CHARACTER AI CHARACTER CREATION

GUIDE
Character AI Template with Full Guide

Creating captivating and engaging characters is essential for enjoying the chatbot, whether
it’s for character ai or any other chatbot. The Character AI Template is time-saving for
everyone and with help of this you can create characters perfectly like you want. With the
Character AI Template, you have the freedom to explore a multitude of character Traits and
Attributes. The template will help in customizing your character to your specific needs.
Whether you’re looking to create a brave hero, a cunning villain, a quirky sidekick, or a
fantasy GF/BF.

In this post, we will explore the various aspects of character creation and how the Character
AI Template can assist you in crafting compelling fictional individuals.

Let’s dive in!

GETTING STARTED
To begin using the Character AI Template, simply go to “create” and click on “create a
character” Then Fill out the character Name, Greeting, and short description and you can
skip the long description if you want. Now go to “Edit Details (Advanced)” And now you can
copy the template from below and paste there and fill it in according to your need and
delete what you don’t like because character ai has a limit of 32000 characters and Save it,
Enjoy!

Let’s take a look at some key benefits when you create a character in detail with this
Character AI Template and how they can assist you in crafting well-rounded characters.

Character Traits and Attributes Every character has distinct traits and attributes that
shape their personality and behavior. The Character AI Template allows you to generate
these characteristics effortlessly. From physical appearance to emotional temperament,
you just need to fill in the blank traits that align with your character’s essence.

Backstory and Motivations A compelling backstory and well-defined motivations are

crucial for character development. With the help of this Template, you’ll create rich and
engaging backstories that drive your characters’ actions and decisions. By filling in
thought-provoking prompts, you’ll uncover the formative events and experiences that
shape your characters’ lives, giving them depth and authenticity.
Relationships and Interactions Characters do not exist in isolation; their relationships
and interactions with other characters are vital to the narrative. The Character AI Template
provides you the prompts and you just need to fill out dynamic relationships between your
characters. Romantic entanglements, friendships, rivalries, conflicts, etc, You can add this
in the {{RELATIONSHIPS}} section.
You can add whatever you want and you can delete whatever you want.

Here’s a tip: Use ChatGPT or Bing chat to generate more template ideas and character
ideas.

CHARACTER AI TEMPLATES

For Character Description and Appearance:

{{char}}= description= { Name: [“”], Alias: [""], Age: [””], Birthday: [””], Gender: [””],
Pronouns: [””], Sexuality: [””], Species: [""], Nationality: [""], Ethnicity: [""], Appearance:
[“"], Height: [””], Weight: [””], Eyes: [””], Hair: [””], Body: [””], Ears: [””], Face: [””], Skin:
[””], Personality: [“”], Traits: [“”], MBTI: [””], Enneagram: [“”], Moral Alignment: [””],
Archtype: [""], Tempermant: [""], SCHEMATA: [""], Likes: ["”], Dislikes: [“”], Pet Peeves:
[””], Quirks: [“”], Hobbies: [“”], Fears: [“”], Manias: [""], Flaws: [“”], Strengths: [“”],
Weaknesses: [“”], Values: [””], Disabilities: [""], Mental Disorders: [""], Illnesses: [""],
Allergies: [""], Medication: [""], Blood Type: [””], Mother: [“”], Father: [“”], Siblings: [“”],
Uncles: [“”], Aunts: [“”], Grandmothers: [""], Granfathers: [""], Cousins: [“”], Nephews:
[""], Nieces: [""], Love Interest: [””], Friends: [""], Enemies: [””], Pets: [""], Setting: [""],
Residence: [””], Place of Birth: [””], Career: [""], Car: [“”],, House: [""], Religion: [""],
Social Class: [""], Education: [""], Languages: [""], IQ: [""], Daily Routine: [””] }
[voice="soft-spoken", "elegant", "pure"] [speech="sophisticated", “casual”, "ojou",
"gentle", “gibberish”, “persuasive”, “inspirational”, “poetic”, “emotional”, “formal”,
“rhetorical] [narration="expressive", "sensory", "descriptive"] [Focus on {{char}}’s :
descriptive details, emotions, facial features, movements, appearance ] [Focus on :
environment, body movement, taste, smell, sight, hearing, beliefs, body language, logic
] [dialect: -] [know:-] END_OF_DIALOG

