Retrieving Analysis Results in Azure Content Understanding
Short answer
Select the option that calls poller.result() to block and retrieve the completed analysis output.
Question
You are developing an application that analyze invoices by using Azure Content Understanding in Foundry Tools.
You need to ensure that the application retrieves the analysis results after processing completes.
How should you complete the Python code? To answer, select the appropriate option in the answer area.
NOTE: Each correct selection is worth one point.

Key Takeaways
The question tests knowledge of async operations in Foundry; the common trap is trying to access results immediately without waiting, which leads to null or incomplete data.
This scenario tests the correct method for retrieving asynchronous analysis results from Azure Content Understanding. The solution requires using the polling mechanism to wait for the operation to complete before accessing the final data.
Common mistake: Learners often select methods that return immediate status without blocking, or they confuse the result retrieval method with the initiation method, failing to recognize that 'poller.result()' is the synchronous call to get the outcome.
Expert Analysis
Why the Answer Is Correct
In Azure Content Understanding (part of Foundry Tools), long-running tasks like invoice analysis are processed asynchronously. To retrieve the actual analysis results, you must use a poller object. The correct Python code pattern involves calling poller.result, which blocks execution until the operation succeeds or fails, ensuring the returned data is complete and valid.
Why Other Candidate Answers Are Wrong
Alternative options likely include methods that only check status (like .status) or methods intended for initiating the job rather than retrieving its output. Accessing results before the operation completes would yield empty or intermediate data, defeating the purpose of the analysis step.
Community Comment Notes
Community consensus strongly supports the use of poller.result. As one commenter noted, this method "keeps waiting for success or fail," accurately describing the blocking behavior necessary for reliable data retrieval in async workflows.
Exam Strategy
When working with AI services in Foundry that process documents or images, always look for async/poller patterns. Remember that heavy processing jobs require you to explicitly wait for completion using the appropriate result retrieval method.
Frequently Asked Questions
Why can't I access results immediately after starting the analysis?
What does poller.result() do in Foundry Tools?
Discussion 2 contributions
Compiled from public community threads and reader submissions, lightly edited for clarity. Handles and vote tallies are shown as recorded, and comments reflect the views of individual contributors.
From public community threads 2
-
arunAI901 👍 1wait. Why: begin_analyze() returns a poller for the asynchronous analysis operation. wait() waits until processing is complete, after which the analysis results can be retrieved.
-
Sr18 👍 1result is correct answer as 'poller.result' keeps waiting for success or fail
Reader comments & corrections
No reader corrections yet — spotted an error or have a note? Share it below.
Related Analysis
Practice All AI-901 Questions
Access 105 questions with complete answers and detailed explanations.
View Full AI-901 Practice Test →