Why Traditional Web Scraping Fails at Physical Reality (And How to Build a Constraint-Based Schema)
Traditional web scraping is optimized for extracting text, not preserving the conditions under which an instruction can actually be executed. A page can tell an AI agent to "show the driver your phone screen." The text extracts perfectly, the JSON parses cleanly. But the instruction is physically impossible—the driver is navigating traffic, and you are standing on a curb with three suitcases.…
Traditional web scraping is geared towards extracting text, not capturing the real-world conditions necessary for an instruction to work. An AI can perfectly extract and parse information from a webpage, but the instruction might still be physically impossible to execute. For instance, asking an AI to show a driver a phone screen while they are stuck in heavy traffic with suitcases is not just an LLM hallucination problem—it's a fundamental data-modeling failure.
Most travel guides and the models trained on them focus on idealized digital workflows, ignoring the physical constraints that are crucial in real-world scenarios. When you ask ChatGPT how to handle luggage with a DiDi service in China, it confidently suggests booking a standard Express car. However, a 28-inch suitcase simply won't fit in an Express trunk, and the driver would cancel the booking.
To address this, researchers developed the Survival Semantic Action Protocol (SSAP), an open-source approach that aims to account for physical constraints. The core problem with traditional schemas is the loss of physical context. A simplistic schema like {action: "Book a DiDi", payment: "Link Alipay"} lacks the necessary constraints.
SSAP tackles this issue by extending the Schema.org HowTo format with custom namespaces that define physical boundaries. A real action card in SSAP might look like this:
{
@context: {
schema: "https://schema.org/",
ssap: "https://gochinatrip.app/ns/ssap/v1#"
},
@type: "schema:HowTo",
name: "Check DiDi vehicle capacity before booking",
step: [
{
@type: "schema:HowToStep",
position: 1,
text: "Record the number of passengers and the number and size of suitcases."
},
{
@type: "schema:HowToStep",
position: 2,
text: "If you have 2+ large 28-inch suitcases, you MUST book DiDi Premier or a 7-seater."
]
},
ssap:physicalConstraints: [
"Vehicle configuration affects usable luggage space.",
"A seven-seat label does not guarantee sufficient luggage capacity."
],
ssap:communicationChannel: [
"Do not answer the phone. Use the DiDi in-app typed chat."
],
ssap:evidenceGrade: "Operationally tested with documented scope",
ssap:lastReviewed: "2026-11-15"
}
By integrating physical constraints directly into the schema, AI retrieval systems can match a user's intent (e.g., having three suitcases) with the actual physical reality (e.g., Express cars cannot fit that size). The SSAP Solution seeks to make physical feasibility a first-class property of machine-readable knowledge, ensuring that AI agents interacting with the real world account for these constraints.
The researchers are open-sourcing this protocol, inviting developers to participate in testing and improving the schema. The GitHub repository, governance document, and live implementation are all available for reference and collaboration.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
