{"slug": "image-optimization-vs-alt-text-what-ai-agents-actually-read-on-your-page", "title": "Image Optimization vs Alt Text: What AI Agents Actually Read on Your Page", "summary": "AI agents like Claude and ChatGPT cannot see images, only read alt text, making text-level image optimization more critical than byte-level optimization for agent-driven traffic. With ~50% of images having empty or sub-10-character alt text, sites risk silent retrieval failures on every agent query. Developers should prioritize descriptive alt text and structured metadata while maintaining byte optimization for human visitors.", "body_md": "## The Decision\n\nHalf the web's bytes are images [Source 2](#source-2), but the agents now hitting your pages — Claude, ChatGPT, agentic shoppers, coding assistants — consume tokens, not pixels [Source 9](#source-9). The choice between optimizing image *bytes* and optimizing image *text* is no longer about accessibility versus performance; it's about who your traffic actually is.\n\n## The Table\n\n| Dimension | A: Byte-level optimization (`next/image` , WebP/AVIF, CDN loaders) |\nB: Text-level optimization (alt text, captions, structured metadata) |\n|---|---|---|\n| Latency | Cuts LCP — `next/image` auto-serves WebP, lazy-loads, sets width/height to prevent CLS\n|\nZero render impact; agents read HTML, not pixels |\n| Memory | sharp on glibc Linux can balloon without tuning\n|\n\n`alt`\n\n`next start`\n\n; cloud loaders (Cloudinary, Imgix, Akamai) for static export [Source 7](#source-7)[Source 17](#source-17)`ai_image_alt_text`\n\nmodule) [Source 5](#source-5)`dangerouslyAllowSVG`\n\nis blocked [Source 4](#source-4); v16 caps`qualities`\n\nto `[75]`\n\nby default [Source 18](#source-18)[Source 10](#source-10); 8.5% end in`.jpg`\n\n/`.png`\n\nfilenames [Source 5](#source-5)I'd pick **B** as the default in 2026, and bolt A on top. Agents are the fastest-growing consumer of your HTML [Source 11](#source-11), and they cannot see your AVIF.\n\n## The Mechanism\n\n**Why A (byte-level) wins when humans on bad networks dominate.** The `next/image`\n\ncomponent serves device-correct WebP, prevents layout shift via intrinsic width/height, and lazy-loads off-screen images natively [Source 3](#source-3). On a flaky link, this matters: Kornel's observation that mobile bandwidth arrives in \"laggy bursts rather than slowly\" [Source 20](#source-20) means a 155 kB hero is a real LCP hit. Byte savings compound — Lara Hogan's point that images are \"arguably the easiest big win\" for page load time [Source 2](#source-2) still holds, and the v16 default of `minimumCacheTTL: 14400`\n\n(4 hours, up from 60 s) reflects that revalidation cost was real money [Source 18](#source-18).\n\n**Why B (text-level) wins when AI agents are reading your site.** LLMs are next-token predictors over text [Source 15](#source-15). Even multimodal models tokenize images through a vision encoder + projector into the same latent space as text [Source 1](#source-1)[Source 1](#source-1) — and IBM's own teams admit \"text-ify everything\" loses visual context [Source 12](#source-12), which is why hybrid multimodal RAG keeps text captions as the retrieval index even when the LLM can see the image [Source 12](#source-12). Translation: when an agent or RAG pipeline crawls your page, the `alt`\n\nattribute *is* the image as far as retrieval is concerned. Docling's whole pitch for AI ingestion is converting unstructured assets into \"clean, structured text that large language models can actually use\" [Source 13](#source-13)[Source 14](#source-14). The Web Almanac is blunt that ~50% of images ship with empty or sub-10-character alt text [Source 10](#source-10) — that's a silent retrieval failure on every agent-driven query. Pick B as the default.\n\n## The Migration Path\n\nIf you optimized for bytes and now need agents to actually understand your pages:\n\n**Audit alt coverage.** Grep your codebase for`