Technical overview # One structured topic behind every format How the platform is designed to work, from the manual you have today to content that people and AI assistants can use. In development The platform is in development. This page describes its design. 01 · Principles ## Five rules behind every decision 1. ### One topic, one question, one URL Each task, concept, error code or question for a specific model gets its own stable web page. 2. ### The answer comes first The first two or three sentences answer the question completely and name the brand and the model. 3. ### One source of truth Each topic exists once as structured content. The web page, Markdown, video, subtitles, audio and MCP response are made from it, so they do not contradict each other. 4. ### One official page Every topic has one canonical address, on your own domain or on your subdomain of the platform domain. 5. ### Text first, media as support Assistants read text. Video and audio help people, and count for assistants through the text around them: titles, transcripts, subtitles and chapters. 02 · Content model ## The topic is the atomic unit - Client deployment - Workspace (a brand) - Model group · models - Manual (versioned) - Topic - Topic version (per language) - Renditions Topic types: task, concept, reference, troubleshooting, error code, FAQ. Each topic version is immutable and carries a SHA-256 source hash. ### A topic document holds typed blocks - A 1–3 sentence summary naming brand and model - Steps with stable ids for anchors and chapters - Warnings inside the step they apply to - Supplies, tools and warnings as shared components - UI names from a vocabulary, not free text - Links by topic key, never hard-coded URLs - Valid models and firmware range 03 · Import ## Existing manuals come in as they are How each source is imported, and what comes out | Source | How | Result | | --- | --- | --- | | DITA/XML | Mapped field by field: steps, supplies, warnings, map order, links | Topics | | PDF | Text and layout extraction, then segmentation into topics | Drafts to review | | iiRDS | Packages read as untrusted input, mapped per client | Topics | | Word, Markdown | Planned; the exact list of upload formats is still open | Drafts to review | ### Re-imports update Each topic keeps an import key (source, source id, language). A new version never duplicates; only changed topics and what depends on them are rebuilt. ### AI only drafts LLM help with structuring runs through your approved provider, produces drafts only, and never rewrites safety text. 04 · Review workflow ## Nothing is published without people 1. Draft 2. In review 3. Approved 4. Published 5. Retired What each role does | Role | Does | | --- | --- | | client-admin | Domains, SSO, crawler policy, public marking, MCP, YouTube connection | | author | Imports, edits drafts, submits for review | | reviewer | Approves or rejects, never their own edits | | publisher | Publishes and retires, as a separate step after approval | | viewer | Reads everything, sees status and analytics | Every transition is written to the audit log. Warnings, cautions, torque values and part numbers are never reworded without human approval. 05 · Generate ## One publish fans out to every format Web - HTML per host - Markdown - JSON-LD - sitemaps · llms.txt - IndexNow Search - chunks - embeddings - public read model - MCP · site search Media - script - voice-over - subtitles · chapters - video - YouTube · page **Idempotent.** Each job is keyed by topic version, format and host, and skips work when the source hash is unchanged. **Text never waits.** The page goes live first; video and audio attach when ready. **Stale is detected.** A changed step marks only its video, audio and subtitles for rebuild. 06 · The topic page ## Every page follows one contract ### Body, in this order 1. Breadcrumb, then title with brand and model 2. The direct answer: a short summary 3. Validity: models, firmware, last updated 4. Video with captions and chapters, audio 5. What you need: supplies and tools 6. Numbered steps, warnings at their step 7. Troubleshooting and FAQ 8. Related topics, transcript, publisher ### Head, for machines - Canonical link and hreflang per language - Link to the Markdown version - One JSON-LD graph: TechArticle, HowTo, VideoObject with chapters, AudioObject, Product with GTINs, Organization, BreadcrumbList Complete without JavaScript. 07 · Where content lives ## Stable URLs on your own host - `https://{host}/{model-group}/{lang}/{topic-slug}` - `…/{topic-slug}.md` Markdown, noindex, canonical link - `…/{error-segment}/{code}` error-code topics - `https://{host}/media/{model-group}/{lang}/{slug}.mp4` ### The host Your own domain, or {slug}.ifuto.ai delegated by DNS to your own deployment. That host is always canonical. ### Never broken A slug change writes a 301. A retired topic returns 410 with a link to its replacement. URLs are never deleted. ### Host files robots.txt, sitemaps with hreflang and video, llms.txt, llms-full.txt, and mcp.json when MCP is on. 08 · Honest about each channel ## What each output adds for AI ### MCP Strongest lever Assistants query official content directly and get the current version plus the URL to cite, without waiting for a search index. ### Video Clear added value Strong reach for how-to questions, and physical steps are clearer on screen. Only when it matches its page one to one: title, subtitles, chapters, link back. ### Audio User feature Rarely found or cited by assistants on its own. On the page it helps accessibility and hands-free use. ### llms.txt Cheap, limited effect Major crawlers mostly read the HTML. Agents and developer tools do use it, so it is provided. The web page underneath all of them is what assistants read. 09 · MCP server ## Five tools for AI assistants The five MCP tools and what each returns | Tool | Returns | | --- | --- | | search_topics | Ranked topics for a query, by brand, model, language or type | | get_topic | Steps, warnings, supplies, video chapters, Markdown | | lookup_error_code | Meaning, cause and fix for a code on a model | | list_models | Models with GTINs, aliases, languages, topic counts | | resolve_product | Best match for free text or a GTIN, with confidence | ### Rules Every result carries the canonical URL, update date, valid models and publisher. Ambiguous model: candidates, never a guess. Wrong model: no steps, a pointer instead. Safety text returned exactly as approved. Public and read-only, per client deployment, off until you enable it. A second, authenticated endpoint behind your SSO serves drafts and authoring tools, under the same four-eyes rules. 10 · Media pipeline ## Video, subtitles and audio from the same topic 1. 01 ### Script Built from the topic: summary plus steps, a chapter per step group 2. 02 ### Voice Text-to-speech by your chosen provider, one voice per language 3. 03 ### Subtitles From word timings; chapters start at the step anchors 4. 04 ### Video Title card, a clip per step, on-screen labels and warnings, end card 5. 05 ### YouTube Your own channel, captions, a playlist per model group **Per-step clips meet.** The last frame of one step's clip matches the first frame of the next; every seam is checked. **Old versions go.** When narration changes, the new video goes up and the old one is deleted on every channel. 11 · Measure ## Is the official content being read? ### AI bot analytics Which AI and search bots fetch which topics, and which topics are never fetched. Built from edge logs of public hosts only, counted per bot family. Off until you enable it. No IP addresses kept; raw logs deleted within 24 hours. ### Answer checks A curated set of real user questions, run regularly against assistants with web search. Records whether the answer cites your page and whether key facts match. Opt-in, from your own deployment and account. Results are trends, not guarantees. Next step ## Talk to us [Talk to us](https://ifuto.ai/talk-to-us/)