Editorial AI in AEM: Giving Editors Control Over LLM-Generated Image Descriptions
summary
An open-source AEM workflow encodes images in Base64 and sends them over plain HTTP to Azure AI Foundry for vision-capable LLM chat completions, returning alt text saved into asset dc:description metadata; prompts live as plain-text files inside the DAM so authors get versioning, permissions, diffs and immediate edits. Implementation adds caching, circuit breakers and timeouts, costs ~5¢ per asset (2,000 assets ≈ $100) and replaces ~167 manual hours; prototype ships as a Maven module and took about a week of dev time.
AI-written summary · about
