Part 1 of 2 -- Why Context Reconstruction is the Real Cost Center of Modern AI
Gary Newcomb
CTO & Co-Founder, FetchRight
Every large-language-model query comes with an invisible price tag: context reconstruction.
In this first article of a two-part series, I'll unpack why today's LLMs waste so much compute rebuilding knowledge they've already seen, and how that inefficiency reshapes the economics of AI.
In Part 2, I'll move from diagnosis to design, showing how publishers and model operators can share structured, licensed context through FetchRight and the open Peek-Then-Pay standard.
Every time a large language model answers a question about the world - whether it's "what's the best router for gaming?" or "summarize this article from PCMag" - it has to reacquire and reprocess context.
That means:
For a model like GPT-4, that process burns thousands of tokens just to get to the starting line, before even generating a response. Multiply that across billions of daily queries and you begin to see it: context is the real cost center of modern AI.
Many publishers already manage structured, high-quality content with canonical URLs, metadata, topics, and sometimes even embeddings for internal search or personalization.
Yet few have exposed that structure in ways AI agents can directly query or understand; capabilities that increasingly belong on their own domains.
Still, today's AI systems treat publishers as if they're flat text files.
They scrape, strip, and rebuild knowledge from scratch, spending enormous compute to recreate structure that could already exist in higher fidelity within publishers' own systems, while offering publishers no visibility or value in return.
This mismatch is not just inefficient. It's unsustainable for both sides.
Peek-Then-Pay is an open standard that defines how AI crawlers can discover, preview, and license structured content from the web.
Think of it as: robots.txt for AI, but enforceable and auditable.
A publisher hosts a simple manifest file - peek.json - that declares:
LLMs can "peek" to see what's available and relevant without violating terms, using HTTP 203 responses for previews instead of blind 402 rejections.
When deeper access is needed, the model requests a license through the publisher's chosen provider.
That provider is FetchRight.ai.
FetchRight operationalizes the Peek-Then-Pay protocol.
It gives publishers, AI agents, and model operators a common language for:
It's built to work transparently with Cloudflare, Fastly, or other edge providers, enforcing rules at the perimeter and caching peeks for efficiency.
For LLM builders, FetchRight isn't another gatekeeper - it's the missing layer of clarity.
Instead of guessing what's allowed, you get a contractually clear, machine-readable pathway to authorized, structured context.
If you're building or maintaining retrieval pipelines, you already know the economics:
Now imagine a world where:
That's the FetchRight promise: shared efficiency without shared exposure.
It's cheaper for the LLM, safer for the publisher, and traceable for everyone.
For a typical web-scale LLM:
By replacing raw text crawling with structured peek.json access, models can cut that 90% dramatically - while publishers finally get paid for the structured data already in their CMS.
It's a rare equilibrium where both compute and compensation improve.
FetchRight isn't theory - it's live infrastructure.
It runs natively today on Cloudflare Workers, combining low-latency edge compute with licensing intelligence.
Today, the enforcer supports:
In production, that means:
Performance scales with caching and warmup; subsequent licensed requests typically resolve in under 120 ms.
The result is edge-native licensing and retrieval — fast enough for real-time AI agents, lightweight enough for global publishers, and flexible enough to support live semantic search, QA, and transformation directly at the perimeter.
The web's next protocol war isn't about privacy or SEO.
It's about how AI learns - and who gets a voice in that process.
Peek-Then-Pay gives the web a shared grammar for structured, licensed knowledge exchange.
FetchRight turns that grammar into a real economy.
If you're building AI agents, RAG systems, or model APIs - the path to better answers, faster responses, and lower costs doesn't start with another GPU.
It starts with better context.
And that context already exists - on the publisher's side of the glass.
---
Continue to Part 2: The Next Layer of the Web
A detailed look at how publishers and LLMs share structured context — with FetchRight as the bridge.
FetchRight and Peek-Then-Pay let LLMs ask publishers directly for pre-filtered, attribution-ready context — cutting duplicate embedding work and lowering costs for both sides.
How the Peek-Then-Pay standard is reshaping the relationship between AI systems and content creators, giving publishers control while enabling efficient AI development.
AI has outgrown the infrastructure of the early web. Peek-Then-Pay provides the modern protocol this era requires: structured discovery, transparent licensing, and aligned incentives.