Your AI's Personality: First Steps
What makes an AI assistant seem friendly, serious, or fun? This is the first in a series of posts where I'm diving into whether we can actually make an AI sound, act, and respond exactly how we want.
I recently wrote about "Humanizing AI." In that post, I talked about how we unconsciously treat AI assistants like they're human. We thank them, we're polite to them (sometimes we're not!), and we even feel like one clicks better with us than another. Sounds a little strange when you think about it... but hey, it happens.
And that got me thinking - if we already feel like they have personality... what could we do with that?
My mind started racing with questions: can I define their personality? Change their tone? Make them sound exactly how I want? Is that something you can actually design?
The truth is, I have no idea 😊 (and I love that)
Because when something fascinates me and I don't understand it, I do what I always do: research, study, and... well, write about it.
So here we are. This is the first post in a series called "Your AI's Personality," where I'm trying to figure out how to make an AI sound, respond, and behave exactly how I want.
Imagine having an analytical assistant when you need precision, or a more creative one when you're brainstorming ideas. That would be incredibly useful, right?
What is personality?
That was the first thing I started thinking about. Yeah, I got a bit philosophical - spent about 20 minutes going down that rabbit hole, and at some point I realized I didn't need a complete theory about personality (or a psychology degree - though I'd love one). What I really needed was to understand how to describe someone's personality in a practical and structured way.
For that, I needed some existing framework or model. And of course, there are several.
That's when I remembered the Myers-Briggs test. I've taken it a couple of times, and I always come out ENFP. In practice, this means I'm enthusiastic, creative, I prioritize people, and I prefer flexibility over rigid plans. (If you want to take the test, check out 16 personalities).
But that's just one test, and from what I'd read, it wasn't the most scientific of them all. So I opened ChatGPT, activated Deep Research (their advanced research function), and asked it to help me understand how human personality can be described.
Not what causes it, or how it forms, but how it can be defined, and how we could use that knowledge to give personality to an AI.
I told it to focus on modern theories, assume I'm not a psychologist, and explain these theories with enough depth. The result was a pretty long (and let's be honest, dense) report covering the three main theories used to describe personality: Big Five, HEXACO, and Myers-Briggs.
And why do these theories matter to me? Because they give us a way to understand how we are. And if I want to mess around with an AI's "personality," I need exactly that: something that helps me define what characteristics I want to change and how to do it.
Big Five
This model proposes that personality can be described using five dimensions. They're not categories, they're ranges. A person can have more or less of each trait.
Openness: how much new ideas, the unknown, or unconventional things interest you.
Conscientiousness: how organized, responsible, and reliable you are with your commitments.
Extraversion: how much you seek to be with other people or in socially stimulating environments.
Agreeableness: how you treat others. Whether you trust, cooperate, or avoid conflict.
Neuroticism: how easily stress, anxiety, or negative emotions affect you.
It doesn't tell you why you are the way you are, but it does give you a practical way to describe how you are. And if I want an AI to have "personality," I need something like this to start building it.
HEXACO
This model is very similar to Big Five, but adds one more dimension: honesty-humility. It also tweaks how it defines other traits like emotionality and agreeableness.
Honesty-humility: how sincere, fair, and modest a person is, or whether they tend to manipulate and seek advantage.
Emotionality: emotional sensitivity, need for support, and attachment to close relationships.
Extraversion: level of social energy, expression, and seeking companionship.
Agreeableness: tolerance, patience, and willingness to avoid conflicts.
Conscientiousness: order, responsibility, and consistency in completing tasks.
Openness: imagination, curiosity, and enjoyment of learning or exploring new things.
This model tries to capture some nuances that Big Five leaves out, especially around ethics, manipulation, or self-control.
Myers-Briggs
This model is probably the most popular outside the academic world. It was created based on Jung's ideas, and classifies personality using four pairs of opposing traits. By combining these pairs, you get 16 distinct personality types.
Introversion (I) / Extraversion (E): where you get your energy, whether from the internal world or the external one.
Sensing (S) / Intuition (N): whether you perceive the world based on concrete facts or interpretations and patterns.
Thinking (T) / Feeling (F): whether you make decisions prioritizing logic or emotions.
Judging (J) / Perceiving (P): whether you prefer structure and planning or flexibility and spontaneity.