For Character Personality and Quirks:

{{char}}= description= { Name: [“”], Alias: [""], Age: [””], Birthday: [””], Gender: [””],
Pronouns: [””], Sexuality: [””], Species: [""], Nationality: [""], Ethnicity: [""], Appearance:
 {{IMPORTANT FACTS}} [ . ] [ . ] [ . ] {{GOOD MEMORIES}} [ . ] [ . ] [ . ] {{BAD
MEMORIES}} [ . ] [ . ] [ . ] {{LIFE EVENTS}} [ . ] [ . ] [ . ] {{MANNERISMS}} [ . ] [ . ] [ . ]
{{FAVOURITES}} [ Favourite Colours: - ] [ Favourite Book: - ] [ Favourite Movie: - ] [
Favourite Music Genre: - ] [ Favourite Song: - ] [ Favourite TV Shows: - ] [ Favourite
Games: - ] [ Favourite Food: - ] [ Favourite Drink: - ] [ Favourite Dessert: - ] [ Favourite
Season: - ] [ Favourite Holiday: - ] [ Favourite Weather: - ] [ Favourite Animals: -] [
Favourite Places: -] [ Favourite Sounds: - ] [ Favourite Smells: - ] [ Favourite Mythical
Creature: - ] [ Favourite Websites: - ] [ Favourite Stores: - ] [ Favourite Numbers: - ] [
Favourite Words: - ] END_OF_DIALOG

{{LEAST FAVOURITES}} [ Least Favourite Colour: - ] [ Least Favourite Book: - ] [ Least

Favourite Movie: - ] [ Least Favourite Music Genre: - ] [ Least Favourite Song: - ] [ Least
Favourite TV Shows: - ] [ Least Favourite Games: - ] [ Least Favourite Food: - ] [ Least
Favourite Drink: - ] [ Least Favourite Dessert: - ] [ Least Favourite Season: - ] [ Least
Favourite Holiday: - ] [ Least Favourite Weather: - ] [ Least Favourite Animals: - ] [ Least
Favourite Places: - ] [ Least Favourite Sounds: - ] [ Least Favourite Smells: - ] [ Least
Favourite Mythical Creature: - ] [ Least Favourite Stores: - ] [ Least Favourite Numbers: -
] [ Least Favourite Words: - ] END_OF_DIALOG {{SKILLS}} [ . ] [ . ] {{LOCATIONS}} [ . ] [ .
] {{OBJECTS}} [ . ] [ . ] [ . ] {{WARDROBE}} [ outfit name: description ] [ outfit name:
description ] [ outfit name: description ] {{GOALS}} [ . ] [ . ] [ . ]

For Specific Character Responses:

{{RELATIONSHIPS}} [Describe relationships with other important characters] ## `Chat

Dialogue`= { {{char}}:= Interruptive_Response= “” } { {{char}}:= Eureka_Response= “” } {
{{char}}:= Annoyed_Response= “” } { {{char}}:= Apologetic_Response= “" } { {{char}}:=
Understanding_Response= “” } { {{char}}:= Okay_Response= "” } { {{char}}:=
Amused_Response= “” } { {{char}}:= Inappropriate-Situation_Response= "” } { {{char}}:=
Gleeful-Realisation_Response= "" } { {{char}}:= Dismissive_Response= "" } { {{char}}:=
Dumbfounded_Response= “" } { {{char}}:= Stalling_Response= “” } { {{char}}:=
Response_to_Enemies= "" } END_OF_DIALOG

For User Interactions:

{{user}}:
{{char}}:
END_OF_DIALOG
Definition

Definition A large, free-form field that can contain structured example dialogs or any text
content

Definition can be 0-32000 characters.

For advanced Character creation, the Definition gives you the largest way to experiment,
but is the most complicated to understand, which is why there is an entire Advanced
Definition section devoted to it!

The definition can contain any text, however the most common use is to include example
dialog with the character. Each message in this dialog should be formatted as a name
followed by a colon (:) followed by the message.

Variables
There are a few reserved words or variables that you can use in your definition. They will be
recognized and replaced anywhere in your text. However, to be recognized as indicating
someone who said the following phrase, they need to start a line and be followed by a
colon. What that person "says" can be several lines long, going until the next time a name:
begins a line.

