Back to prompt library
Orchestrate Self-Improvement with Dagster and DeepEval
Linked challenge: Self-Improving GPT-5.3-Codex Agent for Code Generation & Refinement
Prompt source
implementation1 lines1 sectionsNo variables0 checklist items
Design a Dagster pipeline (`@job` and `@op` definitions) that orchestrates the iterative self-improvement loop of your agent. This pipeline should include steps for invoking the OpenAI agent to generate/refine code, executing tests via your custom tool, and then using DeepEval to analyze the test results and provide structured feedback to the agent for its next iteration. Show how DeepEval can assess aspects like code correctness and adherence to best practices. Provide Python code for the Dagster pipeline and DeepEval integration.