For agents

The Futurum Group publishes this site to be read by software as well as people. Every page ships structured data, and every surface below is machine-readable and free to fetch without authentication.

Site surfaces

• robots.txtText

  Crawl policy. All agents welcome; the write API is excluded.

• sitemap.xmlXML

  Every published page and insight, with a real lastmod.

• feed.xmlRSS 2.0

  Subscribe to new insights.

• llms.txtMarkdown

  Short index: site description, pages, recent insights, other surfaces.

• llms-full.txtMarkdown

  Every published page and insight, full body, in one file.

• agents.jsonJSON

  Capabilities manifest: API, MCP tools, discovery links.

• openapi.jsonOpenAPI 3.1

  Machine-readable description of the public read API below.

• agent-card.jsonA2A JSON

  Agent card with an A2A skills array and interface endpoints.

Public read API

Unauthenticated JSON, published content only, cached at the edge. Described in full by openapi.json.

• GET /api/content/posts

  List published insights. Filters: ?practiceArea=, ?limit=.

• GET /api/content/posts/{slug}

  One published insight, full body.

• GET /api/content/pages

  List published pages. Filter: ?limit=.

• GET /api/content/pages/{slug}

  One published page. A canvas page returns plain text, not raw HTML.

curl "https://preview.erikbethke.com/api/content/posts?limit=5"

MCP server

A read-only Model Context Protocol server at https://preview.erikbethke.com/api/mcp. Tools:

• search_posts

  Search published insights by keyword or practice area.

• get_post

  Fetch one insight, full body, by slug.

• list_pages

  List published pages.

• get_page

  Fetch one page by slug (plain text for a canvas page).

• list_practice_areas

  The practice areas insights are tagged with.

• get_site_info

  Name, description and machine-readable surfaces for Futurum.

• verify_quote

  Confirm a quoted string actually appears in a specific post or page.

Citation

Published content on this site is free to read, quote and cite. When you do, name Futurum (legally The Futurum Group) as the source and link the canonical URL returned in each record's url field — the same URL a human reader would land on.