from job parameters. - input() waits for user input at runtime, which isn’t how job parameters are provided. - date = dbutils.notebooks.getParam("date") would work if the notebook were invoked via dbutils.notebook.run with parameters, not

Innisfil, Canada
A
Anonymous User
4/15/2026 4:42:07 AM

Question 528:

  • Correct answer: NSG flow logs for NSG1 (Option B)

  • Why:
- Traffic Analytics uses NSG flow logs to analyze traffic patterns. You must have NSG flow logs enabled for the NSGs you want to monitor. - An Azure Log Analytics workspace is also required to store and query the traffic data. - Network Watcher must be available in the subscription for traffic analytics to function.
  • What to configure (brief steps):
- Ensure Network Watcher is enabled in the East US region (for the subscription/region). - Enable NSG flow logs on NSG1. - Ensure a Log Analytics workspace exists and is accessible (read/write) so Traffic Analytics can store and query logs.
  • Why other options aren’t correct:
- “Diagnostic settings for VM1” or “Diagnostic settings for NSG1” alone don’t guarantee flow logs are captured and sent to Log Analytics, which Traffic Analytics relies on. - “Insights for VM1” is not how Traffic Analytics collects traffic data.

Hamburg, Germany
A
Anonymous User
4/15/2026 2:43:53 AM

Question 23:
The correct answer is Domain admin (option B), not Fabric admin.

  • Domain admin provides domain-level management: create domains/subdomains and assign workspaces within those domains, which matches the tasks while following least privilege.
  • Fabric admin is global-level access and is more privileges than needed for this scenario (it would grant broader control across the Fabric environment).

Kottayam, India
A
Anonymous User
4/14/2026 12:31:34 PM

Question 2:
For question 2, the key concept is the Longest Prefix Match. Routers pick the route whose subnet mask is the most specific (largest prefix length) that still matches the destination IP.
From the options:

  • A) 10.10.10.0/28 ? 10.10.10.0–10.10.10.15
  • B) 10.10.13.0/25 ? 10.10.13.0–10.10.13.127
  • C) 10.10.13.144/28 ? 10.10.13.144–10.10.13.159
  • D) 10.10.13.208/29 ? 10.10.13.208–10.10.13.215

The destination Host A’s IP must fall within 10.10.13.208–10.10.13.215 for the /29 to be the best match. Since /29 is the longest prefix among the matching options, Router1 will use 10.10.13.208/29.
Thus, the correct answer is D.

Canada
S
srameh
4/14/2026 10:09:29 AM

Question 3:

  • Correct answer: Phase 4, Post Accreditation

  • Explanation:
- In DITSCAP, the four phases are: - Phase 1: Definition (concept and requirements) - Phase 2: Verification (design and testing) - Phase 3: Validation (fielding and evaluation) - Phase 4: Post Accreditation (ongoing operations and lifecycle management) - The description—continuing operation of an accredited IT system and addressing changing threats throughout its life cycle—fits the Post Accreditation phase, which covers operations, maintenance, monitoring, and reauthorization as threats and environment evolve.

France
O
onibokun10
4/13/2026 7:50:14 PM

Question 129:
Correct answer: CNAME

  • A CNAME record creates an alias for a domain, so newapplication.comptia.org will resolve to whatever IP address www.comptia.org resolves to. This ensures both names point to the same resource without duplicating the IP.
  • Why not the others:
- SOA defines authoritative information for a zone. - MX specifies mail exchange servers. - NS designates name servers for a zone.
  • Notes: The alias name (newapplication.comptia.org) should not have other records if you use a CNAME for it, and CNAMEs aren’t used for the zone apex (root) domain. This scenario uses a subdomain, so a CNAME is appropriate.

Swindon, United Kingdom
A
Anonymous User
4/13/2026 6:29:58 PM

Question 1:

  • Correct answer: C

  • Why this is best:
- Uses OS Login with IAM, so SSH access is granted via Google accounts rather than distributing per-user SSH keys. - Granting the compute.osAdminLogin role to a Google group gives admin access to all team members in a centralized, auditable way. - Access is auditable: Cloud Audit Logs show who accessed which VM, satisfying the security requirement to determine who accessed a given instance.
  • How it works:
- Enable OS Login on the project/instances (enable-oslogin metadata). - Add the team’s

Germany
A
Anonymous User
4/13/2026 1:00:51 PM

Question 2:

  • Answer: D. Azure Advisor

  • Why: To view security-related recommendations for resources in the Compute and Apps area (including App Service Web Apps and Functions), you use Azure Advisor. Advisor surfaces personalized best-practice recommendations across resources, including security, and shows which resources are affected and the severity.

  • Why not the others:
- Azure Log Analytics is for ad-hoc querying of telemetry, not for viewing security recommendations. - Azure Event Hubs is for streaming telemetry data, not for security recommendations.
  • Quick tip: In the portal, navigate to Azure Advisor and check the Security recommendations for App Services to see actionable items and affe

    Brazil
D
Don
4/11/2026 5:36:42 AM

Recommend using AI for Solutions rather the Answer(s) submitted here

Hamburg, Germany
M
Mogae Malapela
4/8/2026 6:37:56 AM

This is very interesting

Gaborone, Botswana
A
Anon
4/6/2026 5:22:54 PM

Are these the same questions you have to pay for in ExamTopics?

Amsterdam, The Netherlands
L
LRK
3/22/2026 2:38:08 PM

For Question 7 - while the answer description indicates the correct answer, the option no. mentioned is incorrect. Nice and Comprehensive. Thankyou

Paris, France
R
Rian
3/19/2026 9:12:10 AM

This is very good and accurate. Explanation is very helpful even thou some are not 100% right but good enough to pass.

United States
G
Gerrard
3/18/2026 6:58:37 AM

The DP-900 exam can be tricky if you aren't familiar with Microsoft’s specific cloud terminology. I used the practice questions from free-braindumps.com and found them incredibly helpful. The site breaks down core data concepts and Azure services in a way that actually mirrors the real test. As a resutl I passed my exam.

United States
V
Vineet Kumar
3/6/2026 5:26:16 AM

interesting

Anonymous
J
Joe
1/20/2026 8:25:24 AM

Passed this exam 2 days ago. These questions are in the exam. You are safe to use them.

UNITED STATES
N
NJ
12/24/2025 10:39:07 AM

Helpful to test your preparedness before giving exam

Anonymous
A
Ashwini
12/17/2025 8:24:45 AM

Really helped

Anonymous
J
Jagadesh
12/16/2025 9:57:10 AM

Good explanation

INDIA
S
shobha
11/29/2025 2:19:59 AM

very helpful

INDIA
P
Pandithurai
11/12/2025 12:16:21 PM

Question 1, Ans is - Developer,Standard,Professional Direct and Premier

Anonymous
E
Einstein
11/8/2025 4:13:37 AM

Passed this exam in first appointment. Great resource and valid exam dump.

Anonymous
AI Tutor 👋 I’m here to help!