Back to Prompt Library
implementation

Claude Thinking Prompt

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

Linked challenge: Multi-Model Safety Evaluator with Claude Agents SDK and Triton

Format
Text-first
Lines
1
Sections
1
Linked challenge
Multi-Model Safety Evaluator with Claude Agents SDK and Triton

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Initialize a Claude agent using the Claude Agents SDK with extended thinking enabled. Create a tool that queries a Triton Inference Server for real-time model predictions. The agent should receive video metadata and 'think' through whether the car's behavior constitutes a safety backslide according to NHTSA guidelines.

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.