Personas

Adding Personality to ChatGPT

Overview

Overview

A More Expressive ChatGPT

Why does every conversation with ChatGPT feel the same?

Whether I needed a curious brainstorm partner or a no-fluff explainer, I kept wishing ChatGPT could shift tone as easily as I shift tasks. Instead, I found myself coming up with personality prompts for each chat or tweaking global settings every time I wanted a mood change. These limitations led to the idea for Personas.

Problem

Users can’t easily switch ChatGPT’s personality per chat. They have to prompt it manually or change global settings.

Goal

Let users create and save personas so they can easily select a different one for each new chat.

Why not just use ChatGPT as it is?

ChatGPT is powerful, but not designed for character-driven conversations. If I want to keep a consistent personality, I have to tweak global settings, which affect every chat. But what if you want different voices for different contexts?

ChatGPT's chart interface with a personality prompt in the input bar.
ChatGPT's chart interface with a personality prompt in the input bar.
ChatGPT's chart interface with a personality prompt in the input bar.

What about custom GPTs?

Custom GPTs are great, BUT:

But they’re best for building tools, not personalities.

They’re siloed. Each Custom GPT lives in its own space, with no fast way to hop between personas or run multiple roles in the same session.

Personas could work with custom GPTs by letting users add personality to their custom GPT, blending character and function.

Screenshot of the "Explore Custom GPTs" page.

The "Explore Custom GPTs" page.

Expanding ChatGPT's Value

As model performance across competitors begins to level out, the next battleground is user experience. Personas would add to ChatGPT's value proposition by:

Encouraging personalization without potentially adding infrastructure costs.

Deepening engagement and session time by making users more entertained.

Adding value to the Pro plan as Personas can be framed as a Pro-exclusive feature.

Horizontal bar chart comparing the performance of major AI services, showing that most models now perform at similar levels.

AI intelligence comparison, June 2025, from artificialanalysis.ai

What Drives Engagement with Personas?

I used the Octalysis framework (a human-focused design model outlining eight core user motivations) to identify what would drive engagement with this feature. Personas create value by tapping into:

Core Drive 3: Empowerment & Creativity

Users get to create and customize personas to their liking.

“I created this persona, and now they’re talking to me the way I envisioned.”

Core Drive 4: Ownership & Possession

Users invest emotionally because they’ve created something uniquely theirs.

"These are MY personas. I like how I can switch between them based on my mood.”

Core Drive 5: Social Influence & Relatedness

Personas create a sense of tone, voice, and presence that makes chats feel less generic.

“I don’t just use ChatGPT. I talk to Clara when I want to learn something while laughing."

Core Drive 7: Unpredictability & Curiosity

Emergent characters unfold through dialogue, inviting users to discover how they evolve.

"I wonder what kind of characteristics this persona will develop over time."

Ethics & Responsible Design

OpenAI’s safety guidelines emphasize developing AI that benefits humanity while remaining safe and aligned with human values. Personas align with this by supporting expressive communication, not by simulating real relationships. This feature gives users ways to personalize tone and style, not too different from what they already offer with content & style customization in the settings panel. 

The goal is exploration, clarity, and customization, not companionship simulation.

Similar Products Out There

Similar products analysis.
Similar products analysis.

The Edge Over Similar Products: Emergent Personalities

Most platforms require users to define a personality up front: name, tone, rules, etc. But what if the character emerged through the conversation itself? The AI builds its persona organically, responding to cues and solidifying traits over time based on interaction. The result? Characters that feel more alive.

The Magic of It

No blank page paralysis: users don’t need to “design” a persona, they can just start talking.

More natural, dynamic interactions: It's like meeting someone new.

Discovery becomes part of the user experience.

Screenshots showing how emergent characters work.
Screenshots showing how emergent characters work.

Emergent personas evolve as you chat, shaped by your tone, topics, and the flow of the conversation.

define

Walkthrough

Walkthrough

Step 1: Discover the Personas Button

The persona switcher lives right above the chat history. It shows the current selected persona.

Screenshot of ChatGPT's chat screen with an arrow pointing at where the persona switcher on the top bar.
Screenshot of ChatGPT's chat screen with an arrow pointing at where the persona switcher on the top bar.

Step 2: Select a Persona, Browse the Store, or Create a New Persona

For this demonstration, let's take a look at the store.

Screenshot of the persona switcher panel open with an arrow pointing at the "Persona Store" button.
Screenshot of the persona switcher panel open with an arrow pointing at the "Persona Store" button.

Step 3: Select "Create" to Create a New Persona

Pick pre-made personas created by the community. Or build your own.

Screenshot of the persona store. An arrow points at the "Create" button.
Screenshot of the persona store. An arrow points at the "Create" button.

Step 4: Choose Your Creation Style

Emergent or Manual. Emergent lets you start chatting with a blank persona that unfolds naturally. Manual lets you define it yourself in just a few steps.

