A travel AI agent books flights and hotels. The airline API returns 'departure_time' in 24-hour format ('14:30'), while the hotel API returns 'check_in_time' in 12-hour format ('2:30 PM'). The agent's itinerary builder requires all times in 24-hour format. What is the most appropriate action?

Aggregate the two time fields into one

Use direct mapping for both fields

Apply a transformation rule to the 'check_in_time' field

An e-commerce AI agent recommends products based on user behavior. The source data has a field 'user_id' (integer) and the target schema expects 'customer_id' (string). The values are otherwise identical. Which mapping strategy is most appropriate for this field?

Aggregation with a group-by operation

Direct mapping with a type conversion

Schema alignment with a new field

Transformation rule with a lookup table

What is the primary purpose of data transformation in an AI agent's input processing pipeline?

To encrypt all input data so that it cannot be read by external systems.

To convert raw input data into a format and structure that the agent can effectively process and understand.

To generate a backup copy of the input data for disaster recovery purposes.

To permanently delete any data that is not immediately useful to the agent.

What is a common way to handle format mismatches, such as dates in different formats, during data mapping?

Storing the data in its original format without any changes.

Encrypting the data to hide the format differences.

Deleting the records with mismatched formats.

Applying a transformation rule to standardize the format to a common representation.

How can data transformation help address missing values in input data for an AI agent?

By ignoring the missing values and proceeding with the remaining data.

By encrypting the missing values to protect them.

By imputing missing values with a default or calculated value.

By converting missing values to a different data type.

CiscoAI Technical Practitioner

Domain 6Objective 5

6.5 Describe Data Transformation and Mapping Within AI Agents AI-TECHNICAL-PRACTITIONER Practice Questions (Page 2)

Part of the Agentic AI domain, which accounts for 20% of the AI-TECHNICAL-PRACTITIONER exam. Cisco does not publish an official question count, but from its 60-minute exam (~25–40 total, ~5–8 in this domain), expect 1–2 from this objective — we provide 25 practice questions to prepare you well beyond it. (estimate)

25questions here

5free pages

6concepts

20%of the exam

Questions 6–10

6application · medium
A travel AI agent books flights and hotels. The airline API returns 'departure_time' in 24-hour format ('14:30'), while the hotel API returns 'check_in_time' in 12-hour format ('2:30 PM'). The agent's itinerary builder requires all times in 24-hour format. What is the most appropriate action?
Select an answer first
7application · medium
An e-commerce AI agent recommends products based on user behavior. The source data has a field 'user_id' (integer) and the target schema expects 'customer_id' (string). The values are otherwise identical. Which mapping strategy is most appropriate for this field?
Select an answer first
8foundation · easy
What is the primary purpose of data transformation in an AI agent's input processing pipeline?
Select an answer first
9foundation · easy
What is a common way to handle format mismatches, such as dates in different formats, during data mapping?
Select an answer first
10foundation · easy
How can data transformation help address missing values in input data for an AI agent?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to AI-TECHNICAL-PRACTITIONER

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Cisco. “AI-TECHNICAL-PRACTITIONER” is a trademark of its owner, used for identification only.