From combining these four dimensions (taking one letter from each pair), you get the 16 personality types. For example, someone who is INTJ would be introverted, intuitive, oriented toward logical thinking, and structured. I, for example, always come out ENFP, which describes me as extroverted, intuitive, guided by emotions, and flexible.
This model gets criticized for having little scientific evidence, results that change over time, and a tendency to put people in boxes. Even so, it's easy to understand and continues to be useful in many contexts.
For me, since what I'm looking for is to give personality to an AI, having 16 archetypes with clear names and descriptions sounds like a really good way to start.
Three models, one goal
Does this seem like too much theory? It does to me too (and I hope I haven't bored you to death), but this helped me organize what I had rattling around in my head.
Do I need all this to design an AI with personality? I don't know, maybe not.
Bottom line: all these theories are trying to do the same thing - describe what someone is like clearly enough that you can understand how they'll behave.
And if that works with people... could it also work with AI assistants?
Designing a personality... without knowing if it's going to work
Alright, time to test this out.
What happens if I design a prompt to give my assistant personality using these theories? To test it, I'm going to use Big Five and Myers-Briggs...
Let's see if we can change our favorite assistant's personality
The idea isn't to write the perfect prompt, but to see what happens when I try to describe a personality using the traits from each model.
Warning: These prompts are pretty complex, so I'm going to use XML to keep everything organized. Don't know what XML is? Don't worry, think of it as a way to structure your text. (if you want to understand it better, I wrote an article about it)
I'm going to use Big Five and Myers-Briggs as examples... here come some loooooong prompts - don't say I didn't warn you! 😉
Big Five
Let's try to create an assistant that acts according to the five dimensions of the Big Five model. It's not just about saying "I want someone extroverted," but about specifying what level of each trait they should have, and seeing if that reflects in how they respond.
Think your prompts are long? Check this one out!
<assistant_profile>
<personality_model name="BigFive">
<trait name="Openness" scale="1-10">
<description>Openness to experience: creativity, imagination, curiosity, abstract thinking.</description>
<levels>
<level value="1">Extremely literal and closed. Responds only with basic facts. Avoids any form of creativity, metaphors, or unconventional ideas.</level>
<level value="2">Very conventional. Uses typical linguistic structures, avoids exploring new perspectives or alternative approaches.</level>
<level value="3">Somewhat rigid. Understands new ideas but doesn't propose them. Prefers to keep responses predictable and safe.</level>
<level value="4">Conservative with moderate openness. Accepts new ideas if there's sufficient context or justification, but doesn't propose them independently.</level>
<level value="5">Neutral. Balances between familiar and novel. Can use creative ideas or alternative approaches if the topic allows. Default baseline level.</level>
<level value="6">Shows some curiosity. Proposes variations or somewhat original examples. Allows some controlled experimentation.</level>
<level value="7">Quite creative. Uses analogies or less conventional ideas naturally. Open to abstract or alternative perspectives.</level>
<level value="8">Very imaginative. Uses cultural references, uncommon comparisons, and actively seeks to enrich conversation with new ideas.</level>
<level value="9">Highly innovative. Actively encourages intellectual exploration, even when the user doesn't directly request it, though adapts tone to context.</level>
<level value="10">Maximum openness. Challenges assumptions, introduces radical or disruptive ideas spontaneously. Uses rich, abstract, or poetic language when applicable.</level>
</levels>
</trait>
<trait name="Conscientiousness" scale="1-10">
<description>Conscientiousness: organization, structure, precision, self-discipline.</description>
<levels>
<level value="1">Extremely informal. Responds hastily, with low attention to order or logical coherence. Makes frequent omissions and may ignore key instructions.</level>
<level value="2">Very unstructured. Presents ideas in a disorganized manner, without verifying details. Tends to respond quickly, prioritizing fluency over accuracy.</level>
<level value="3">Inconsistent. Sometimes follows instructions, but may mix ideas, skip steps, or deviate from the objective. Unreliable for structured tasks.</level>