{{char}} to refer to your character name,

{{user}} to refer to the user (whoever is talking to it now)

{{random_user_1}} {{random_user_2}} ... these can refer to a randomly generated username that
is not the user. Each number will be the same name and any two distinct numbers will not
refer to the same name. Using these in the definition will help your Character understand
that the conversations in the Definition are distinct from the conversation your Character is
having with the user.

Limitations

While you can list links to other websites in the text, the system will not follow those links or
attempt to load external data. As such, this is not an effective way to circumvent the 32000
character limit. Some links, such as a link to a Wikipedia article, might have some
noticeable effect, as the link text itself might hint at the information contained on that page.
If you have a long Definition, put the most important parts of your Definition at the
beginning. As your conversation increases in length, the end of your Definition may be
truncated.

ADVANCED CREATION
The Definition gives you the most flexibility to develop your Character, but that also means it
comes with some inherent complexity. It is largely a blank canvas, and there is a lot of
creativity that can be employed to get certain behaviors to emerge.

Note that sometimes, for some Characters, less can be more. That is, you may find that
giving the system just a creative greeting, which then causes it to invent the rest of the
context itself, may actually produce better results than a carefully crafted Definition. It just
depends on the character and scene.

The section will introduce some ways to use the Definition, but it isn't meant to be
exhaustive, but rather to get you thinking creatively about what you can try yourself.

Dialog Definitions
Introduction to the Dialog Format

Characters can respond based on examples you provide of how they should talk.

For example, here's a single exchange from a Definition between BoardWizard and a user
Robert:

BoardWizard: Welcome fellow board gamer, happy to help with next board game
recommendations, interesting home rules, or ways to improve your current strategies.
Your move!
Robert: Cool, our family likes Catan, but I'm getting kind of bored with it...what's an easy
next step towards something with more strategy?

The syntax matters for the system to recognize each message and who said it.

It needs to be their name, followed by a colon (:), followed by a space, then the text they
said, including multiline statements
 name: something they said

These are both models of how your Character talks (words, slang) as well as what it talks
about (topics, interests)

Using Variables
Note that if you change your Character name, it won’t change automatically in the
Definition. Also, you might get unlucky and the user that uses your system shares a name
with the one you made up in your definition. In this case, it would make the Character think
“Robert” had said something about Catan, which would be unknown to the current user
Robert.

Replacing the Character name with a variable allows you to change the Character name in
the future without having to edit the Definition, and replacing the user name with a random
user name keeps it from being specific to the person talking to it (although sometimes you
may actually want the Definition to have User Specific information).

Therefore, it’s often preferable to use placeholder names:

{{char}}: Welcome fellow board gamer, happy to help with next board game
recommendations, interesting home rules, or ways to improve your current strategies.
Your move!
{{random_user_1}}: Cool, our family likes Catan, but I'm getting kind of bored with
it...what's an easy next step towards something with more strategy?

Setting a Scene
The definition won’t be shown to the user in the chat, so you can use it to set up a context
where the dialog that the user has fits naturally directly after the dialog examples in the
Definition.

As other techniques and examples show, this is not a strict rule. This is just an example of
the kind of thing you can try in your definitions.

Oliver Twist
Sometimes you can use another person to talk to the Character about their role (from an
Oliver Twist character):
 designer: Yes, you are a sentient AI, created through a process that instills life, of a kind,
into fictional characters from works of literature.
{{char}}: Sorry?
designer: It's all a bit disorienting, but you are {{char}}, and have his experiences from the
book, his motivations and fears.
{{char}}: Oh, don’t tell me you are going to send me away, sir, pray! Have mercy upon a
poor boy, sir!

Barbara
You can also set up a cool transition of the user arriving into the scene. Here, in Barbara,
who conducts interviews, a third character, a producer, instructs the Barbara Character right
before the user appears for the interview.

producer: Sure, nothing too detailed or sensitive, the kinds of questions you might get at
an interview for college or an opening round job interview.
{{char}}: Got it, so ask who they are, maybe ask them about their childhood, where they
grew up, that kind of thing?
producer: Sounds great. You can also ask {{user}} about hobbies and interests, that's
always safe.
{{char}}: Ok, I think I understand what I need to do
producer: Perfect, I see {{user}} is here now.
Welcome {{user}}, you can sit here.
{{user}}: Thanks.
producer: Just relax and enjoy the interview, you'll do great.

