Back to Prompt Library
implementation

Claude Agent with Retrieval Tool Implementation

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

Linked challenge: Agent for Complex Policy & Contract Analysis

Format
Text-first
Lines
1
Sections
1
Linked challenge
Agent for Complex Policy & Contract Analysis

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Initialize your **Claude Agent** using the **Claude Agents SDK** with **Claude Opus 4.1**. Define a custom tool (`retrieve_document_chunks(query: str) -> List[str]`) that queries your Weaviate instance and returns the top-k most relevant document chunks. The agent should be able to use this tool when asked to analyze a document or a specific legal concept. Provide the agent initialization code and the tool definition.

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.