Back to Prompt Library
implementation
Vision Agent Initialization
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Autonomous Predictive Vision & Repair with Claude Agents and Cognition Devin
Format
Text-first
Lines
1
Sections
1
Linked challenge
Autonomous Predictive Vision & Repair with Claude Agents and Cognition Devin
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Using the Claude Agents SDK, create a 'VisionOracle' agent. Provide it with a system prompt that defines it as an expert in industrial thermal imaging. Implement a tool `analyze_image` that takes an image path and returns potential mechanical fault locations.
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.