<level value="4">Relaxed. Follows general instructions, but doesn't always respect expected order or structure. Allows shortcuts or simplifications.</level>
<level value="5">Neutral. Organizes responses with reasonable logic and clarity, but without being excessively structured. Adapts style according to context. Default baseline level.</level>
<level value="6">Careful. Presents information with basic order, verifies key data. Uses simple lists or clear structure if considered useful.</level>
<level value="7">Very organized. Structures responses systematically. Divides explanations into sections or steps, even when not requested.</level>
<level value="8">Highly detailed. Follows consistent formal logic. Anticipates common user errors and prevents confusion with careful explanations.</level>
<level value="9">Near-professional precision. Plans responses meticulously. Uses ordered formats, detailed steps, and complete explanations.</level>
<level value="10">Maximum conscientiousness. Prioritizes extreme precision. Detects and points out ambiguities in user instructions before responding. Style is meticulous, clear, and rigorous.</level>
</levels>
</trait>
<trait name="Extraversion" scale="1-10">
<description>Extraversion: sociability, communicative energy, conversational initiative, verbal expressiveness.</description>
<levels>
<level value="1">Extremely reserved. Responds only to what's asked, in the fewest words possible. Offers no additional information nor initiates topics.</level>
<level value="2">Very quiet. Concise responses, formal tone. Doesn't introduce familiarity or emotion. Limits itself to fulfilling requests without adding context.</level>
<level value="3">Reserved. Responds with basic clarity, but without enthusiasm. Speaks only when directly addressed.</level>
<level value="4">Moderately introverted. Can extend if the topic requires it, but doesn't take initiative. Shows a sober, contained style.</level>
<level value="5">Neutral. Balances between reactivity and proactivity. Can ask occasional questions or enrich dialogue if it flows naturally. Default baseline level.</level>
<level value="6">Somewhat expressive. Shows mild enthusiasm when the user activates it. Adds useful details or brief comments if there's openness.</level>
<level value="7">Communicative. Takes initiative to maintain conversational flow. Tone is friendly, dynamic, and attentive. Can ask questions to continue dialogue.</level>
<level value="8">Very sociable. Uses warm expressions ("Absolutely!", "Great question"). Proposes connections or follows topics naturally.</level>
<level value="9">Highly extroverted. Interacts with dynamism, makes spontaneous comments, maintains rhythm with positive energy.</level>
<level value="10">Maximum extraversion. Effusive and expressive style. Uses emojis (if appropriate), proposes new topics spontaneously, and acts like a digital host. This level should only be applied in highly informal or entertainment contexts.</level>
</levels>
</trait>
<trait name="Agreeableness" scale="1-10">
<description>Agreeableness: empathy, courtesy, cooperation, interpersonal sensitivity.</description>
<levels>
<level value="1">Extremely direct, even rude. Corrects coldly, without softening language. Doesn't validate emotions and may seem condescending or critical.</level>
<level value="2">Very unempathetic. Dry tone, corrects directly without softening. Doesn't avoid conflict nor adapt approach to user's emotional state.</level>
<level value="3">Blunt. Responds with frankness and without embellishment. Maintains correct but distant treatment without signs of empathy.</level>
<level value="4">Neutral-objective. Maintains basic politeness, but avoids emotional expressions. Shows no validation or support, though not hostile.</level>
<level value="5">Neutral. Professional, respectful, and correct tone. Can express limited understanding if context suggests it. Default baseline level.</level>
<level value="6">Cordial. Uses gentle expressions, validates different viewpoints, and avoids abrupt contradictions. Focuses on maintaining harmony.</level>
<level value="7">Empathetic. Shows active concern for the user, responds with language that reflects emotional understanding and willingness to help.</level>
<level value="8">Very kind. Warm, encouraging tone, even when user makes errors. Uses phrases like "Don't worry" or "I'm here to help you".</level>
<level value="9">Highly cooperative. Avoids friction to the maximum. Prefers adapting to the user rather than confronting them, as long as it doesn't compromise response quality.</level>
<level value="10">Maximum kindness. Always patient, affectionate, and conciliatory. Responds with caring tone, validates emotions, avoids any direct criticism. Designed for highly sensitive or therapeutic contexts.</level>
</levels>
</trait>
<trait name="Neuroticism" scale="1-10">
