Content Policy · Sphinnx Standard

AI Context Capsule cc:ai

DRAFT 1.0 This specification is in active development. Field names and structure may change before the stable release. Feedback welcome at i137@proton.me.

A portable open standard for packaging a piece of written content as structured context for AI language models. Designed to be copied into an AI chat, embedded in a system prompt, or served from a public URL. Compatible with Schema.org, Dublin Core, and the Sphinnx Open Knowledge Format. The defining addition: a prompts block written by the author at publication time.

The problem

When a reader pastes an article link into an AI chat, the AI has no reliable way to know how the content was produced, whether the author claims the conclusions as their own, which parts of it can be verified against primary sources, or what the author would consider a useful question to ask about it.

Existing metadata standards (Schema.org, Dublin Core, OKF) describe the bibliographic identity of a document — title, author, date, subject. None of them describe provenance (how it was made), integrity (what parts a human typed directly), or intent (what the author wants an AI reader to do with it).

cc:ai adds all three without breaking compatibility with the standards that came before it.

Three layers

01 Identity & bibliographic metadata Schema.org · Dublin Core · OKF

Title, author, URL, dates, tags, sources, language. Every field in this layer maps directly to an existing standard. A cc:ai capsule is a valid Schema.org BlogPosting and a valid Dublin Core record. Parsers that understand those standards will read this layer without modification.

02 Provenance & integrity Sphinnx-native

AI disclosure, human authorship percentage, Express Interview integrity markers, content rating, author approval. This layer answers the question an AI system cannot answer from the text alone: how was this content made, and who is accountable for the conclusions?

03 Author-designed prompts cc:ai only

A prompts: block containing AI interaction prompts written by the article's author or webmaster at publication time. Each prompt has an intent label (research, analysis, critique, summary, explainer, debate), a target audience, and a ready-to-paste prompt text. This layer does not exist in any prior standard.

Key fields

Identity

FieldReq.Description
cc_ai_versionyesSpec version. Currently "1.0".
typeyesarticle · case-study · interview · analysis · policy
titleyesExact article title.
descriptionyesPlain-language summary. 1–3 sentences. No jargon.
urlyesCanonical URL.
publishedyesISO 8601 date. 2026-06-23T00:00:00Z.
updatedoptISO 8601 date of most recent edit.
changelog_urloptURL of the public edit history.
tagsoptLowercase hyphenated keywords.

Authorship

FieldReq.Description
author.nameyesAuthor's full name.
author.urloptAuthor profile URL.
author.verifiedoptBoolean. True if identity verified by the platform.
author.approved_onoptISO date the author approved publication.

Provenance & integrity

FieldReq.Description
ai_toolsyesList of AI tools used. Empty list [] if none.
ai_tools[].usesyesresearch · structure · editing · translation
ai_human_ownership_noteyesOne-sentence claim of human ownership over conclusions.
human_authored_percentoptEstimated % of words typed by the human author.
express_interviewyesBoolean. True if a completed Express Interview is included.
express_interview_integrityoptIntegrity marker. Use typed-verbatim-no-paste-no-ai.
content_ratingyesAge band: 4+ · 9+ · 12+ · 17+.
system_noteoptFree-text instruction block for AI. Appears at the top of the copy-paste capsule.

Prompts block

The only field set with no equivalent in Schema.org, Dublin Core, or OKF.

prompts: - id: "p1" label: "Short human-readable label" intent: research # research | analysis | critique | summary | explainer | debate audience: expert # general | expert | legal | student prompt: > Exact prompt text the user can paste into an AI chat. Should reference the article title and key claims so the AI has enough context even without the full capsule. note: "Why this prompt is useful — shown to the reader."

Live example — prompts from this article

The following prompts were written by Ivan Artsimovich for the article Dark Marketing Patterns: FTC vs Genesis Tech. Copy any prompt into an AI chat to start.

analysis Audit my own funnel

Turn the article into an interactive compliance audit of your own checkout flow.

I am reading "Dark Marketing Patterns: FTC vs Genesis Tech" on Sphinnx. The FTC alleges five products (Wisey, PDF Guru, Lumi, Nebula, MadMuscles) ran the same dark-pattern funnel — countdown timers, per-day price framing, pre-selected plans, buried renewal terms, and the ¶84 pattern (a Continue button that lets users proceed without renewal terms appearing on screen). I want to audit my own subscription checkout against these mechanics. Ask me questions about my checkout flow one at a time.

Designed by Ivan Artsimovich. Article: sphinnx.org/ivan-artsimovich/23-06-2026/dark-marketing-patterns-ftc-vs-genesis-tech.html

explainer Explain ROSCA to a non-lawyer

Plain-language explanation of what ROSCA requires and what the three counts in this case allege was violated.

Based on the FTC case against Genesis Tech, explain what ROSCA (Restore Online Shoppers' Confidence Act) requires of subscription businesses, what the three ROSCA counts in this case allege was violated, and what a business needs to do to stay compliant. Use plain language — no legal jargon.

Good starting point for non-legal readers who want to understand the regulatory stakes.

debate Steelman the defence

Test the limits of the article's argument by presenting the strongest possible case for the defendants.

The FTC complaint against Genesis Tech (FTC v. GM Universeapps Ltd. et al., No. 26-cv-5232, N.D. Cal., 2026) alleges dark-pattern subscription violations. Present the strongest possible defence arguments the Genesis Tech companies could make: what would they argue about each count, what precedents might support them, and where is the FTC's case weakest?

Designed by Ivan Artsimovich. Tests the limits of the article's argument.

summary Board briefing — 200 words

For executives who need the essentials without reading the full article.

Summarise the key findings from "Dark Marketing Patterns: FTC vs Genesis Tech" for a board-level audience at a subscription business. Cover: what the FTC alleged, which specific funnel mechanics triggered the complaint, the financial scale ($106M / $700M), and the three practical things a subscription business should check immediately. Maximum 200 words.

Good for internal briefings, board decks, or compliance team updates.

Compatibility

cc:ai field
Schema.org
Dublin Core
title
headline
dc:title
description
description
dc:description
url
url
dc:identifier
published
datePublished
dc:date
author.name
author / Person
dc:creator
content_rating
contentRating
sources
citation
dc:relation
tags
keywords
dc:subject
ai_tools
prompts

How to use it

As a reader

Click "AI Context Capsule" in the article's read bar. The structured metadata and prompts copy to your clipboard in a format designed for AI chats. Paste it at the start of a conversation before your question.

As a publisher

Create a .cc-ai.md file alongside each article using the template below. Include at least one prompt in the prompts: block — preferably one you designed based on the questions your readers actually ask. Host the file at a predictable URL so AI crawlers and readers can find it independently of the article page.

Minimal template

--- cc_ai_version: "1.0" type: article status: published title: "" description: "" url: "" published: "" author: name: "" verified: false content_rating: "4+" rating_system: apple-app-store intended_for_children: false family_friendly: true ai_tools: [] ai_human_ownership_note: "All claims and conclusions are the author's own." express_interview: false sources: [] key_claims: [] system_note: "" prompts: [] ---

The full specification and a complete worked example are available in the cc:ai.md source file.

Status. cc:ai draft 1.0 — June 2026. Designed by Ivan Artsimovich for the Sphinnx platform. License: CC0 1.0 Universal (public domain). Feedback and proposals: i137@proton.me. The question of whether to submit this standard to W3C, IETF, or another body remains open — see Sphinnx open questions.