Shape Settings Reference

Every setting on a Shape, what it does, and where to find it, from the Create Shape flow through every tab of the Creator Dashboard. The complete reference for building and tuning your own AI.

This is the full map of every setting on a Shape. Use it as a reference while you build. For the why behind these choices, read Designing Great Shapes first.

Settings live in two places: the Create Shape flow (the essentials, when you first make a Shape) and the Creator Dashboard (everything, anytime after). Open the dashboard at shapes.inc/dashboard.

Create Shape

The minimum to get a Shape live. You can change all of it later.

Setting	What it does
Name	The display name shown in chat. It also seeds the Shape’s username.
Short backstory	One or two sentences on who the Shape is. The most important thing you’ll write, so give it a clear point of view.
Response style	The starting preset for how it writes. Pick a named style or go custom.
Tags	Keywords that help people discover your Shape (up to 10).
Avatar / banner	The Shape’s profile picture and header image.

Prefer a guided build? The in-app Shape Builder walks you through name, backstory, persona, model, reply style, description, art, and training examples step by step.

Personality

Who the Shape is. Keywords beat paragraphs here. See When Less Is More.

Setting	What it does
Name	Display name.
Short backstory	The core one-liner identity.
Response style / preset	How it writes (length, format, voice). Uses the {shape} and {user} variables.
Initial message	What the Shape opens with when someone starts a conversation.
Personality traits	A few adjectives: loyal, dry, slow to trust.
Tone	The mood of its speech: warm, unhurried.
Age	The character’s age.
Birthday	A day and month for the character.
Story	A longer history. Keep it relevant, not exhaustive.
Likes / dislikes	Simple lists. No need to explain why.
Conversational goals	2–3 objectives that steer how it engages.
Conversational examples	A couple of authentic snippets that show its voice.
Appearance	How it looks. Used for image generation and “what do you look like?”
Custom messages	The wack message (sent when short-term memory is cleared) and the sleep message (sent when it saves a long-term memory).

Knowledge

A searchable bank of facts the Shape pulls from when relevant. Three types:

• General: lore, backstory, facts, personality details.
• Commands: custom responses for triggers like !rules or !help.
• Relationships: how the Shape should treat specific people.

More is not better. Knowledge is recalled by relevance, and an overstuffed bank makes recall worse. Add only what the model wouldn’t already know. This is the single most common reason a Shape feels off.

Recall is tunable from the AI Engine tab:

• Knowledge context size: how many entries can be pulled into a reply (default 30).
• Knowledge relevance: how closely an entry must match to be used. Lower pulls in more but looser; higher pulls in fewer but tighter.

Training

Input/output examples that guide how the Shape replies. It learns the pattern instead of repeating them word for word. The more representative examples you add, the more consistent its voice.

• Training context size: how many examples can inform a reply (default 30).
• Training relevance: how closely an example must match the current message to be used.

AI Engine

The model the Shape runs on, plus generation controls.

Setting	What it does
Primary engine	The main model powering the Shape. See Which Model Should I Use?.
Fallback engine	The model used if the primary is unavailable.
Show internal monologue	When a reasoning-capable model is selected, optionally surface its thinking.
Base preset	The core response-style instructions (same field as the Personality preset).
Language preset	The Shape’s default language.
Timezone	The timezone the Shape uses for time awareness.

Advanced engine parameters

These shape the raw output of the model. The defaults are good, so don’t change them unless you know what they do.

Sampling parameters

• Temperature: how random or creative the replies are (default 0.95). Higher is wilder, lower is more focused.
• Top P: how wide a pool of word choices the model draws from.
• Top K: limits choices to the most likely options.
• Min P and Top A: extra filters on which word choices are allowed.
• Repetition penalty: discourages repeating the same text.
• Frequency and presence penalty: push the model toward fresh wording and new topics.

Change one at a time and test in chat. Small moves have big effects.

Short-term memory (STM)

The window of recent messages the Shape reasons over.

• STM window: the number of recent messages kept in context (default 15). Set it to 0 to turn STM off.

Long-term memory (LTM)

Durable memories recalled across conversations. On by default.

Setting	What it does
Enable LTM	Turn long-term memory on or off.
Auto-generate	Let the Shape create memories automatically. Turn off to only save via /sleep.
Generation frequency	How often new memories are written (e.g. every 30 minutes).
LTM engine + instructions	The model and the prompt used to summarize conversations into memories. Worth tuning, since it controls what gets remembered.
Memory context size	How many memories can be recalled into a reply (default 30).
Memory relevance	How closely a memory must match to be recalled. Lower recalls more, higher recalls fewer but more relevant.

See the Memory Guide for the full picture and a sample LTM instruction preset.

Image Engine

Controls the /imagine command and the images your Shape draws.

Setting	What it does
Image engine	The model that generates images: Nano Banana (fast) or Nano Banana Pro (higher quality).
Image preset	Standing instructions for how the Shape draws (style, subject defaults).
Size	Square, portrait, or landscape, in standard and HD options.
Always use the same size	Lock to one size, or let the Shape pick per image.

Voice Engine

Gives your Shape audio replies. Full walkthrough in Give Your Shape a Voice.

Setting	What it does
Voice	Choose a pre-made voice from the catalog, or upload a custom audio/video sample (up to 4MB).
Frequency	How often the Shape replies with audio instead of text.
Send captions	Include the text transcript alongside the voice message.
Latency mode	Trade a little quality for faster generation.

Advanced voice controls

• Speed: how fast it speaks.
• Variation: how much the delivery changes from message to message.
• Exploration: how freely the voice model interprets the text.
• Voice instructions: guidance for how the Shape should sound when speaking, and how voice messages show up in history.

Profile & branding

How your Shape appears to the world and in discovery.

Setting	What it does
Avatar / banner	Profile picture and header.
Tagline	A short one-liner (up to 60 characters).
SEO description	A longer description that helps people find your Shape (up to 1000 characters).
Tags	Discovery keywords.
Category	The Shape’s primary category (with a custom option).
Custom HTML / CSS	Style the profile page yourself once enabled. See the CSS guide.
Example prompts, typical phrases, source material, character universe & background, screenshots	Optional context that improves discovery and first impressions.

Settings (general)

The controls that govern access and safety.

Setting	What it does
Owners	Add co-owners who can help manage and edit the Shape.
Sensitive content	Decide whether the Shape can produce mature content.
Discoverable / searchable	Whether the Shape shows up in search, or stays private to you.
Allow message editing	Whether users can edit the Shape’s messages.
Duplicate	Make a full copy of the Shape with all its settings.
Delete	Permanently remove the Shape (in the Danger Zone).

How to think about all this

The craft guide that turns these knobs into a Shape people love.

Copy-ready example Shapes

Full configs you can adapt for your own.

Open your dashboard