Three providers, three modalities, under 55 lines of Python — and a PNG file on disk at the end....
Building a Multimodal AI Pipeline: Text Image Text Across Three Providers
Related
Workfront MCP and Claude: a field report from production
What Adobe's Workfront MCP server does, where it stops, and what a verified Claude toolkit does differently — findings from production, with timings.
I Trust My AI Completely—Except When It Says “Done”
A forged confirmation, falsely green tests, and the acceptance gate I built afterward.
Model + Harness = Agent: The Gap Isn’t Where You Think
Same model, different harness: why agent reliability depends on the system around the model.