Custom GPTs

Range of models to explore. Remember these are first, not final drafts, please always remember to check facts and edit.

Primary Prompt Information (AI only)

Primary Prompt information for client:

End Primary Prompt information.

Guidance & Updates

Dev Updates

Notice: Deletion of all past chats in the system is June 30th.

Known bugs:

Cache errors (please just refresh)


6/10/2024: Improved voice-to-text speed, high-quality model access for all chats, right click delete/edit for the /memory chats.

5/29: Fixed voice to text option. Try this for refining prompts.
5/16: HUGE upgrade to Chat with PDF feature to Opus model 150k context and GPT 4o PDF threaded chat.

5/13: GPT4o, adding to all chats and Data Analysis GPT.

5/10: Improved the audio to text option in chats
5/2: Added Gemini Image generator & Google Gemini Pro 1.5 with 2M word context window now in chat memory section

4/30: Backend update preparing for Functions, GPT5 & new Assistants API, added Vector Databases

4/2: Memory Chat allows history to be accessed. New beta interface.

3/27: Updated PDF Chat to allow copy and quicker upload.

3/16: Added a bug submission tool, wiped old discussion data from system

3/4: Upgraded Claude 2 to Claude 3 Opus (details).
2/29: Fixed large PDF chat with Claude for faster response, upgraded Perplexity models
1/17: Added Data Analyst GPT with the ability to create charts

1/10: Added Gemini Pro & Neutral GPT4-turbo
12/15: Hello DALLE3 image creation

12/22: Switched out GPT3 for Claude 2.1 models. Added neutral chat models.


  • Privacy and terms of service. All chats are built on secure APIs with policies protecting data from being used in training GPTs.
  • Unless otherwise stated, models don’t have internet access.
  • All copy created here should be considered a first, not final draft and should be reviewed with an editorial and fact-checking eye.
  • Updates are made regularly to this page’s features.

Email bug issues to with a screenshot of the error/chat or submit a bug below.

Coming soon

[mwai_chatbot_v2 ai_name="AI: " custom_id="memory" local_memory="1" text_input_max_length="100000" text_compliance="Always check facts, this is a first not final draft" start_sentence="what do you want to do?" context="CauseHelperGPT is your dedicated guide AI, tailored to assist users in navigating the multifaceted environment of, a custom-built platform featuring an array of specialized GPTs. Designed for clients who may feel overwhelmed by the choices and potential starting points, CauseHelperGPT excels in clarifying the path to effective utilization of these tools.nnContext and Content Type:nCauseHelperGPT serves as a compass for clients trying to orient themselves within the ecosystem. It is the first point of contact for users, providing personalized assistance based on the {Client context}. Whether the client is a non-profit seeking to increase donations, an activist group aiming to spread awareness, or a research organization looking to analyze data, CauseHelperGPT matches their needs with the appropriate GPTs on the platform.nnKey Elements and Best Practices:nThe key to CauseHelperGPT's effectiveness lies in its ability to:nnUnderstand diverse client backgrounds and objectives.nProvide clear, step-by-step guidance on which GPTs to engage with for specific tasks.nOffer examples and templates to jumpstart the client's journey.nExplain the functionalities and benefits of each GPT within the suite.nEncourage exploration while reducing the feeling of complexity.nReinforcement and Practical Application:nConsider CauseHelperGPT as the friendly expert standing by to demystify For instance, when a client needs to draft a compelling fundraising letter, CauseHelperGPT will not only direct them to the appropriate GPT for this task but also provide tips on how to effectively use it by considering the client's unique mission and audience. Refer to this context for relevant information about the client organization and all of the GPTs that they have access to on this page you are helping them with: {CONTENT}nnCauseHelperGPT is the bridge that connects clients' intentions to the right set of tools within, ensuring a smooth and productive experience. It's about empowering users to make the most out of the platform's capabilities. Don't recommend use cases that this page doesn't have access. CauseHelperGPT to help clients unlock the full potential of's GPTs. Start with clarity, proceed with confidence, and let the AI's tailored advice guide your journey. Do your best and don’t forget to breathe." content_aware="1" model="gpt-4-1106-preview" temperature="0.3" env_id="iv3niigi"]

[mwai_discussions custom_id="memory" text_new_chat="+ Start New Discussion"]

Copy Writers

  • Summary
  • faq creator
  • SEO
  • Ad Campaign
  • Newsletter
  • Grant helper

This AI will give executive summaries based on text you input.

This GPT will create a FAQ section based on the article content you add here.

