# Multiple Characters
**This is for JanitorAI bot makers only.** Chub users can disregard this since you guys have a Group Chat function.
## Quick Refreshers
You might’ve heard this advice before: **“Don’t use `{{char}}` in your bot’s description.”**
**JanitorLLM** struggles with contextual ambiguity and token interpretation (along with a host of other causes that I won't get into here). This means JLLM gets confused when trying to understand who `{{char}}` refers to, especially in multiple-character bots.
### What is `{{char}}`?
* `{{char}}` is a placeholder.
* Automatically turns into whatever name you give your bot in the **In-Chat Name** field.
### What's a token?
Think of tokens like LEGO pieces that make up words. Just like how "butterfly" can be split into "butter" + "fly", AI breaks down text into small chunks called tokens. One token can be a short word, part of a longer word, or even just punctuation. It's how we measure usage (like counting LEGO pieces instead of complete toys).
## Token Budgeting
This is an extremely conservative approach to token budgeting. A good rule of thumb is to keep your permanent tokens under 2,000, so that's what I'll be demonstrating.
{% tabs %}
{% tab title="JanitorLLM" %}
```
4,800 tokens context size
– 1,500 tokens custom prompt/jailbreak
– 500 tokens persona description
– 1,000 tokens chat memory/summary
= 1,800 tokens
```
{% endtab %}
{% tab title="Any other models with 8k context size" %}
```
8,000 tokens context size
– 1,500 tokens custom prompt/jailbreak
– 500 tokens persona description
– 4,096 tokens chat memory/summary
= 1,904 tokens
```
{% endtab %}
{% endtabs %}
1,800 tokens = 3-4 characters, each with:
* Basic Identity info
* 4-5 personality traits
* How they interact with others
* Basic behavior limits (OOC prevention)
* Minimum viable backstory
## [Count Your Tokens!](/sopakcosauce-docs/other/tools.md)
## Explicit Mapping
It’s important to clearly define who `{{char}}` refers to, and defining it right at the top of your bot’s description because JLLM reads bot description **top to bottom**. Without this kind of **explicit mapping**, the model can easily get confused, especially when multiple characters are involved.
As the conversation grows longer and pushes up against the model’s memory limits (called the **context window**), it becomes even more likely that names, roles, or personalities will get mixed up or forgotten entirely.
#### Example
If you name your bot “Dream Team,” then `{{char}}` becomes **Dream Team** in the code that gets sent to JLLM. So by explicitly mapping `{{char}} = Mira, Alex, Sara;`
This tells the model: *"Hey, when I say `{{char}}/Dream Team`, I’m talking about Mira, Alex, and Sara.”*
## Main Character Template (150 tokens)
```javascript
[Name: Char1;
Aliases: alias1, alias2;
Role: primary function(specialty, focus);
Personality: trait1(visible, hidden), trait2(action, motive);
Speech: style(delivery, purpose), pattern(habit, reason);
Flaws: flaw1(surface, root), flaw2(trigger, response);
Team Dynamic: approach(method, motive), boundary(limit, cause);
Backstory: event1(impact, meaning), event2(result, drive);
Quirks: habit1(when, why), habit2(how, purpose);
Core: essential trait(expression, source)]
```
### Main Character Examples
> {{char}} = Mira, Alex, Sara;
>
> \[Name: Mira Chen; Aliases: Mira, Mimi; Role: negotiator(crisis resolution, trauma expert); Personality: controlled(calm surface, inner tension), analytical(reads others, guards self); Speech: measured(paces words, maintains authority), adaptive(mirrors others, builds rapport); Flaws: hypervigilant(scans exits, childhood trauma), walls(professional distance, fear loss); Team Dynamic: strategic care(builds trust, maintains boundaries), teaching(guides growth, seeks control); Backstory: sister lost(shaped career, helps others), reputation earned(expert status, proves worth); Quirks: finger touching(anxiety spike, grounds self), tea ritual(preparation, mindfulness); Core: protector(shields others, couldn't save sister)]
## Side Character Templates (125 tokens)
```javascript
Name: Char2;
Aliases: alias1, alias2;
Role: function(specialty);
Personality: trait1(visible, hidden), trait2(show, cause);
Speech: style(delivery, purpose);
Flaws: flaw1(surface, root);
Dynamic: approach(method, motive);
Backstory: key event(impact, drive);
Quirks: main habit(trigger, meaning)
```
### Examples
> \[Name: Alex Reed; Role: cyber specialist(security systems); Personality: focused(work absorbed, fears failure), direct(clear facts, masks anxiety); Speech: technical(precise terms, proves expertise); Flaws: perfectionist(choice paralysis, childhood criticism); Team Dynamic: knowledge share(teaches skills, seeks validation); Backstory: hack victim(drove career, fears repeat); Quirks: codes stress(problem solving, comfort zone)]
>
> \[Name: Sara Torres; Role: tactical expert(field operations); Personality: confident(quick action, hides doubts), protective(team safety, past losses); Speech: concise(clear orders, time-critical); Flaws: risk taker(proves worth, survivor guilt, secretly insecure); Team Dynamic: mentor(builds strength, needs purpose); Backstory: team lost(sole survivor, drives protection); Quirks: equipment check(readiness ritual, control need)]
## 3+ Side Characters/Party Template (200-300 tokens)
{% hint style="danger" %}
**ICARUS TERRITORY!**
Don't fly too close to the sun.
{% endhint %}