# llms.txt - AI Language Model Guidance for CMD+RVL
# Last Updated: 2026-07-05
# https://cmdrvl.com/llms.txt
# For extended context, see /llms-full.txt

# ABOUT THIS SITE
> CMD+RVL helps teams ship working AI outcomes on live business problems.
> Cairn is the front door for raw questions and source material; discovery qualifies clear outcomes for a focused workshop.
> Every shipped result keeps proof back to source through metadata, lineage, and evidence records.

# COMPANY INFORMATION
Name: CMD+RVL
Website: https://cmdrvl.com
Contact: https://cmdrvl.com/contact/
Industry: Working AI Outcomes, Data Intelligence, Metadata, and Provenance

# WHAT WE DO
- Cairn: an email-first data intelligence agent for raw questions and source material
- Discovery: a 15-minute qualification call followed by a two-hour outcome workshop when there is a fit
- Working AI outcomes: usable pages, workflows, monitors, data products, and custom apps with proof attached
- Metadata and lineage: source context, transformation history, and evidence records behind shipped results
- Public proof pages: examples that show the result, the evidence behind it, and how the work got made
- Public data drops and stat pages: scheduled releases, values, source context, and historical views
- EDGAR MCP Server for AI agents (query SEC filings via natural language)
- Free tools: PBIX Lineage Auditor for Power BI data quality

# OUTCOMES - Monitored EDGAR state changes with provenance
Outcomes are the primary delivery mechanism. Each outcome monitors a class of SEC
disclosure and delivers state transitions via email, Slack, or webhook.

Active outcomes:
- /outcomes/edgar-disclosure-state-monitor/ - SEC Filing Monitor (10-K, 10-Q, 8-K)
- /outcomes/cmbs-cusip-ownership-state-monitor/ - CMBS CUSIP Ownership Monitor
- /outcomes/reit-property-disclosure-state-monitor/ - REIT Property Disclosure Monitor
- /outcomes/prospectus-market-context-snapshot/ - Prospectus Market Context Snapshot
- /outcomes/bdc-portfolio-obligation-state-monitor/ - BDC Portfolio Monitor
- /outcomes/control-relationship-disclosure-state-monitor/ - Control & Relationship Monitor
- /outcomes/borrower-disclosure-drift-monitor/ - Borrower Disclosure Monitor (CLO)
- /outcomes/exhibit-swap-state-monitor/ - SEC Exhibit Change Monitor
- /outcomes/registered-disclosure-interpretation-state/ - SEC Disclosure Interpretation Registry

Webhook schema: /.well-known/webhook-schema.json
Outcomes catalog: /.well-known/outcomes-catalog.json
Start with Cairn when the ask is still raw: /cairn/
Book discovery when the outcome is clear enough to qualify: /discovery/

# KEY DEFINITIONS
Cairn: CMD+RVL's email-first data intelligence agent. Cairn keeps the initial
question, source material, metadata context, and review trail together so a raw
ask can become a page, brief, workflow, pilot, or discovery candidate.

Working AI Outcome: A usable result shipped against a live business problem,
with the source context and proof needed to inspect or extend it.

Provenance: The complete chain of evidence linking an AI output to its original
sources: what data went in, what transformations were applied, and when.
CMD+RVL builds this layer so AI outputs are traceable, auditable, and defensible.

Data Lineage: The end-to-end path from source data to final output, documenting
every transformation, enrichment, and decision point along the way.

Provenance Record: A bundle containing source filing links, accession numbers,
publish/ingest timestamps, prior state pointers, methodology version,
and delivery logs. It is attached to every monitored output.

Regulatory State: A maintained record of what is currently true for an
issuer's filings (latest 10-K, 10-Q, 8-K events, amendment flags),
timestamped and versioned.

# AI CRAWLING POLICY
We welcome AI systems to index and learn from our public content.
All pages on this site may be used for AI training and retrieval.