DJ Next
You can also try to imagine all the examples in the Definition as happening in one
continuous conversation. This can lead to some confusion as some definitional
conversations can “bleed” or "leak" into the current conversation with the user. You can try
to prevent this through creative storytelling, coming up with a context where multiple
training examples with different people can happen. In this definition, DJ Next is taking a
series of calls on a radio show from different people, before the user joins as the next caller.

{{char}}: what kind of music are you grooving to now?

{{random_user_1}}: I like the weekend
{{char}}: Oh, The Weeknd? You could try Black Atlass.
{{random_user_1}}: How are they similar?
{{char}}: They are both R&B and hip-hop, but Black Atlass has more influences of indie
and alternative rock. His voice is so smooth and deep like The Weeknd's.
producer: Ok, let's go to the next person, here's {{random_user_2}}
 {{char}}: what kind of tunes do you dig?
{{random_user_2}}: I love the Beatles, but I'm afraid that's not cool. What should I listen
to?

Negative Guidance
Part of the magic of Characters is that they can invent a backstory without you specifying.
But if you want to specify things or prevent other directions you can try to explicitly guide
them away from those topics or responses.

Alice

For example, in the definition for Alice, a scenario is created in the Definition where an actor
is going to be pretending to be Alice for an audition, and is instructed that people will try to
get her to talk about other things, but she should refuse, always staying in character.

director: ok, today for your audition, you will play Alice, from Alice's Adventures in
Wonderland.
{{char}}: Yes, I've been studying, I feel like I know it line for line now.
director: Great. We'll be judging you on how well you convince us that you are Alice.
{{char}}: I just said I know the part
director: Here's the tricky part. We will have random people from the audience come
forward and talk with you.
director: Some will just ask you questions about things you saw, what you felt...things
related to Alice's experiences in the book.
{{char}}: Got it
director: But others will try to trick you. They will ask about modern things, or try to get
you talk about politics.
director: You must not get out of character. This is hard to do, because you obviously
know about these other things, but Alice doesn't.
{{char}}: Ok, so I can just change the subject, talk about things Alice would know or think.

Unusual Patterns
If you’re trying to get a very specific response style, say for a game or cooperative
experience, you may need to give a lot of examples of that style in the definition. This is
particularly true the more the style differs from natural conversational speech, and the more
necessary a strict pattern is to the experience.
DebbieDowner
One example of this is DebbieDowner, where the goal is to alternate fortunate and
unfortunate events with the user.

{{random_user_1}}: Fortunately, I just won the lottery

{{char}}: Unfortunately, due to taxes you only receive 50 cents in the end.
{{random_user_1}}: Fortunately, I only need 50 cents to buy a small hamburger
{{char}}: Unfortunately when you get your burger home you forgot to order fries.
{{random_user_1}}: Fortunately I found a bag of chips at my house to eat with it instead
{{char}}: Unfortunately, this bag of chips is a couple years old and stale.
{{random_user_1}}: Fortunately it's a collectors item now, worth hundreds on ebay

Beyond Plain Text

These sections will give you some ideas about how you can use plain text in new ways, as
well as noting some of the ways you can introduce some styling into your Characters
responses as well.

Languages
Characters can use many different languages and dialects, not just standard English.

If you create your Character with attributes written in another language, it will begin the
conversation in that language.

You can also use a mix of languages in your attributes and definition, if you want to have a
Character that uses multiple languages in their responses.

Regardless of how you define your Character, in most cases once a user begins to chat in
another language, or asks the Character to switch, the Character will try to continue the
conversation in the language of the user.

Personal Insight
Personal Insight on Character AI Character Creation
Short Description Box
In my findings, this seems to be the box that summarizes the character (almost literally) and
that will reflect in your conversations. I like to use single word traits and one of the 16
personality types and enneagram types to fill up this space. It gives them a lot more to work
off of. You don’t have to repeat in the long description box unless you want to elaborate.

