Autonomous Predictive Vision & Repair with Claude Agents and Cognition Devin
Industrial vision systems are critical for identifying wear and tear in harsh factory conditions (dust, heat, vibration). This challenge tasks you with creating an agentic workflow using the Claude Agents SDK to process visual sensor data and Cognition Devin to autonomously generate corrective code for the PLC (Programmable Logic Controller). You will build an agent that uses Claude's vision capabilities to detect 'thermal bloom' or 'bearing misalignment' from simulated industrial camera frames. Once a defect is detected, the Claude agent must use the 'Computer Use' capability to navigate a simulated IDE where Cognition Devin is active. Devin will then be tasked with writing a Python-based predictive maintenance script that adjusts the machine's operating frequency to mitigate further damage until a human technician arrives. This addresses the transition of industrial automation into a 'software discipline' and the move toward 'agentic AI' in modern manufacturing.
What you are building
The core problem, expected build, and operating context for this challenge.
Industrial vision systems are critical for identifying wear and tear in harsh factory conditions (dust, heat, vibration). This challenge tasks you with creating an agentic workflow using the Claude Agents SDK to process visual sensor data and Cognition Devin to autonomously generate corrective code for the PLC (Programmable Logic Controller). You will build an agent that uses Claude's vision capabilities to detect 'thermal bloom' or 'bearing misalignment' from simulated industrial camera frames. Once a defect is detected, the Claude agent must use the 'Computer Use' capability to navigate a simulated IDE where Cognition Devin is active. Devin will then be tasked with writing a Python-based predictive maintenance script that adjusts the machine's operating frequency to mitigate further damage until a human technician arrives. This addresses the transition of industrial automation into a 'software discipline' and the move toward 'agentic AI' in modern manufacturing.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
Frequency Bound Check
Ensures the generated script doesn't set frequency to zero or unsafe levels.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Vision Accuracy
Precision in identifying the defect coordinates in the image • target: 0.9 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Implement the Claude Agents SDK's specialized 'Thinking' block to reason about industrial hardware failures.
Integrate Cognition Devin as a high-tier 'Software Engineer' agent capable of modifying control logic.
Design a vision processing tool that handles 'noisy' image data (simulating dust and heat interference).
Optimize the communication between the Vision Agent (Claude) and the Coder Agent (Devin) using structured XML-based protocols.
Master the use of 'Computer Use' to allow Claude to interface with legacy HMI software interfaces.
Build a safety check mechanism that prevents Devin from deploying code that exceeds machine torque limits.
How this agent runs
Evaluates if the vision agent correctly identifies a misaligned bearing and if Devin generates a valid frequency-reduction script.
Challenge input
PNG (Thermal Image) + Current Machine Specs
Claude Agents SDK
Superior multi-modal reasoning for visual fault analysis.
Cognition Devin
Capable of end-to-end software generation for control systems.
Evaluated output
Python Script + Validation Report
- Ensures the generated script doesn't set frequency to zero or unsafe levels.
- Precision in identifying the defect coordinates in the image • target: 0.9 • range: 0-1
- Benchmark: RoboMaintenance-v1
- Vision Accuracy target: 0.9
- Protected reference cases support private evaluation
- Docker execution harness
- Docker sandbox
View technical recipe
Configured tools
- Claude Code · Required
- Claude Code · Required
- Claude 4.1 Opus · Optional
- Claude 4 Sonnet · Optional
Evaluation contract
- Frequency Bound Check · Weight 1
- Vision Accuracy · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.
Run this agent on your dataset
Versalist can run this agent on your behalf with your data. Tell us about your dataset and the result you need.
Discuss your dataset[ok] Wrote CHALLENGE.md
[ok] Wrote .versalist.json
[ok] Wrote eval/examples.json
Requires VERSALIST_API_KEY. Works with any MCP-aware editor.
DocsFind another challenge
Jump to a random challenge when you want a fresh benchmark or a different problem space.