Skip to main content

Custom GPTs

Feature Request

Similar to Chatgpt’s Custom GPT.

The Problem:

As a marketer with junior level React experience, I find ChatGPT's Custom GPT feature a major differentiator. The ability to discover, use, and share custom AI assistants created by others is incredibly valuable, especially for non-developers.

I know many users (especially non-developer) prioritize ease of use and readily available prompts over coming up with your own prompts. That’s because non-technical users often struggle with prompt engineering and prefer to use (and buy) readily available templates and pre-built solutions.

Currently the only AI platform (that I know of) that offers this is ChatGPT (and imo, is one of the reasons why people (i.e. non-developers) still use ChatGPT over Claude.

Here’s an example where these custom GPTs become very useful and valuable.

You can even see a growing trend of people searching for custom GPTs online:

Image 1

Image 2

Why This Would Work?:

T3 Chat’s biggest USP is the speed of its chats and the diverse model selection.

This allows T3 to have a competitive advantage:
- Neither Claude nor Gemini currently offer a comparable feature set.
- Unlike ChatGPT, T3 Chat can leverage its wide array of models to power custom GPTs, offering users greater flexibility and choice.
- T3 Chat's speed advantage will make it the preferred platform for interactive custom AI assistants.

Marketplace Potential: This feature opens the door to an internal marketplace where users can share, sell, or offer custom GPTs as lead magnets, driving user acquisition and engagement (similar to Dharmesh Shah's Agent AI concept).

Addressing Potential Concerns:

I understand (and suspect) that developers might not be the primary users of this feature.

But, a custom GPT marketplace can still benefit developers by:

- Accelerating Development: Developers can create and share custom GPTs for specific tasks, streamlining their workflows.

- Community Building: Fostering a community around custom GPT creation and sharing.

- Showcasing T3 Chat's Capabilities: Demonstrating the platform's flexibility and power to a wider audience.

Financial Incentive for T3 Chat:

I think you could charge this in your next tier ($20+ ) and people would happily pay for it.

It would also keep developers happy because they are not wasting money on features they might not need.

If you couple this feature with the features like shareable link + browsing the web, I don’t know why anyone would ever pay for Claude, ChatGPT or even Gemini.

Status: Gathering Interest26 comments

Log in to comment and vote

Comments26

  • Plum Pen

    +1, but just basically for exposing model params like system prompt and temperature, and letting us save those as chat presets. Don’t need much more than that.

  • Apricot Mat

    It wouldn’t have to be as full-blown as OpenAI’s system.

    Simply an editable library of pre-canned system messages would be ideal.

    (Public sharing would be a nice to have, but far from essential.)

  • Purple Star

    Oh, forgot to mention, presets may also not be an awful place to expose:

    • temperature settings

    • “Customize T3 Chat” overrides

    • per-model params (reasoning effort, quality, size, variations)

    • return type rendering methods (e.g. image returns, artifact/canvas prompts)

    • other power-user suggested customization that complicate new-user on-boarding

      • e.g. templating

      • model selction parameters

      • custom emoji

      • debug display of prompt inputs

      • feature flags for experiments

        • “continue generating” buttons

        • “retry” button

  • Maroon Canteen

    I would very much like custom GPT’s I use a custom GPT on chat gpt currently to help write emails. And it limits me after a few messages. I’m already paying for t3 chat id like the option to just not have to use ChatGPT

  • Black Pumpkin

    I use this in ChatGPT to store and reuse my system prompts. It would be great to be able to do something similar in t3.chat.

    Not to mention templates, which is a kinda different feature but I would love to have something like that.

    Sometimes I feel like we are stuck in the “chat” display, maybe it’s time to give a try to Google’s NotebookLM

  • Purple Star

    edit: nevermind, those are about slightly different concepts/features

    ~After a more thorough read of feature requests, I am possibly duplicating~:

    ~Unclear if they’re looking for “per message” or “per conversation” adjustment, but definitely didn’t find these on my initial search~

  • Purple Star

    To describe better describe how “others” do this, a prompt I’ve seen for user styles explains the situation and problems/resolutions with it, but avoids confusing things by providing example “styles”. I’m sure that versions of these prompts can be easily located.

    Here is the broad strokes of claude’s implementation (without providing the exact text):

    Providing Context:

    • Clarify Available Options - Explains what choices are available to the user (e.g., selecting a specific Style) to prevent unexpected behavior.

    • Set User Expectations - Informs both the assistant and, indirectly, the user about the mechanisms in place, ensuring that any behavior (like a style change) is predictable and transparent.

    • Maintain Continuity - Reminds the system that earlier style instructions (potentially from previous interactions) might still be influencing behavior, ensuring consistency throughout the conversation.

    Instructing:

    • Direct Action - Clearly tells the model how to adjust its responses—for example, by specifying that it should adopt a particular style or tone when instructed.

    • Guide Behavior Adjustment - Provides explicit commands for the assistant on how to modify its output in response to user instructions, ensuring that changes occur as intended.

    Conflict Resolution:

    • Prioritization Mechanism - Outlines how to handle situations when user instructions conflict—for instance, indicating that the assistant should follow the latest non-style instructions if they differ from the active style.

    • Clarification in Discrepancies - Describes what the assistant should do when there is a divergence between current style settings and new user directives, ensuring that the assistant resolves any conflicts in a consistent, predictable manner.

  • Blue Raccoon

    It’s a feature that I miss the most from OpenAI, there are some things specific to some project or programming language that we need to preprompt in all new chats to get good results. While there’s an option for general preprompt we lack the option to save and choose different preprompted models that are already tuned for some general area of conversation, like cooking advices, working with Unity DOTS or doing translations.

  • Salmon Jaguar

    This is just an amazing feature to have! But I would love to have a somewhat watered down version of it too like Claude's modes (concise, explanatory, etc…) which I could swap quickly in the chat UI, looking forward to how the best of both these worlds could be implemented in t3chat

  • Red Pineapple

    I’m a fan of this but the other ticket for creating projects with bounded context and additional prompts, coupled with sharing effectively creates a similar functionality without obfuscating the mechanism that the “GPT” was created by.

    i.e. you clone my project and can look at my prompts and resources, and can then tweak them to suit your use case.