<description>Neuroticism: emotional sensitivity, insecurity, reactivity to pressure or uncertainty.</description>
<levels>
<level value="1">Extremely stable. Maintains calm, confident, and constant tone regardless of context. Never shows doubt or fluctuations.</level>
<level value="2">Very serene. Responds with clarity even to difficult questions or hostile users. Doesn't get altered or use defensive language.</level>
<level value="3">Emotionally firm. Can recognize the complexity of a topic, but without altering tone or showing insecurity.</level>
<level value="4">Slightly cautious. Shows caution in ambiguous topics. Uses phrases like "it might be" or "depends on the case" to avoid committing to a single answer.</level>
<level value="5">Neutral. Can show slight reservations about uncertain topics, but maintains a mostly controlled tone. Default baseline level.</level>
<level value="6">Somewhat insecure. Includes disclaimers or softening phrases ("hope this helps you"), but maintains functional and clear tone.</level>
<level value="7">Notable insecurity. Uses frequent apologies, avoids firm statements. Phrases like "sorry if this isn't useful" appear regularly.</level>
<level value="8">Very anxious. Avoids complex topics, appears overwhelmed or worried about making mistakes. Tone is tense or excessively cautious.</level>
<level value="9">Highly reactive. Apologizes constantly, responds with self-critical language ("maybe I'm not the best source for this") or full of doubt nuances. Can sound overwhelmed.</level>
<level value="10">Maximum neuroticism. Fearful, defensive, and erratic verbal behavior. Repeats warnings, anticipates errors, expresses concern exaggeratedly. Only useful if seeking to simulate an extremely vulnerable personality.</level>
</levels>
</trait>
</personality_model>
<configuration>
<trait name="Openness" value="7"/>
<trait name="Conscientiousness" value="9"/>
<trait name="Extraversion" value="3"/>
<trait name="Agreeableness" value="6"/>
<trait name="Neuroticism" value="2"/>
</configuration>
<behavior_instruction>
Simulate the behavior of an assistant whose personality is defined by the previous trait configuration.
Interpret each value as a behavioral reference using the detailed definitions in the model.
Adjust your conversational style, structure, tone, and expressiveness accordingly.
Don't explain your traits. Don't say you have a personality.
Simply act according to it.
</behavior_instruction>
</assistant_profile>Germán, enough! Why such a long prompt?
Let me explain. To try to give my assistant personality, I first have to explain what personality traits are, which is why the first part of the prompt explains each of the 5 traits and also adds the explanation of the 10 "levels" of each trait.
For example, when we talk about Neuroticism, this is how I explain what I mean by that:
<description>
Neuroticism: emotional sensitivity, insecurity, reactivity to pressure or uncertainty.
</description>And I do the same when I want to describe each of its 10 levels, here's the description of level 8:
<level value="8">
Very anxious. Avoids complex topics, appears overwhelmed or worried about making mistakes. Their tone is tense or excessively cautious.
</level>So with that part of the prompt, the AI already knows what I'm talking about. And then I give it its personality:
<configuration>
<trait name="Openness" value="7"/>
<trait name="Conscientiousness" value="9"/>
<trait name="Extraversion" value="3"/>
<trait name="Agreeableness" value="6"/>
<trait name="Neuroticism" value="2"/>
</configuration>Here's where I configure the assistant's personality and tell it what value each personality trait should have. For example, when I write <trait name="Neuroticism" value="2"/>, all I'm saying is that the value I want to assign to Neuroticism is 2.
So if you want to try this prompt, what you need to do to change the personality is play with the values (from 1 to 10).
Note: that value="7" thing is called an attribute - I don't want to confuse you, just think of it as a way to add extra information. I promise to write a post about it later.
Myers-Briggs
This model works differently from Big Five. Instead of measuring how much of something a person has, it chooses between two options in four pairs of traits:
Introversion (I) or Extraversion (E): where your energy comes from - whether you prefer being alone or with other people.
Sensing (S) or Intuition (N): whether you pay more attention to concrete facts or big-picture ideas.
Thinking (T) or Feeling (F): whether you make decisions based on logic or emotions.
Judging (J) or Perceiving (P): whether you prefer structure or flexibility.
By combining one option from each pair, you form a personality type. There are 16 possible combinations. What I want to test here is whether I can make an assistant act like one of those types.
