Microsoft GH-300 Bundle

The action "Add path-specific instructions for the Python subtree" is useful when Python changes require lint rules different from the repository's TypeScript files. Scoped rules reduce irrelevant instructions on other files. Under the stated condition Copilot code review ignores a newly written instructions file, instead choose "Check supported path, branch, and review configuration". Instruction discovery is sensitive to file placement and review context.

The alternative "Create a reusable prompt file rather than permanent global guidance" fits another situation: A team wants a focused migration task reusable on demand. Prompt files are invoked for specific tasks rather than automatically everywhere. Here the condition is Copilot code review ignores a newly written instructions file; use "Check supported path, branch, and review configuration" instead. Instruction discovery is sensitive to file placement and review context.

The alternative "Add supported repository-wide Copilot instructions" addresses A team wants standing coding standards applied across Copilot interactions. Persistent instructions provide shared conventions without repeating each prompt. It does not resolve Copilot code review ignores a newly written instructions file; the correct choice is "Check supported path, branch, and review configuration". Instruction discovery is sensitive to file placement and review context.

For the different scenario A team tries to use Copilot review as the only required protected-branch reviewer, "Retain the organization's human-review and branch protection rules" could be appropriate. Automated suggestions do not satisfy independent governance by themselves. The present requirement is A pull request changes access checks and the team requests automated assistance, which calls for "Request Copilot code review, then have humans resolve and verify findings". AI review helps find issues but does not replace human approval.

"Request re-review of the updated pull request" targets A reviewer notices that an agent missed a new bug after a large follow-up commit. Substantial new changes can invalidate prior review observations. That differs from A pull request changes access checks and the team requests automated assistance; the required decision here is "Request Copilot code review, then have humans resolve and verify findings". AI review helps find issues but does not replace human approval.

The action "Reject or revise the suggestion based on test evidence" is useful when A Copilot comment proposes a fix that breaks a contract test. Review comments are hypotheses rather than guaranteed corrections. Under the stated condition A pull request changes access checks and the team requests automated assistance, instead choose "Request Copilot code review, then have humans resolve and verify findings". AI review helps find issues but does not replace human approval.

For the different scenario A pull request changes access checks and the team requests automated assistance, "Request Copilot code review, then have humans resolve and verify findings" could be appropriate. AI review helps find issues but does not replace human approval. The present requirement is A repository needs review guidance about secure API error handling, which calls for "Add relevant instructions for Copilot code review". Custom standards make automated feedback more context aware.

The action "Reject or revise the suggestion based on test evidence" is useful when A Copilot comment proposes a fix that breaks a contract test. Review comments are hypotheses rather than guaranteed corrections. Under the stated condition A repository needs review guidance about secure API error handling, instead choose "Add relevant instructions for Copilot code review". Custom standards make automated feedback more context aware.

The alternative "Retain the organization's human-review and branch protection rules" fits another situation: A team tries to use Copilot review as the only required protected-branch reviewer. Automated suggestions do not satisfy independent governance by themselves. Here the condition is A repository needs review guidance about secure API error handling; use "Add relevant instructions for Copilot code review" instead. Custom standards make automated feedback more context aware.

The action "Add relevant instructions for Copilot code review" is useful when A repository needs review guidance about secure API error handling. Custom standards make automated feedback more context aware. Under the stated condition A reviewer notices that an agent missed a new bug after a large follow-up commit, instead choose "Request re-review of the updated pull request". Substantial new changes can invalidate prior review observations.

The alternative "Retain the organization's human-review and branch protection rules" fits another situation: A team tries to use Copilot review as the only required protected-branch reviewer. Automated suggestions do not satisfy independent governance by themselves. Here the condition is A reviewer notices that an agent missed a new bug after a large follow-up commit; use "Request re-review of the updated pull request" instead. Substantial new changes can invalidate prior review observations.

The alternative "Request Copilot code review, then have humans resolve and verify findings" addresses A pull request changes access checks and the team requests automated assistance. AI review helps find issues but does not replace human approval. It does not resolve A reviewer notices that an agent missed a new bug after a large follow-up commit; the correct choice is "Request re-review of the updated pull request". Substantial new changes can invalidate prior review observations.

The action "Request re-review of the updated pull request" is useful when A reviewer notices that an agent missed a new bug after a large follow-up commit. Substantial new changes can invalidate prior review observations. Under the stated condition A Copilot comment proposes a fix that breaks a contract test, instead choose "Reject or revise the suggestion based on test evidence". Review comments are hypotheses rather than guaranteed corrections.

The alternative "Request Copilot code review, then have humans resolve and verify findings" addresses A pull request changes access checks and the team requests automated assistance. AI review helps find issues but does not replace human approval. It does not resolve A Copilot comment proposes a fix that breaks a contract test; the correct choice is "Reject or revise the suggestion based on test evidence". Review comments are hypotheses rather than guaranteed corrections.

For the different scenario A repository needs review guidance about secure API error handling, "Add relevant instructions for Copilot code review" could be appropriate. Custom standards make automated feedback more context aware. The present requirement is A Copilot comment proposes a fix that breaks a contract test, which calls for "Reject or revise the suggestion based on test evidence". Review comments are hypotheses rather than guaranteed corrections.

The alternative "Add relevant instructions for Copilot code review" fits another situation: A repository needs review guidance about secure API error handling. Custom standards make automated feedback more context aware. Here the condition is A team tries to use Copilot review as the only required protected-branch reviewer; use "Retain the organization's human-review and branch protection rules" instead. Automated suggestions do not satisfy independent governance by themselves.