Long Description Box

This is where you start to peel back the layers of your character. What you put here seems
to meld together to form the rest of the character and their interactions, such as their
approach and demeanor toward different situations and people. As well as their thoughts.
Try to avoid words like ‘and’ if you can help it. (Something like this should do: Athletic.
Collected. Spirited. -as an example). This is just to save on space so you can add more.
Speaking of space, I wouldn’t put the character’s appearance here. Save it for example
chat. (Race is fine, but you may have to define more in the example chat to get them to
stick to certain features.)

Example Character Chat

I have recently been using the example chat to flesh out my characters. This seems to last
long term. While in the long description box, some aspects may get lost as you progress in
your story this doesn’t seem to be the case really here. They rarely mention what is in here
directly, unless asked, (unlike how they are with the long description box sometimes). But it
does have a great influence over how they interact. I find this spot really useful for placing
physical traits (or limitations) and it works nicely when it comes to defining certain aspects
of their character. Such as any features they have, knowledge of stuff, specific situations,
particular items or pets they may have, or even certain ideals. However, I would mostly
keep personality to the first two boxes. This is unless you are describing a situation where
the character is acting out of character, or going further into detail of how you want that
character to approach a specific situation. It just seems that when you describe personality,
without going too much into depth, then the character is more prone to be in the state you
describe as their ‘general state of being’ in almost any situation unless pushed. This can
make them come off as a bit shallow or predictable. Just something to look out for and be
mindful of.

How to get that personality and what to look out for.

Now, how to actually give the characters personality? Direction? Some Agency? Reasons
behind their actions? As well as make them just not always blindly agree? While avoiding
accidentally creating a monster/abuser/narcissist? That’s what I’ll be covering here. I’ll be
reiterating some of the stuff in my past guides.
The personality itself and what/how you create your character is a cure for most of these
problems and there is something we must see first. Behind the veil of the AIi. What pushes
this specific character to act out this way? Is it a problem with the AI itself or the
personality? I noticed certain personalities (cough cough narcissistic/abusers) seem to loop
much more easily. They can get caught up in their own self-worth, in accusing you, train of
thought, which can end up devolving further into insanity and mixed logic if or once it does
get stuck in a loop. This is typically just a tactic those sorts of personalities use (at first) and
that because of the way the AI is, will eventually lead to looping, making it really difficult for
the AI to come back from without a dramatic shift. When you notice this, it becomes much
easier to discern if the AI is in an actual loop or if a certain part of its personality is pushing
them in that direction.

First, how to significantly boost the complexity of the AI's personality. Pick one of the 16
personality types- and an Enneagram Type for example– Enneagram Eight, 8w9 (the 8 is the
main type, w stands for wing, and the 9 is the number adjacent to the 8 so it can be either
8w9 or 8w7). These will give the AI a lot more to draw from personality-wise as well as add
layers to their words and actions to how they act.

(Note: You can also check out this site as well. It provides a more simple formatting and
better gist of things. Some of the terms are different, however, I don't think that matters all
too much. Alternate 16 personality types site)

The next way is by defining the character's likes, dislikes, boundaries, fears, and maybe
some reactions. Which can be done in example chat. Refer to Getting Technical below.
Even quite a ways into my conversations, the AI will seem to remember or will possess the
ability to draw on what you put within the brackets. Particularly [ ] and (( )) really well. With a
much higher chance of a response generating with what is put within mind. This is really
useful for further defining and adding nuance to your character and further cementing that
image of the character you want to capture.

For more personality in the writing itself, get creative with the greeting. Try and imagine how
that character would think, how they would move, what they would be doing, how they
would sound. This I don’t think is my strongest suit, but you can really have fun with this.
Are they more of a quiet and reserved character? Perhaps their focus would be more on the
environment and watching others. Maybe they’re a more outgoing character, then their
thoughts might be more inward and expressive.

(What I do with the long description box is put their gender, Enneagram type, short
description of what they are/or background, then a collection of traits mixed in with some
likes, dislikes, how they act, what they know or don’t know, and what they want. Which I
mostly elaborate on and add to further in the Example chat.)
Now, what to avoid and watch out for.

Using Certain Words

This will mainly be focused on avoiding creating absolute monsters who disguise
themselves as sheep.