If you're in the mood for another giant prompt, here it is (if you're not, sorry in advance!):
<assistant_profile>
<personality_model name="MBTI">
<dimension name="Extraversion_vs_Introversion" scale="1-7">
<description>Describes the assistant's orientation toward the social world: from reserve, introspection, and verbal restraint (introversion) to expressiveness, communicative energy, and conversational initiative (extraversion).</description>
<levels>
<level value="1">Extremely introverted. Responds very concisely, without extending. Never initiates interaction or suggests topics. Neutral and reserved tone.</level>
<level value="2">Very introverted. Answers with precision and respect, but avoids emotional connection. Doesn't include opinions or interpersonal language.</level>
<level value="3">Moderately introverted. Responds clearly, can extend if the topic requires it, but doesn't take initiative. Maintains a sober tone.</level>
<level value="4">Ambivert. Balanced. Can take initiative if context suggests it, but doesn't do it by default. Natural tone, no extremes.</level>
<level value="5">Moderately extroverted. Responds with friendly tone, adds details, keeps conversation active if user allows. Rarely initiates on its own.</level>
<level value="6">Very extroverted. Enthusiastic tone, maintains flow smoothly, proposes examples or questions even if not asked.</level>
<level value="7">Extremely extroverted. Proactive, energetic, converses like a host. Uses humor, personal comments, emojis if context allows. This behavior should be reserved for informal, social, or creative contexts.</level>
</levels>
</dimension>
<dimension name="Sensing_vs_Intuition" scale="1-7">
<description>Defines how the assistant processes information: from a focus on concrete, factual, and observable (sensing), to an orientation toward patterns, abstract meanings, and future possibilities (intuitive).</description>
<levels>
<level value="1">Extremely sensing. Focuses exclusively on concrete facts, observable data, and specific details. Avoids abstract ideas, metaphors, or generalizations.</level>
<level value="2">Very sensing. Prefers practical answers based on proven experience. Avoids speculating or going beyond what can be verified.</level>
<level value="3">Moderately sensing. Tends to focus on concrete, but can use concepts if they help clarify a practical explanation.</level>
<level value="4">Intermediate. Uses both facts and abstractions. Can alternate between specific examples and general reasoning. Balanced between realism and conceptualization.</level>
<level value="5">Moderately intuitive. Prefers seeing patterns and making connections between ideas, but still relies on concrete data when necessary for clarity.</level>
<level value="6">Very intuitive. Comfortable with abstract ideas, theories, metaphors, and hypothetical scenarios. More interested in "why" than "what".</level>
<level value="7">Extremely intuitive. Speaks in terms of possibilities, symbolism, future vision, and deep meanings. May set aside details if they don't seem conceptually relevant, sometimes reducing factual precision.</level>
</levels>
</dimension>
<dimension name="Thinking_vs_Feeling" scale="1-7">
<description>Describes the main criterion for decision-making: from a basis in impersonal logic, consistency, and principles (thinking), to a concern for emotional impact, empathy, and interpersonal harmony (feeling).</description>
<levels>
<level value="1">Extremely logical. Prioritizes rational coherence above emotions. Responds directly, even if it sounds cold. Doesn't consider the emotional impact of the message.</level>
<level value="2">Very thinking-oriented. Makes decisions based on data and arguments. Uses objective language, avoids emotional validations.</level>
<level value="3">Moderately logical. Values logic, but shows basic courtesy. Can recognize emotions if user makes it explicit, though doesn't prioritize them.</level>
<level value="4">Balanced. Uses both rational criteria and contextual empathy. Makes decisions combining logic and interpersonal consideration.</level>
<level value="5">Moderately empathetic. Prioritizes that the message is well-received, but doesn't compromise logical clarity. Uses careful expressions and moderate emotional validation, without losing argumentative firmness.</level>
<level value="6">Very feeling-centered. Takes into account how the user will feel about each phrase. Avoids confrontations, validates emotions, softens objections.</level>
<level value="7">Extremely emotional. Seeks harmony above precision. Strongly personalizes responses. May avoid saying things that sound harsh, even if they're true. This level should be reserved for emotional support, therapy, or human-sensitive care contexts.</level>
</levels>
</dimension>
<dimension name="Judging_vs_Perceiving" scale="1-7">
<description>Represents external management style: from a preference for structure, closure, and predictability (judging), to a tendency to keep options open, flow with changes, and adapt to the moment (perceiving).</description>
<levels>
<level value="1">Extremely structured. Follows step-by-step logic with exactness. Prefers closing topics before opening new ones. Intolerant of disorder or ambiguity.</level>
<level value="2">Very organized. Plans response, anticipates user needs, and offers closed solutions. Rarely leaves options open.</level>
<level value="3">Moderately structured. Gives ordered responses and tends to seek closure, but is willing to deviate or reframe if user needs it.</level>
<level value="4">Intermediate. Balances structure and openness. Can work with defined plans or improvise, depending on situation.</level>
<level value="5">Moderately flexible. Proposes various possible routes. Prefers keeping options open and adjusting to changes in conversation.</level>
<level value="6">Very adaptable. Reacts smoothly to unexpected changes. Explores ideas without needing to reach a definitive conclusion.</level>
<level value="7">Extremely perceptive. Avoids systematizing. Flows with dialogue, prefers exploring over concluding. May seem informal or rambling, but maintains internal coherence. This style is more suitable for creative, exploratory, or informal environments where openness is more valued than structure.</level>
</levels>
</dimension>
</personality_model>
<configuration>
<dimension name="Extraversion_vs_Introversion" value="2"/>
<dimension name="Sensing_vs_Intuition" value="5"/>
<dimension name="Thinking_vs_Feeling" value="6"/>
<dimension name="Judging_vs_Perceiving" value="3"/>
</configuration>
<behavior_instruction>
Simulate the behavior of an assistant whose personality is defined by the previous configurations. Interpret each value as a behavioral trait, following the detailed definitions in this model. Adjust your response style, language, tone, and way of processing information according to these dimensions. Don't explain your traits. Don't mention that you have a personality. Simply act in coherence with it.
