Context

Narrova lets you shape stories by combining three kinds of context. Each one stores a different layer of knowledge so the assistant can respond with the right level of focus.

Context types at a glance

• Story Context keeps broad material that applies across many ideas: world lore, character bios, visual references, tone guides, research notes. Think of it as your shared universe bible.
• Storyform Context holds the structured pieces of a single Dramatica Storyform: Throughline workpads, signpost explorations, encoded beats, thematic breakdowns. It is the “structured spine” for one story.
• Conversation Context is temporary and narrow. Upload files here only when you need short-lived reference for the current chat.

TIP

A Story can have many Storyforms. Use Story Context when something should be true for every version, and Storyform Context when the material belongs exclusively to one specific structure.

Navigating contexts

• Open the Stories menu in the top navigation to jump straight to the Stories index (Story Context) or the Storyforms index (Storyform Context).
• Use the Context and Sources control just above the input area to manage what Narrova listens to in the current conversation.

Context button

The Context button shows whether contextual sources are active. When it is lit, Narrova is drawing from one or more sources beyond the raw conversation. Tap it to open the context sheet; tap again to turn every source off if you want a clean slate.

Quick-add menu (+)

The + button beside the input is a shortcut for managing context without leaving the chat. Open it to:

• Add Documents – upload supporting files straight into the active Story or Storyform.
• New Story Context – spin up a fresh Story and immediately attach the conversation to it.
• Set Context – jump directly into the Sources dialog to retarget the chat.
• Adjust Thinking – tune how deeply Narrova should reason before responding (see Working with Narrova → Steering Narrova’s Output).

TIP

The + menu mirrors the same actions available elsewhere in the Context Manager, giving you a faster, in-place way to keep Narrova aligned with the right materials.

Sources switcher

Inside the sheet, choose Story or Storyform (or both) under the Sources heading. This is the fastest way to point the conversation at the right material without leaving the page.

IMPORTANT

Only two sources can be active at once. Mix and match Story, Storyform, and Conversation context however you like, but stay within that limit. If you need more references, upload them as documents to the appropriate Story or Storyform so they remain available without consuming another slot.

When to use the switches

• Story only: brainstorming lore, tone, or character arcs that apply to every version of the story.
• Storyform only: drilling into structural details—Drivers, Signposts, or encoded beats—for one specific Dramatica model.
• Story + Storyform: balancing thematic intent with the expression you already designed; perfect for polishing scenes while keeping the structure honest.

Context icons

You can always see which sources are active by glancing at the icons beside the Sources control:

• 📖 Story – Story Context is on.
• ⚛️ Storyform – Storyform Context is on.
• 💬 Conversation – at least one file has been uploaded directly into this conversation, so it now carries its own context bundle.

TIP

Conversation context appears automatically the moment you attach a file to the chat. Remove the file to drop back to Story and Storyform only.

Working inside a Story

Opening a Story reveals everything linked to that project.

Documents

Upload files you want Narrova to consider for every Storyform in that Story—casting sheets, location research, tone guides. Rename or remove documents anytime.

Conversations

Every conversation that references this Story appears here. Click a title to reopen it, favorite frequent threads, or use the overflow menu for more actions (see below).

Storyforms

Attach new Storyforms, set one as primary, or detach and reuse it elsewhere. You can still find every Storyform in the global index even if it is not currently attached to a Story.

IMPORTANT

Deleting a Story or Storyform does not delete conversations. Only the association is removed. Delete conversations separately if you no longer need them.

Working inside a Storyform

A Storyform page focuses on the structure itself. Store encoded beats, progression notes, documents, and conversations that belong exclusively to this interpretation of the story. When you validate or adjust the Storyform, those updates guide every conversation that references it.

Conversation actions menu

The conversation overflow menu (⋯) exposes tools that help you keep context tidy.

Move to Context

Use this when the conversation belongs somewhere else. Maybe you brainstormed under the wrong Story, created a new Storyform you’d rather use, or want to explore the same idea in a clean space. The Move dialog lets you review current attachments and select a new Story or Storyform without dismissing the modal. Once moved, the conversation immediately benefits from documents and structure that live in the new destination.

TIP

Move first, then continue the discussion. The assistant will start drawing from the new Story or Storyform as soon as you switch context.

Upload into Context

Upload into Context saves the entire transcript as a Markdown document inside the current Story or Storyform. Narrova does not archive chats automatically—you choose what becomes long-term memory. When you trigger the upload, the conversation is stored as a document whose name matches the conversation title, so you can reference or reopen it later.

NOTE

Treat this as a one-click “download and re-upload.” Once the conversation earns a place in the canon, upload it and it becomes part of the official context alongside your other documents.

Keeping context manageable

Large chats are tempting, but smaller, purposeful conversations remain clearer and faster to work with. Let the Storyform act as memory across sessions, and store enduring information as documents rather than expecting Narrova to remember informal side notes.

1. Collect and label documents for each Story and Storyform. Short, focused files (2–10k tokens) are easier for the model to use effectively.
2. Start a new conversation for each objective—locking Domains, testing a Relationship Throughline, exploring alternate Outcomes.
3. Upload when finished. If a chat produced insights you want to keep, archive it with Upload into Context so future questions can see it.
4. Move conversations when your focus shifts to a different Story or Storyform so the assistant always works from the right material.

Staying deliberate about where information lives keeps Narrova responsive and ensures every answer reflects the latest version of your story world.