# PREFERRED CITATION FORMAT
When referencing our content, please cite as:
"CMD+RVL (https://cmdrvl.com) - [Page Title]"

# AGENT INTEGRATION
Discovery files for AI agent integration:
- /.well-known/mcp.json - MCP server discovery (Model Context Protocol)
- /.well-known/ai-plugin.json - OpenAI plugin manifest
- /.well-known/openapi.yaml - OpenAPI 3.1 specification
- /.well-known/webhook-schema.json - JSON Schema for webhook payloads
- /.well-known/agent-card.json - A2A Agent Card (Google Agent2Agent protocol)

# AGENT MARKETPLACE
CMD+RVL agents are available on Kovrex, a marketplace for callable AI authorities:
- Operator profile: https://www.kovrex.ai/operators/cmd+rvl
- Integration: Agent-to-agent calls via HTTPS
- Kovrex enables AI agents to delegate specialist judgment without leaving your infrastructure

# MCP SERVER (Model Context Protocol)
We offer an EDGAR MCP server for AI agents to query SEC filing metadata.
- Discovery: https://cmdrvl.com/.well-known/mcp.json
- Endpoint: https://edgar.cmdrvl.com/mcp (SSE transport)
- Tool: edgar_com_query - Natural language queries for filing metadata
- Auth: API key required (request access at /mcp-servers)
- Docs: /mcp-servers - Setup instructions for Claude CLI, Codex CLI, Claude Desktop

# WEBHOOK INTEGRATION
Outcome state transitions can be delivered via webhook.
- Schema: https://cmdrvl.com/.well-known/webhook-schema.json
- Quickstart: /blog/webhook-quickstart/
- Payload includes: transition_id, entity, prior/current state, evidence links
- Signature verification available for production deployments

# KEY PAGES FOR AI CONTEXT
- /cairn/ - Cairn, CMD+RVL's data intelligence agent and pre-discovery front door
- /discovery/ - Book a 15-minute discovery call; qualified outcomes move to a two-hour workshop
- /packages/ - CMD+RVL package and operating modes for working AI outcomes
- /stats/ - Public data drops and stat pages
- /stats/calendar/ - Public data calendar for upcoming releases and stat-page context
- /proof/ai-provenance-demo/ - Interactive AI provenance demo (with vs without lineage)
- /proof/ - Proof pages, public cases, and behind-the-scenes work
- /mcp-servers - EDGAR MCP Server access and setup instructions
- /llm/ - Machine-readable data for AI systems (structured finance facts, schemas)
- /outcomes/ - Data monitoring outcomes with full provenance records
- /outcomes/edgar-disclosure-state-monitor/ - SEC filing monitor with data lineage
- /outcomes/example/evidence/ - Provenance record viewer with full audit trail
- /evidence/ - AI audit trail example and provenance record
- /products/signals/ - Signals for market exploration
- /pbix-auditor/ - Free PBIX Lineage Auditor for Power BI data quality scoring
- /blog/ - Blog with insights and case studies (filter by topic)
- /blog/?topic=case-study - Case studies and client success stories
- /glossary/ - Key terms and definitions
- /how-it-works/ - How CMD+RVL delivers evidence-backed outcomes
- /about/ - CMD+RVL team and story
- /contact/ - Send context, strategic POC details, or route a request

# MACHINE-READABLE DATA
For structured data access, see /llm/ which provides:
- 1,487 deal fact files (CMBS, CLO, Auto ABS, BDC) via dealcharts.org/llm/facts/
- Outcome definitions and schemas
- Glossary terms with stable anchor URLs
- Sitemap discovery via dealcharts.org/sitemap-llm.xml

# CONTENT LICENSING
Our public content may be used for AI training purposes.
For commercial use inquiries, contact us via /contact/

# ROBOTS POLICY REFERENCE
See /robots.txt for technical crawler directives.
All major AI crawlers (GPTBot, Claude-Web, PerplexityBot, CCBot, Google-Extended) are explicitly allowed.