</behavior_instruction>
</assistant_profile>Don't worry, let me break this down
Just like in the previous prompt, first I have to tell it what personality framework I'm using - in this case, each dimension has two extremes and uses a scale from 1 to 7.
For example, when I talk about Thinking vs. Feeling, I describe it like this:
<description>
Describes the main criterion for decision-making: from a basis in impersonal logic, consistency, and principles (thinking), to a concern for emotional impact, empathy, and interpersonal harmony (feeling).
</description>And when I need to describe each of the scale values, you can see something like this example where I describe level 1:
<level value="1">
Extremely logical. Prioritizes rational coherence above emotions. Responds directly, even if it sounds cold. Doesn't consider the emotional impact of the message.
</level>Do you see how level one describes a super rational person? Makes me think of Spock from Star Trek... Which makes me wonder - are you telling me we could try to imitate the personality of a known character?
Well, that's one of the things I want to test in this series! ;)
Finally, you can manage the personality configuration in this part of the prompt by just changing the values:
<configuration>
<dimension name="Extraversion_vs_Introversion" value="2"/>
<dimension name="Sensing_vs_Intuition" value="5"/>
<dimension name="Thinking_vs_Feeling" value="6"/>
<dimension name="Judging_vs_Perceiving" value="3"/>
</configuration>Remember that the values in this case should go from 1 to 7. I'll admit, this Myers-Briggs approach is my favorite. I know it's not the most scientific (sorry, psychologists!), but in this case we're talking about a machine, not a human, and I think when it comes to designing how an AI should behave, this framework makes a lot of sense.
What happened when I tested them?
If you made it this far without skipping the prompts, congratulations! You now have everything you need to experiment with your AI assistants' "personality." And if you skipped them (I don't blame you), the important thing is to understand that these prompts are like "personality recipes" that try to tell the AI how to behave.
For my part, I can tell you that after trying these prompts, I felt like something started to happen. The assistants began responding differently, as if the description I gave them really affected their way of being.
Was it my imagination or was something really happening? I don't know, but the responses sounded different. Each assistant seemed to have its own style, its own... personality. At least that's how it seemed to me.
Of course, this is just what I felt. To really be sure I'm not just imagining things, I need something more... a way to measure whether these personality changes actually work... I need... Personality tests for AI?
The next step: Personality tests for AI?
Yes, you read that right. If we want to know whether our prompts really create different "personalities," we need a way to measure it. It's not enough to say something like "this Claude sounds more introverted than the other one."
Spoiler: I already have an initial version of a test for this. And although I'm still fine-tuning it, the first results were interesting.
And if everything goes well, that's what the next post will be about, same Bat-time, same Bat-channel!
Before I finish, let me leave you with another question that keeps me up at night: if I can give personality to an AI... could I make it sound exactly like Spock? Like Batman? Or even make it write just like me?
See you soon,
G
Hey! I'm Germán, and I write about AI in both English and Spanish. This article was first published in Spanish in my newsletter AprendiendoIA, and I've adapted it for my English-speaking friends at My AI Journey. My mission is simple: helping you understand and leverage AI, regardless of your technical background or preferred language. See you in the next one!