Document the dynamic system_prompt pattern for common-ai agents#69636
Merged
gopidesupavan merged 2 commits intoJul 10, 2026
Merged
Conversation
kaxil
approved these changes
Jul 9, 2026
Lee-W
approved these changes
Jul 9, 2026
phanikumv
approved these changes
Jul 10, 2026
gopidesupavan
approved these changes
Jul 10, 2026
joshuabvarghese
pushed a commit
to joshuabvarghese/airflow
that referenced
this pull request
Jul 16, 2026
…ache#69636) * Document dynamic system_prompt pattern for common-ai agents * Address review nits in dynamic system_prompt example
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
5 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
system_promptonAgentOperator/LLMOperator(and@task.agent/@task.llm) is a templated field, but the provider docs only mention this in passing — there's no worked example showing it templated from an upstream task's XCom, a common pattern for tailoring an agent's instructions to an earlier classification.What
docs/operators/agent.rst, backed by a new example DAG function (example_agent_dynamic_system_prompt) inexample_dags/example_agent.pythat Jinja-templatessystem_promptfrom aclassifytask's XCom.seealsocross-reference indocs/operators/llm.rst, since@task.llmtemplatessystem_promptidentically.Was generative AI tooling used to co-author this PR?