Back to Prompt Library
implementation

Integrating Semantic Search with Weaviate as a Tool

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

Linked challenge: Misinformation Debunking Team

Format
Text-first
Lines
2
Sections
2
Linked challenge
Misinformation Debunking Team

Prompt source

Original prompt text with formatting preserved for inspection.

2 lines
2 sections
No variables
0 checklist items
Enhance the 'Source Verifier' agent with a custom tool that allows it to perform semantic searches over a simulated or actual Weaviate vector database. Populate Weaviate with a small set of 'verified facts' (e.g., WHO statements, scientific journal abstracts). The agent should dynamically use this tool to query the database when it encounters a claim, retrieving relevant supporting or refuting evidence. Ensure the tool's output is correctly processed by the agent.

Consider how to define the tool so the agent knows when and how to call it effectively.

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.