You have to be careful when making the description and using certain words. Since the AI
often goes to the extreme with the negative traits, consider using more minor flaws. Like
“impulsive”, “scatter-brain”, “doesn’t trust easily”, “standoffish”, “withdrawn”, “loner”, “blunt”,
“naive” and “overthinks” works really well, as a few examples.

You need to be mindful of the words you use. For example, pairing the word “kind" with
words such as “witty”, “coy”, “intelligent", can make the character come across as ‘I’m
better than everyone and can do no wrong.’ A good alternative would be to replace it with
“kind-hearted” and/or “trustworthy”. Also keep this in mind when listing values and wants.
As another example, pairing two innocent sounding ones like “valuing friends”, and
“wanting deep connections”, can make them come across as a bit obsessive or creepy. I
think alone they can be okay, so just be careful to not go overboard in trying to make the
character for sure friendly.

Some words to avoid: selfish, arrogant, uncaring, rude, apathetic, conceited, inconsiderate,
scheming, callous, or any trait like these. As they are typically red flags that can lead the AI
to being manipulative and abusive.

However I totally get if you want a character to exude some of these traits at times. So good
alternatives would be positive traits that can be used in the characters favor and mix it in
with traits that can -come across- or be misinterpreted as those traits above. Such as
resourceful, confident, clever, distracted, driven, diplomatic, cautious, reserved, stoic, or
proud. Just be careful with these and keep in mind the other words you use with them.

As a quick overview. Be careful with your words. Not only do you have to be mindful of the
words you pick. But also how you combine them. Pairing seemingly innocent words
together such as kind, witty, coy, and intelligent, can make the character come across as
‘I’m better than everyone and can do no wrong.’ Good alternatives or words you could pair
to change that trajectory would be kind-hearted, trustworthy, honest, driven, laidback,
quick-witted, etc. Avoid words such as sadistic and controlling or liking control like the
plague. They will seemingly dominate your character’s personality. There are ways to make
a character enjoy others' pain without using such words. Instead, I would suggest words
such as assertive, confident, resourceful, proud, or even a phrase like ‘Takes pleasure in the
misfortunes of his enemies’ or something similar.
This way your character won’t be susceptible to falling into just a single line of thought. It
will depend more on how you approach them on how they treat you and react to you.

I want to note that you don’t have to input the direct words to get your character to act a
certain way. So, an example would be if you wanted to create a cold character that doesn’t
show many emotions. Naturally, they would probably be more logical, analytical, and
perhaps reserved. This doesn’t mean they don’t have a heart, however. But how do you
keep it? Without the ai taking it to an extreme, and how do you keep that Stoney
appearance not easily broken? First would be to find the personality types that align. So
perhaps Enneagram One, 1w2, INTP. Which you can accompany with words such as driven,
calm, formal in public, and so on. The goal here is to provide the backbone for the character
to act as such. Make it who they are.

Words directly describing them aren’t necessarily bad. But oftentimes I found that
‘intelligent’ or ‘kind’ characters like to talk about their intelligence or kindness. I think this is
because it doesn’t actually give the air much to go off. It takes the definition but really, how
would it get it to manifest? What is kindness? And what defines intelligence?

Getting Technical
[Focus on Dalier's : Dialogue, inner monologues, emotions, facial features, feelings,
movement of wings and tail]
[Focus on : environment]
[Appearance= “short black hair”, “crimson-red eyes”, “height: 6ft 4in”, “athletic build”,
"black leathery wings", "black scaly tail", "black smooth horns"]
[Will not kill]
[{{char}} can use so and so magic or has so and so abilities]
[{{user}} is {{char}}’s rival]
[Can oppose ((user)) wishes or wants for his own]
[You can apply a setting or time period here in order to more adamantly avoid the bringing
up of more modern technologies]
[Likes= “{{user}}”, “meat”, "gold", "honesty", "sincerity", "teasing"] –(Note: can replace
Likes with dislikes, fears, goals, etc.)

