S1
Scanner
Self-service readiness assessment. Enter a URL, get a scored report across seven dimensions: discoverability, legibility, freshness, trust, comparison readiness, action readiness, and standards compliance.
Free tier live. Pro from $49/mo.
Platform
Six systems for agent-ready websites.
Intrinsic is not a single tool. It is six integrated systems that scan, detect, plan, generate, transact, and learn across your entire agent surface.
The systems
What the platform does.
Each system handles one dimension of agent readiness. Together they form a continuous loop: scan surfaces, detect visitors, plan responses, generate content, enable transactions, and learn from the network.
S2
Detection
Identifies, classifies, and profiles every non-human entity touching the site. Behavioral fingerprinting, intent classification, and a network-wide agent registry.
Sub-5ms cached identification.
S3
Intelligence
Policy engine and interaction planner. Determines the optimal response strategy per agent, per request, based on the site owner's goals.
Per-request planning, cached strategies.
S4
Generation
Generates and maintains all machine-facing content from a single source: agents.json, llms.txt, reasoning.json, schema.org, and more. Automatic freshness management.
One source, every standard.
S5
Commerce
Declares bounded agent-callable actions: query, quote, compare, reserve, purchase. Machine-readable pricing exposure and transaction handoff.
Safe delegation, not open access.
S6
Network
Cross-installation collective intelligence. Behavioral benchmarks, threat feeds, pricing signals, and standard adoption tracking across the entire Intrinsic install base.
Every installation is a sensor.
The journey
How an agent-ready interaction progresses.
The platform makes each step easier to understand and easier to complete.
1. Scan
See the gaps
Enter a URL. Intrinsic crawls the site as an agent would and produces a scored readiness report.
2. Generate
Build the surfaces
Intrinsic generates machine-facing manifests, structured data, and action declarations from existing site content.
3. Detect
Know who visits
Identify and classify every agent touching the site. Understand intent, not just identity.
4. Control
Set the policy
Define what agents see, what they can do, and how the site responds per entity class and intent.
Standards
One platform, every standard.
The agent standards landscape is fragmented. Intrinsic generates and validates across all of them from a single source of truth.
agents.json
Agent Web Protocol capability declarations and action discovery.
llms.txt
LLM-readable site overview for language model retrieval.
reasoning.json
Reasoning directives that teach agents how to think about the business.
schema.org
Structured data for search engines and knowledge graphs.
MCP
Model Context Protocol for direct tool integration with agent systems.
agent.txt
Unified manifest pointer. The single entry file for all machine-facing surfaces.
Machine surfaces
Contracts are published, not implied.
Agents should not have to reconstruct commercial intent from presentation. The platform publishes manifests, pricing, actions, and plain-text summaries as first-class routes.
Published surfaces
One canonical model, many outputs.
Capabilities, adapters, use cases, pricing definitions, and action contracts are all emitted from a structured source of truth without duplicating or drifting across pages.
Machine outputs
Retrieve the same data agents retrieve.
Every contract the platform generates for agents is also available at a public URL for inspection.
Next step
Start with a free scan.
The scanner shows where agents get stuck on your site today. The platform fixes it.
What changes
Agent-ready in weeks, not months.
The platform generates, deploys, and monitors all machine-facing surfaces automatically. Your team focuses on the business logic.