Revise Foundry agent creation, permissions, and integration instructions - #249
Open
v-vfarias wants to merge 27 commits into
Open
Revise Foundry agent creation, permissions, and integration instructions#249v-vfarias wants to merge 27 commits into
v-vfarias wants to merge 27 commits into
Conversation
Co-authored-by: Copilot <copilot@github.com>
…nt creation exercise Co-authored-by: Copilot <copilot@github.com>
…port Co-authored-by: Copilot <copilot@github.com>
Update requirements and improve agent configuration instructions
…d configuration settings
Revise agent creation and workflow instructions for Foundry
Revise Foundry agent creation and permissions instructions
…plementing a loop for multiple approval requests and updating related documentation.
…les and refine agent integration instructions
- Corrected variable names in evaluation instructions from `outputs` to `target` for consistency. - Changed output file handling in red team agent script to use a directory for results. - Updated requirements to specify the correct agent framework version.
… clarity and traceability
…nd consistency in setup
…n and red teaming tasks
Add the orchestration package required by the multi-agent lab and align the evaluation solution with target response mappings. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
v-vfarias
marked this pull request as ready for review
August 31, 2026 14:11
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request updates the instructions and starter code for the "Observe, evaluate, and secure your agents" lab to streamline agent setup, clarify Application Insights usage, and ensure consistency across all tasks. The changes unify the workflow so that all tasks use the same grounded agent, improve clarity around tracing (distinguishing between server-side and client-side traces), and update code and documentation to match the new approach.
Key changes include:
Unified agent workflow and documentation
caldova-knowledge-agent), eliminating the creation and deletion of separate test agents in Task 1. Instructions and code have been updated throughout to reflect this unified approach. [1] [2] [3] [4] [5]azdand clarify that every task uses the same agent. [1] [2] [3]Application Insights and tracing clarity
Code and environment changes
agent_referenceobject now includes bothnameandidfor trace correlation. [1] [2] [3] [4]Evaluation task improvements
${target.response}instead of${outputs.response}for clarity and correctness. [1] [2]These updates ensure a smoother, more consistent experience for users and make it easier to understand and correlate tracing data across Foundry and Application Insights.