Screenshot of the modal that opens when user clicks on "create," listing two options: emergent creation, and manual creation.
Screenshot of the modal that opens when user clicks on "create," listing two options: emergent creation, and manual creation.

Step 5: Configure Your Persona

Let's say you select manual. From here, you can tell ChatGPT your requirements or fill in a few key details yourself to craft a personality that feels right for you.

Create Tab

Screenshot showing what the "create" tab looks like in the persona creation screen.
Screenshot showing what the "create" tab looks like in the persona creation screen.

Configure Tab

Screenshot showing what the "configure" tab looks like in the persona creation screen.
Screenshot showing what the "configure" tab looks like in the persona creation screen.

Step 6: Start a Chat and Switch Between Personas

Swap personas. Switch to a new persona mid-chat without losing flow.

Screenshot of the persona swicher with the newly created persona selected.
Screenshot of the persona swicher with the newly created persona selected.

Step 7: Chat Like Never Before

Every conversation feels alive.

Hover to slow down

deliver

Takeaways

Takeaways

Possible Ways to Test this Feature

Internal Dogfooding (Pre-Alpha)

Goal: Identify obvious UX flaws, edge cases, and memory issues.

Key Metrics: Frequency of persona swapping, drop-off rates during persona creation, clarity on emergent vs manual user flow, UI bugs.

Closed Beta with Power Users

Goal: Gather qualitative feedback and measure engagement.

Key Metrics: Persona creation rate, number of personas created per user, time to meaningful use, use cases, sentiment analysis survey, session length increase

A/B Testing in Public Rollout

Goal: Validate long-term retention and feature adoption impact.

Key Metrics: Session length, number of sessions per week, reuse rate of saved personas, upgrade intent for free users (if gated), AI alignment/safety flags.

Post-Launch Monitoring

Goal: Ensure ethical alignment and user satisfaction.

Key Metrics: Persona misuse reports, trends in emotional dependency language, requests for human-like interactions beyond feature scope, and feedback on tone and usefulness.

Impact

Increased retention and engagement: Giving ChatGPT a flexible personality system makes interactions feel more alive, encouraging longer sessions and repeated use.

Broader creative utility: Writers, roleplayers, and educators gain a reusable tool for storytelling, dialogue, and tone experimentation.

Enhanced product differentiation: Character Flow positions ChatGPT as not just functional, but expressive, adding emotional texture that competitors lack.

Vision for the Future

Persona Collaboration Mode: Enable two or more personas to work alongside the user, offering diverse perspectives (e.g., an optimist and a skeptic in the same conversation).

Persona-dependent memories: Each persona has its own persistent memory, allowing users to treat personas like consultants for specific things.

Cross-Platform Portability: Integrate with other tools (like Notion or Slack) to expand character-driven workflows beyond ChatGPT.

Let's work together

ri-moreira@outlook.com

Copy

OR

Let's work together

ri-moreira@outlook.com

Copy

OR

Let's work together

ri-moreira@outlook.com

Copy

OR

What about custom GPTs?

Custom GPTs are great, BUT:

But they’re best for building tools, not personalities.

They’re siloed. Each Custom GPT lives in its own space, with no fast way to hop between personas or run multiple roles in the same session.

Personas let users add personality to custom GPTs, blending function with character.

Screenshot of the "Explore Custom GPTs" page.
Screenshot of the "Explore Custom GPTs" page.

The "Explore Custom GPTs" page.

Expanding ChatGPT's Value

As model performance across competitors begins to level out, the next battleground is user experience. Personas would add to ChatGPT's value proposition by:

Encouraging personalization without adding infrastructure costs.

Deepening engagement and session time by making users more entertained.

Adding value to the Pro plan as Personas can be framed as a Pro-exclusive feature.

AI intelligence comparison, June 2025, from artificialanalysis.ai

Horizontal bar chart comparing the performance of major AI services, showing that most models now perform at similar levels.
Horizontal bar chart comparing the performance of major AI services, showing that most models now perform at similar levels.

What Drives Engagement with Personas?

The Octalysis framework is a human-focused design model that breaks down what motivates users into eight core drives to build more engaging and behaviorally effective experiences. Personas add value by tapping into:

Core Drive 3: Empowerment & Creativity

Users shape personas through creation or conversation.

“I created this persona, and now they’re talking to me the way I envisioned.”

Core Drive 4: Ownership & Possession

Users invest emotionally because they’ve created something uniquely theirs.

"These are MY personas. I like how I can switch between them based on my mood.”

Core Drive 5: Social Influence & Relatedness

Personas create a sense of tone, voice, and presence that makes chats feel less generic.

“I don’t just use ChatGPT. I talk to Clara when I want to learn something while laughing."

Core Drive 7: Unpredictability & Curiosity

Emergent characters unfold through dialogue, inviting users to discover how they evolve.

"I wonder what kind of characteristics this persona will develop over time."