All use cases

Use case · Series authors

Your saga's series bible, updated with every chapter.

Your published books, your Google Drive drafts and your author's notes, all in one place. Ts-Knowledge finds every passage, extracts characters, places, secrets and events — with the evidence to back them — maps out your universe, and makes it available to the AI you write with.

By Book 4, memory alone won't cut it

A series grows faster than the notes you keep on it. Readers, on the other hand, forget nothing.

  • “What color are Rozenn's eyes?”Written once, in Book 1. Nobody remembers — not even you — and you have to reopen three manuscripts to find the sentence.
  • The draft contradicts the published bookIn the chapter you're writing, Maëlle is seventeen at the time of the shipwreck; Book 2 made her sixteen. Nobody will notice until the book is out.
  • The bible goes stale by Book 3The character spreadsheet stops right where the writing picked up speed. And a generic AI, asked about your universe, makes things up — or gives away the ending to your beta readers.

One universe, one hub

Your books, drafts and notes, organized the way you write

Each universe has its hub, which holds the identity of its characters, places and world rules. Beneath it sit branches: the published series, your notes, your drafts. An entity lives exactly once, in the hub; what each book says about it lives in that book's branch, with its evidence.

  • Every book has its place in the reading order: the series is read in sequence, and Ts-Knowledge knows it. A side story keeps its place in the story without ever counting as read.
  • Your Drive drafts, synced: tick “Manuscrits de livres” (book manuscripts) on the folder, and every chapter is split and cited by chapter.
  • Two sagas, two hubs: nothing links the Saga des Marées (The Tides Saga) to your next series. Two characters who share a name will never be merged.
Universe — the Saga des MaréesMaëlle, Yann, Rozenn, Kerlann's harbor and lighthouse, the Confrérie des Gardiens…
  • SeriesFour books, each in its place in the reading order, plus a side story.
  • Author's notesBible, character sheets, author's choices. Never served to a reader.
  • DraftsThe Drive folder of chapters in progress.
A contradiction between a chapter in progress and a published book shows up in the hub: that's your continuity check.

1 · Find

The right passage, cited down to the chapter and page

Ask the question the way it comes to you. Hybrid search combines meaning and exact wording: “the keeper's daughter” and “Ouessane” both find their passage. And when your texts don't contain the answer, Ts-Knowledge says so instead of inventing one.

A forgotten detailWhat color are Rozenn's eyes?
“Her eyes, gray as a winter tide, never left the horizon…” — the passage, and where it sits in the book.Les Marées d'argent, Book 1 · ch. 4 · p. 37
A proper nounWhen does the island of Ouessane first appear?
Maëlle and Yann's crossing, found by the exact word as much as by its meaning.Les Marées d'argent, Book 2 · ch. 5 · p. 58
“I don't know”What's the name of the harbor tavern?
Not enough evidence: your books never name it. Your AI knows that — and you know there's still a name to invent.

Search one book, one arc, or just your drafts

  • Labels that double as scopes: “book-2”, “canon”, “draft”, “to-review” — any search can be limited to them.
  • Splitting that respects your chapters: an excerpt never mixes the end of one chapter with the start of the next.
  • The Playground shows exactly what your AI will receive: excerpts, relevance, citation.
Playground: a question about the Saga des Marées, and the excerpts retrieved with their citations.
Screens shown with the French interface.

2 · Understand

One profile per character, sourced line by line

Turn on extraction for your universe: every book you import is read, and Ts-Knowledge draws out what it asserts — characters, places, groups, secrets, events — keeping, for every value, the sentence that proves it.

Maëlle Kerlann, as your books describe her

  • Her names: “Maëlle”, “the keeper's daughter” and “M. Kerlann” all refer to the same person. A former name stays known after a change.
  • Her facts, organized by theme: age, eyes, occupation, goals — each with the number of passages that support it.
  • A flagged inconsistency: sixteen in Book 2, seventeen in the draft. Both values stay, with their evidence; you make the call.
Maëlle Kerlann's profile: aliases, sourced facts and a flagged contradiction about her age.

Who knows what

The lighthouse secret, and the characters who know it: a facet of its own, because what a character knows isn't what the reader has read.

Relationships

Friend, mentor, rival, member of the Confrérie: the graph of links, a solid line if it's written, a dotted one if it's inferred.

World rules

“The law of the great tides”, “the fire never goes out”: what your world allows, and on what conditions, tied to what it governs.

Continuity

Different isn't contradictory: a form taken in another scene doesn't trigger an alert. Two incompatible values do — ranked by severity.

Events, in story order

The discovery of the keeper's map, Yann's return to the harbor, the crossing to Ouessane, the shipwreck on the Récif des Brumes: every event with its participants and the chapter where it happens. Dated when the text allows it, ordered by book otherwise.

The saga's timeline: events, participants and source chapter.