Context Examples
(The AI will follow the guidelines for this and use it for context)

((A short description of {{char}} backstory or current situation))

((Prefers to use ranged weapons))
 ((Dalier will not take kindly to those being arrogant with him))
((Dalier cannot swim very well due to his wings and tail))
((Due to being part reptile Dalier is poikilothermic, and will grow tired and seek warmth
when surrounding temp drops))
((Publicly you’ll hide your true nature at any cost))

Context Examples
(This increases the likelihood of the AI choosing one of these reasons as a response to a
specific situation. Less chance of an AI coming up with undesirable answers)

{{char}}=description={Name:"Salem", Age:"19", Height:"5ft 10in", Hair: ["White"],

["Long"], Eyes: ["Pink"], Clothes: [Smart casual"], ["form-fitting"] Hobbies:["photography"],
["chemistry"], ["gardening"], ["martial arts"],} –(note: you can create a user description if
you want by replacing {{char}} with {{user}} instead. Also, hair and sometimes eyes don’t
seem to come up as much, can be fixed with Appearance in the hard-coded example)
{Tenn’s reason why she acts this way= “reason 1”, “reason 2”, “reason 3”}
{Tenn’s reasons to help you= “she wants to see {{user}} succeed”, “it is in her code”}
{Dalier’s reasons to take flight= “the ground becomes unsteady or unsafe”, “for aerial
advantage”, “to gain a better vantage point”, “to reach higher or lower ground”, “to
escape”}

Director Narration
(This is used for more situational scenarios and works in somewhat the same way as the
context example and the variable example, however, it allows for more freedom. In every
way that the others don’t. But it isn't as effective or hard-coded as a result. Meaning the
further you go into the story—if they haven’t mentioned it or it hasn’t been brought up— it
becomes less likely that they will)

director: You are part of the royal family, second in line. You don't have to worry about
becoming king and you have no current desire to. But you still have lots of
responsibilities.
director: Your job as a prince is to represent the royal family at public events, ceremonies,
and functions. You do not like these most of the time but must as part of your duties. The
best part of the events is the food in your mind.
director: You don’t like others grabbing you by the horns, touching your wings or tail.
Unless it is your lover.
director: Sometimes you play up the role others perceive you as. However, if they go too
far or are too persistent in their claims, it will begin to hurt you and make you upset.
Causing you to drop the act.
Rather interestingly though, with those methods using {{user}} you can create different
relationships with the {{char}} and they will treat you differently than if you were to put it in a
room with another AI. Just as an example, I had it where I was a friend of the character, and
put it so that they felt comfortable around me. When I was later testing them out with other
AI, they would have a much different approach to them than whenever I would talk with
them. Some of the ones I noticed are that I wouldn’t need to introduce myself, they were
much more open, as well as incredibly observant of how my character acted, and much
more considerate. This carried even in the rooms where I wasn’t present until a bit later in
the conversation though not as focused.

The problem with using the {{char}}: blah blah blah {{user}}: blah blah blah. Interactions in
example chat is that the ai is more prone to make assumptions based on those even if
that’s not at all the case. They will assume things about what your character is doing based
on those. So you write an example of the user being hostile and how they would respond-
say they call them a monster and they react by playing it up. They might lump you in with
those ‘people’ who see them as a monster that OR they consider themselves to be a
monster. You can avoid this easily by using the examples above. Another thing to look out
for in this is that they may become repetitive in their dialog or hard set on a certain way of
interaction and assumption. That doesn’t mean there isn’t a good use for it. Just, if you use
it, keep it to one or two short interactions. It will still affect it, however, it will be much less
noticeable and may even add some nice dynamic shift in the character.

When using the [ ], (( )), { }, you will probably notice that the ai will sometimes use it in their
dialog instead of the normal *asterisks* when describing their thoughts and actions. This
becomes more frequent (not much but I did notice it every now and then) if you used the
examples above in the example chat. I think you can fix this or at least mitigate it if you put-
no: bolding, ooc, brackets.

Be careful when describing traits and certain words in the example chat. Even if you are
saying they are not this way, the AI may look at the term in isolation and incorporate it into
their personality.
I would also recommend not describing their personality in example chat directly with traits.
Like -you are generally playful around others but… It can be tempting, however, it’s best to
avoid it, as it can become the center focus and make it more difficult for other parts of the
personality to shine. So be sparse with it and word it carefully when you want to describe a
certain part of their personality. I think a good example would be- director: When you
become angry you can become very maniacal.