AI-agent auto-detected markdown fallback
Detect likely agent requests and return markdown automatically, even when the client does not explicitly ask for it.
Why this can grow a startup
A lot of assistants still make plain GET requests, which means content negotiation alone leaves retrieval quality to luck. Auto-detection closes that gap. If an agent, bot, or IDE helper lands on the page without the ideal headers, it still gets the clean representation instead of wasting tokens on scripts and interface chrome.
Company example
Vercel recommends a layered detection approach that checks known AI user agents, RFC 9421 Signature-Agent headers, and a low-risk heuristic fallback for requests that look bot-like but are missing browser fetch headers.
Source and metric
Source: Vercel Knowledge Base · Browse Vercel Knowledge Base tactics
Source discovered: May 24, 2026
When to use it
Use this when AI Search, Website, Content is relevant to ai-discovery, content-ops, trust and you can run a bounded test with a medium budget.
When not to use it
Do not use it as a substitute for customer evidence, a clear owner, or a measurable stop condition. Local platform rules and market behavior still need checking.
Founder checklist
- Read Vercel Knowledge Base and identify what is directly supported.
- Choose one channel context: AI Search, Website, Content.
- Define the test around one observable customer behavior.
- Set an owner, evidence window, and stop condition before launch.
Explore the context
Apply this with an operator
Turn isolated search tactics into a crawlable visibility system tied to demand and proof.