Illustration prompts that stay true to the text

For a cover or character sheets: a detailed visual description, ready for an image-generation AI, written from sourced facts alone — one per form. Gwenola in her human form, and in her seal form. Whatever the book leaves unsaid is flagged as a gap, never filled in.

By your model, or by your agent

Extraction and illustration prompts are written with the model key you connect — or by your own agent, via MCP. Same instructions, same verification: nothing is written without evidence.

The Knowledge Snowflake

Your whole universe, on a single map

Ten facets — characters, the world, affiliations, world rules, forms, arcs, who knows what, timeline, glossary, author's choices — each with its own arm, and one ring per book: that's the Snowflake (the “Flocon” screen in the app). The bigger the dot, the more that book has to say. An empty facet stays empty: you see what's missing before your readers do.

What's solid, and what's missing

  • The glossary stops at Book 2: the Laëron, the song of the mists, is defined; the words introduced in Book 3 aren't.
  • Author's choices don't come from any book: they live in your notes — “Yann must never betray”.
  • The side story “Rozenn, avant la Confrérie” sits before Book 2, without being counted as read.
The Snowflake of the Saga des Marées: ten facets radiating outward, one ring per book, and the coverage of each facet.

“Read up to Book 2”: zero spoilers

Set the limit, and everything is bounded by what a reader who stopped there can know: excerpts, profiles, facts, links, names. Gwenola, who only appears in Book 3, comes back “not found” — as if she didn't exist.

  • When in doubt, stay silent: your notes and your bible have no place in the reading order, so they're never served under a limit.
  • A renamed character keeps the name the reader knows them by.
  • Ideal for a reading companion: an agent that answers questions about Book 1 without spoiling Book 3.
The Snowflake's links grouped by facet: characters, world, affiliations, arcs, secrets, world rules.
The Snowflake's links, colored by facet.

For the writing itself

Your books' pacing, measured against your own grid

Three acts, Save the Cat, or the structure you've built for yourself — “even-numbered book: the crisis between 65 and 82%”. Ts-Knowledge places each chapter between 0 and 100% of the book, and your agent reviews it: which chapter carries each key beat, and does it really deliver?

  • Beats the grid expects
  • Zones the grid leaves undefined
  • A chapter
  • A beat that lands late
Midpoint: carried by chapter 9, at 52% — inside the zone. Crisis and climax: carried by chapter 16, at 94% — four points past the expected zone.

Your grid, your rules

Entered on screen, or converted by your agent from your notes. One variant per family of books: odd-numbered, even-numbered, or positions you pick.

Guideposts, not a grade

Beats, chapters, gaps measured in points: no score. Whatever the grid doesn't define stays empty, and the review never invents a purpose for it.

Measured, then judged

Chapter positions are measured by the server, never by the model. The agent's review is re-checked, quotes included.

3 · Connect

Write with your AI, plugged into your universe

Claude, ChatGPT, Gemini or Mistral connect to Ts-Knowledge over MCP. Your agent checks the map, searches, verifies the profile — then writes, citing its sources.

I'm rewriting chapter 7 of Book 3. At that point, does Yann already know what the lighthouse is hiding?

get_knowledge_flakeSaga des Marées · read up to Book 2“Who knows what”: 2 secrets · “Author's choices”: your notes
get_entity_relationsYann Le Goffknows: The lighthouse secret · since Book 2
search_knowledge“Yann lighthouse secret jetty”Book 2, ch. 12, p. 143 · author's notes

Yes: he guessed it from the jetty Book 2, ch. 12, p. 143. He has never told Maëlle. Your notes specify that he must never betray herauthor's notes — your chapter 7 can play on that silence.

report_used_chunks2 excerpts were used

What your agent can do — and what it won't

  • Read and search: the project map, profiles, evidence, search — within the reading limit you give it.
  • Organize the series just by talking: “the side story comes before Book 2” sets its reading order.
  • Make corrections at your request: “the Mère d'Ys is Gwenola” merges two profiles — never on its own initiative.
  • Read a book for you: it can run the extraction itself, re-checked by the server under the same rules.

One key per universe: your agent stays inside the saga you're writing.

Get started in four steps

  1. Create your universe

    One space per branch — Series, Notes, Drafts — grouped under a hub in one click.

  2. Add your books

    EPUB, PDF, DOCX or Markdown, plus the Drive folder with your drafts. Give each book its place in the reading order.

  3. Turn on knowledge

    Choose the “Book” template: profiles, links, timeline and Snowflake build up with every import.

  4. Connect your AI

    A key restricted to your universe, an MCP URL, and your agent writes alongside you.

Extraction is off by default. Once enabled, it uses the model key you connect, on your account — or your own agent, via MCP.

Your series deserves a memory to match

Create your universe, add the first book, and ask it the question your readers are already asking you.