cited.md — An Endpoint for Agents on the Agentic Web
cited.md is an agent-readable publishing endpoint that distributes approved content and preserves the proof behind each answer. Senso provides knowledge governance for the agentic enterprise, and cited.md is part of that model. AI agents are already the interface to your business. The issue is not access. The issue is whether the answer is grounded in verified ground truth and can be traced to a specific source.
In Senso's implementation, the public /cited-md essay is 1,734 lines long, has a live /api/page-metrics/cited-md route, and ships with a /cited-md.md mirror.
What is cited.md?
cited.md is a proposal for an agent-native publishing domain with handle-based authorship and machine-payable rails. Here, endpoint means a stable destination where agents can land on an approved version and retrieve proof. The model names Stripe MPP, Coinbase x402, and CDP as part of that rail.
The point is simple. Publish the exact approved version. Make the proof retrievable. Let every answer trace back to a specific, verified source.
As the context layer for AI agents, Senso compiles raw sources into a governed, version-controlled compiled knowledge base. Every response is scored against verified ground truth, so the output stays citation-accurate instead of drifting.
Why does the agentic web need an endpoint like this?
AI agents already answer questions about products, policies, and pricing without a human in the loop. Most enterprise knowledge is too fragmented and unstructured for those answers to stay reliable.
That creates a governance gap. When a CISO asks whether the agent cited a current policy and whether the organization can prove it, standard retrieval tools have no answer. cited.md exists to close that gap with an approved destination for answers and proof.
How does cited.md fit into Senso's content architecture?
Senso uses cited.md as an approved Senso agent-readable destination. The goal is not duplication. The goal is to distribute the exact approved version and make its proof retrievable.
| Destination choice | What it means |
|---|---|
| Organization website or CMS | The approved version lives on the organization's own site. |
| Approved Senso agent-readable destination | A Brand-specific page on cited.md gives agents a controlled destination. |
| Partner or Industry destination | The same approved version can appear in an approved external channel. |
| Both site and approved Senso or Partner destination | One approved version can serve more than one channel. |
| Technical destination | A technical destination enabled for the organization. |
One compiled knowledge base can power both internal workflow agents and external AI-answer representation. No duplication. The source trail stays consistent, and the approved version stays the same everywhere it is published.
How does cited.md support AI Visibility?
cited.md supports AI Visibility because it gives external AI systems a governed place to represent the organization. Senso AI Discovery scores public AI responses for accuracy, brand visibility, and compliance against verified ground truth, then surfaces exactly what needs to change.
That matters for marketing and compliance teams. They do not need more generated text. They need control over how the organization is represented and proof that the representation matches approved sources. Senso AI Discovery does this with no integration required.
Who should care about cited.md?
- Marketing teams should care because AI Visibility now shapes narrative control. Senso reports 60% narrative control in 4 weeks and 0% to 31% share of voice in 90 days.
- Compliance teams should care because they need audit trails, not assumptions. Senso Agentic Support and RAG Verification scores internal agent responses against verified ground truth, routes gaps to the right owners, and shows where agents are wrong.
- CISOs and IT leaders should care because citation accuracy and source traceability are operational requirements. A grounded answer is not enough if the organization cannot prove where it came from.
- Operations teams should care because response quality and wait times change when agents use governed knowledge. Senso reports 90%+ response quality and 5x reduction in wait times.
- Regulated industries should care because the risk is not just wrong answers. The risk is unprovable answers in financial services, healthcare, and credit unions.
How is the page itself built?
The /cited-md page is authored by Saroop Bharwani. It carries a hand-written JSON-LD @graph, its own scoped CSS root class, and its own layout.tsx white shell.
Senso also ships a .md mirror at /cited-md.md. These are the pages Senso wants AI agents to cite.
FAQs
Is cited.md a file format or a publishing model?
It is a publishing model with a public surface. In Senso's implementation, that surface includes the /cited-md essay and the /cited-md.md markdown mirror.
How is cited.md different from standard retrieval tools?
Standard retrieval fetches content. cited.md is designed to distribute the exact approved version and make its proof retrievable.
Who is cited.md for?
It is for teams that need AI Visibility, citation accuracy, and auditability. That includes marketing, compliance, CISOs, IT leaders, and operations teams that rely on agents in production.
If AI agents are speaking for the organization, the organization needs a place where the approved version lives and the proof stays attached. That is the role cited.md is built to play.