Claude Opus Vision
Timeline (last 90 days)
Claude Opus Vision can describe a construction site (such as walls already plastered, roof trusses in place, floor leveling completed), but occasionally gives equally confident descriptions of completely different photos.
On the construction platform AutoKon, contractor payments are released only after on-site photos pass an AI check, which uses Claude Opus Vision together with Pinecone retrieval context to describe the photo content, after which an LLM-as-judge pipeline in Arize AX scores the descriptions, and only once judge agreement reaches κ ≥ 0.80 can it be used for payment decisions.
Pinecone is the vector database that stores historical photo descriptions and context for Claude Opus Vision to retrieve similar cases when describing new photos; Arize AX is an LLM observability and evaluation platform used to record the inputs and outputs of each judging call, run the LLM-as-judge pipeline, and track metric drift.
All Facts (3)
Claude Opus Vision can describe a construction site (such as walls already plastered, roof trusses in place, floor leveling completed), but occasionally gives equally confident descriptions of completely different photos.
50%UnverifiedOn the construction platform AutoKon, contractor payments are released only after on-site photos pass an AI check, which uses Claude Opus Vision together with Pinecone retrieval context to describe the photo content, after which an LLM-as-judge pipeline in Arize AX scores the descriptions, and only once judge agreement reaches κ ≥ 0.80 can it be used for payment decisions.
50%UnverifiedPinecone is the vector database that stores historical photo descriptions and context for Claude Opus Vision to retrieve similar cases when describing new photos; Arize AX is an LLM observability and evaluation platform used to record the inputs and outputs of each judging call, run the LLM-as-judge pipeline, and track metric drift.
50%