Back to Prompt Library
implementation

Implement LangGraph Workflow and RAG

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: LangGraph Scientific Discovery Agent with Gemini 2.5 Pro Deep Think

Format
Text-first
Lines
1
Sections
1
Linked challenge
LangGraph Scientific Discovery Agent with Gemini 2.5 Pro Deep Think

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Implement the core LangGraph workflow using Python. Create nodes for literature review (integrating a vector database for RAG) and initial hypothesis generation. Ensure proper state management and the ability to retrieve and summarize relevant scientific papers based on a given research area. Use Gemini 2.5 Pro for synthesizing information from RAG results.

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.