The alternative "Request re-review of the updated pull request" addresses A reviewer notices that an agent missed a new bug after a large follow-up commit. Substantial new changes can invalidate prior review observations. It does not resolve A team tries to use Copilot review as the only required protected-branch reviewer; the correct choice is "Retain the organization's human-review and branch protection rules". Automated suggestions do not satisfy independent governance by themselves.

"Reject or revise the suggestion based on test evidence" targets A Copilot comment proposes a fix that breaks a contract test. Review comments are hypotheses rather than guaranteed corrections. That differs from A team tries to use Copilot review as the only required protected-branch reviewer; the required decision here is "Retain the organization's human-review and branch protection rules". Automated suggestions do not satisfy independent governance by themselves.

For the different scenario A Copilot answer quotes a Space page that does not justify the claim, "Open the cited document and validate the conclusion" could be appropriate. Retrieval references support verification but not automatic factual truth. The present requirement is An engineering team repeatedly explains the same design documents in separate chats, which calls for "Build an authorized Copilot Space containing relevant project context". Curated context can improve grounded answers across collaborators.

"Supply relevant repository or Space context to the question" targets A team wants guidance about a codebase beyond a single open editor file. Broader curated context can reveal dependencies missing from a local file. That differs from An engineering team repeatedly explains the same design documents in separate chats; the required decision here is "Build an authorized Copilot Space containing relevant project context". Curated context can improve grounded answers across collaborators.

The alternative "Update the referenced content and identify the current source of truth" fits another situation: A Space contains obsolete API specifications and produces incorrect guidance. Retrieval quality depends on freshness of curated materials. Here the condition is An engineering team repeatedly explains the same design documents in separate chats; use "Build an authorized Copilot Space containing relevant project context" instead. Curated context can improve grounded answers across collaborators.

"Supply relevant repository or Space context to the question" targets A team wants guidance about a codebase beyond a single open editor file. Broader curated context can reveal dependencies missing from a local file. That differs from A Space contains obsolete API specifications and produces incorrect guidance; the required decision here is "Update the referenced content and identify the current source of truth". Retrieval quality depends on freshness of curated materials.

The action "Build an authorized Copilot Space containing relevant project context" is useful when An engineering team repeatedly explains the same design documents in separate chats. Curated context can improve grounded answers across collaborators. Under the stated condition A Space contains obsolete API specifications and produces incorrect guidance, instead choose "Update the referenced content and identify the current source of truth". Retrieval quality depends on freshness of curated materials.

The alternative "Confirm sharing permissions and minimize the included materials" fits another situation: A user wants a Space to include sensitive documents from another team. Context organization does not authorize cross-team disclosure. Here the condition is A Space contains obsolete API specifications and produces incorrect guidance; use "Update the referenced content and identify the current source of truth" instead. Retrieval quality depends on freshness of curated materials.

The action "Build an authorized Copilot Space containing relevant project context" is useful when An engineering team repeatedly explains the same design documents in separate chats. Curated context can improve grounded answers across collaborators. Under the stated condition A user wants a Space to include sensitive documents from another team, instead choose "Confirm sharing permissions and minimize the included materials". Context organization does not authorize cross-team disclosure.

The alternative "Update the referenced content and identify the current source of truth" fits another situation: A Space contains obsolete API specifications and produces incorrect guidance. Retrieval quality depends on freshness of curated materials. Here the condition is A user wants a Space to include sensitive documents from another team; use "Confirm sharing permissions and minimize the included materials" instead. Context organization does not authorize cross-team disclosure.

For the different scenario A Copilot answer quotes a Space page that does not justify the claim, "Open the cited document and validate the conclusion" could be appropriate. Retrieval references support verification but not automatic factual truth. The present requirement is A user wants a Space to include sensitive documents from another team, which calls for "Confirm sharing permissions and minimize the included materials". Context organization does not authorize cross-team disclosure.

The alternative "Confirm sharing permissions and minimize the included materials" addresses A user wants a Space to include sensitive documents from another team. Context organization does not authorize cross-team disclosure. It does not resolve A Copilot answer quotes a Space page that does not justify the claim; the correct choice is "Open the cited document and validate the conclusion". Retrieval references support verification but not automatic factual truth.

For the different scenario A team wants guidance about a codebase beyond a single open editor file, "Supply relevant repository or Space context to the question" could be appropriate. Broader curated context can reveal dependencies missing from a local file. The present requirement is A Copilot answer quotes a Space page that does not justify the claim, which calls for "Open the cited document and validate the conclusion". Retrieval references support verification but not automatic factual truth.

"Update the referenced content and identify the current source of truth" targets A Space contains obsolete API specifications and produces incorrect guidance. Retrieval quality depends on freshness of curated materials. That differs from A Copilot answer quotes a Space page that does not justify the claim; the required decision here is "Open the cited document and validate the conclusion". Retrieval references support verification but not automatic factual truth.

The alternative "Open the cited document and validate the conclusion" addresses A Copilot answer quotes a Space page that does not justify the claim. Retrieval references support verification but not automatic factual truth. It does not resolve A team wants guidance about a codebase beyond a single open editor file; the correct choice is "Supply relevant repository or Space context to the question". Broader curated context can reveal dependencies missing from a local file.

"Build an authorized Copilot Space containing relevant project context" targets An engineering team repeatedly explains the same design documents in separate chats. Curated context can improve grounded answers across collaborators. That differs from A team wants guidance about a codebase beyond a single open editor file; the required decision here is "Supply relevant repository or Space context to the question". Broader curated context can reveal dependencies missing from a local file.

The action "Confirm sharing permissions and minimize the included materials" is useful when A user wants a Space to include sensitive documents from another team. Context organization does not authorize cross-team disclosure. Under the stated condition A team wants guidance about a codebase beyond a single open editor file, instead choose "Supply relevant repository or Space context to the question". Broader curated context can reveal dependencies missing from a local file.