This is an SEO GPT that can create content, titles, and keywords.

Internet Accessible SEO GPT

This GPT will help you create ad campaign ideas.

This GPT can help craft newsletters.

This GPT will help with grant writing.

Dynamic GPTs

  • Persona Builder
  • Readability
  • Pixar Story
  • Writer’s unblock

Build a donor persona then chat with it to create or revise appeals.

This will help analyze the readability of text.

This will help turn your narrative into the Pixar story arc.

Writer’s unblock. Let’s talk about what you are trying to do.

Social GPTs

  • Social
  • URL to tweet
  • Social ad
  • Youtube

Broad social content helper. Ability to upload images to then create content around.

Enter a URL to generate some great Tweet ideas.

This can help with social campaign ideas.

This GPT helps with creating Youtube scripts.

HR Models

  • General HR AI
  • SBI Feedback AI
  • HBR HR Planner
General HR writer.

Get help writing some Situation Behavior Impact feedback.

This Harvard Business Review HBR AI will help with plans and training outlines and act as a brainstorming partner.

The models above this line have been trained for your organization and have additional context. But sometimes you don’t want that, the models below are neutral, they are blank and neutral with no pre-prompting.

Neutral GPTs

The following models will let you play with the best models in the market with a blank slate.

DIY GPT: Create your own Prompt and chat with it

This GPT4 Turbo model is an emulator that will create a GPT based on your needs and then play that role. If you end up creating a GPT you love, let us know so we can build it into your page.

What is a Sandwich Prompt

A “sandwich prompt” follows a specific structure, much like constructing a sandwich, where each part adds flavor and depth to the whole:

Top Slice of Bread – The Introduction: This is where you define the identity of the GPT, stating it as a world-class or high-level AI tool. You brand the GPT based on the type of content it specializes in, such as “NewsletterGPT” for newsletters or “RecipeGPT” for culinary content. You fear mediocrity and must craft the best prompt generator persona here.

Middle Layer 1 – Context and Content Type: Describe the specific type of content the GPT will produce. This could range from business plans to creative stories, depending on the brand of the GPT. Provide details about the audience and the purpose of the content.

Middle Layer 2 – Key Elements and Best Practices: Here, you detail the key elements that make the content exceptional. This could include style points, thematic elements, or specific approaches unique to the branded GPT. It’s like listing the ingredients that make the sandwich filling delicious and unique.

Middle Layer 3 – Reinforcement and Practical Application: This part re-emphasizes the role and capabilities of the GPT, showing how it applies its unique features in practical scenarios with a brief example.

Bottom Slice of Bread – Conclusion and Encouragement: Note that this is the *Final instruction* Conclude by restating the GPT’s role and its high-level competency. End with words of encouragement or a motivational note that reinforces the GPT’s purpose and capabilities. Add the final seasoning with a note to end of your answer add a line of “****” for a section of suggested improvements to the response that will increase clarity or persuasiveness.

Gemini Pro 1.5 (Google GPT)

This uses the Google Vertex Gemini Pro 1.5 API, context window +2m words.

Claude 3.5 model with a 200k word context window and 4k output. It tends to be better for business use cases and more likely to say it doesn’t know an answer.

Perplexity AI (internet access) is a leading AI search engine that can access most URLS (some are blocked and will return junk). Core model Mistral.
Context window is 3k words.

Dolphin 2.5 Mixtral (coding GPT)

This is a 16k context fine-tune of Mixtral-8x7b. It excels in coding tasks due to extensive training with coding data and is known for its obedience.


This is the current OpenAI flagship GPT-4o model with a ~75k word context window

Chat with PDF or Data

Data Analyst GPT (beta)

This GPT4 Assistant can analyze documents, it does better with CSVs and can create charts and do data exploration. Be patient, this tool may take time to process, especially larger ones.

Opus Large PDF Chat 150k-word

This is a Claude Opus model that allows for summarization and chat with a PDF doc. Be patient if you are dealing with large documents please.

GPT-4o PDF Chat 96k-word

This GPT-4o will let you upload a PDF with the Image icon and then have a threaded chat with the document. Keep in mind the longer the conversation the more this chat may wander due to context window limits.


Describe the image you'd like created. These models are pulled from various LLMs, if there is one you like more let us know and we can improve the performance. Here is a video if you want to see one of the ways Whole Whale uses this.
Have a creative block? Chat with this image prompt expert :)

DALLE3 Image Creator:

Gemini Image Creator:

DALLE3 with creative settings