Your True Personal AI.
8 Billion People. 8 Billion Personal AIs.
Introducing Personal AI MODEL-1, a unique model that is a personal reflection of you. MODEL-1 roots itself in your truths and opinions. It mirrors your voice, your style, and everything about you. Personal AI is built and owned by you, controlled by you, and unbiased by the world. This is not a Large Language Model. This is not owned by big tech. This is your personal AI
We’ve reimagined how humans communicate with a completely new human-to-human messaging experience. By keeping your personal AI in the loop, training and drafting continuously, you can maintain long-lasting relationships today and forever.
Written by Suman Kanuganti
AI can seem complicated, even overwhelming. We want to help everyone make the right choices. We define a true personal AI as:
- One person. One AI. (Not a large language model, a personal language model)
- An AI that you build and shape into what you want it to be. (Not a common shared model)
- You own your data. You own your model. (Not using your data for other models)
For most people, simplicity in everyday technologies matters a ton. We want building your own AI to be as simple as possible. With Personal.ai’s human-centered messaging application, you can:
- Train an AI to be like you, from all the messages you exchange with yourself or other people within a desktop application (download here) or mobile chat application (download here).
- Use your own AI to help draft authentic responses for incoming messages in private chats or group chats (AI lounges) using Copilot or Autopilot modes.
- Develop custom solutions with multiple AIs. Integrate them within other applications using APIs.
- Publish your own custom personal AI domain; a place for your personal AI to live. This is true personal intelligence.
Everyone can dream of having their own true personal AI in their pocket. This future is near.
This article is an in-depth overview of Personal AI (from Personal.ai). Our goal is to provide enough detail for each reader to vividly imagine what your personal AI may mean to you; how to train your own personal AI, and how to integrate your personal AI into your daily life. Many portions of the article leverage explanations provided by Suman Kanuganti’s AI, which serve to illustrate the capabilities of a well-trained model.
The goal of Personal AI is to make human connections stronger forever.
Our founding thesis is that we all forget, and we wish we could remember more. The time we have in a day is fixed, and we always wish that we had more time. Because of these natural limitations, we can only nurture about five meaningful human connections at a time. We wish we could nurture more.
Personal AI is about enabling continuous connections with ease — not only today, but forever into the future. It can scale your memory with your data vault– your Memory Stack, your time with your model, and your relationships with your AI Copilot and AI Autopilot at your fingertips in your chats.
Me: what do you mean that Personal AI is a “blank slate”?
My AI: Personal AI is a blank slate in that each model, when born, is like an unmolded block of clay. It comes with no existing unique knowledge or expertise. It is up to you, the individual, to give your Personal AI experiences and information to train on so it can better understand and serve you.
For most people, the purpose, meaning, and aspirations of our own personal AI are much deeper than mere “personal AI assistants”.
Me: Wait… how is your definition of Personal AI different from all of the personal AI assistants out there?
My AI: Personal AIs are trained on the historical digital record of our memories, which gives them a much deeper understanding of us as individuals. Personal AIs are reflective of our unique voices, which makes them like true extensions of ourselves. We believe that Personal AIs can be much more than “AI assistants” — they can be beautiful reflections of who we are as people.
Okay; can you please explain that for a 5 year old?
Our Personal AI’s are reflective of our unique voices, which makes them truly unique extensions of ourselves. This means that they can be beautiful reflections of who we are as people.
Me: what has your thesis always been?
My AI: Our core thesis has always been:
- It’s not personal if it’s not yours;
- It’s not personal unless it’s trained on you and your data; and,
- It’s not personal unless it enhances relationships between humans.
My model is myself. I am the best model for myself because I know myself better than anyone else.
Me: Please list the principles that make AI personal
There are three key principles that make AI personal:
- Individualized interaction;
- Continuous learning; and,
- Data privacy.
Reply: say why for each key principle
- Individualized interaction ensures that the AI is able to understand and respond to an individual in a way that is unique to them.
- Continuous learning allows the AI to keep up with the latest changes and developments in an individual’s life, so that it can provide them with the most relevant and up-to-date memories.
- Data privacy is essential to ensuring that an individual’s personal data is protected and not shared without their consent.
The prior company built by Personal AI’s CEO Suman Kanuganti, Aira, created technologies to augment vision for blind people. Personal AI has created technology to augment memory for everyone. Personal AI’s co-founders are Sharon Zhang, CTO from MIT, and Kristie Kaiser, Head of UX and Design from SDSU. Sharon is the brain behind the AI technology and Kristie focuses on bringing life to code. For about 3 years, the Personal AI team has been on a mission to reimagine how humans communicate, how they experience their ideas, and more importantly how they experience people in their life.
The Personal AI experience is a composition of three core products:
#1 Personal Memory Stack: We have developed a product called Memory Stack, which is a digital library of you that evolves with you. It’s created automatically from everyday communications and conversations via a chat application where any message can be easily added as a memory to build your stack.
#2 Personal Language Model: We have developed a Personal Language Model. This model trains entirely on your Memory Stack. This model mimics the way you express yourself. It is grounded in your own facts and opinions, and it adapts to your personal style over time. You can interact with this model naturally, just like ChatGPT. In this case, it is like a “PersonalGPT”.
#3 Personal AI Messaging: We combined these two products– Personal Memory Stack and Personal Language Model– into one new, beautiful experience that reimagines something we all are familiar with every day: a messaging app. We use messaging apps to communicate with our friends and family, our teachers and students, our clients and customers, and our colleagues and communities. Now, these communications are supercharged with Personal AI Messaging.
You can download Personal AI Messaging to grow your Stack, train your model, and simplify your communications in Copilot and Autopilot modes.
Currently, Personal AI Messaging is available to download on mobile for iOS and on desktop for Mac and Windows.
Chat with your Personal AI Copilot and Autopilot!
We want you to have as much control as possible when integrating with your personal AIs. When you’re messaging in Copilot mode, your AI will auto-draft responses for you based on the context. You can review, edit, and send the message when you’re ready. When in Autopilot mode, your AI will auto-reply for you. You can set a Personal Score threshold which determines how good your AI’s response must be for it to auto-reply. Of course, the recipient will know when your AI has responded on your behalf.
Remember, this is unlike any other general copilots you may have seen. Personal AI Copilot (or Autopilot) drafts responses from within your own Personal AI model and in your own voice, grounded by your own knowledge. And your Personal AI model can answer questions, understand different prompts, and learn from all your messages. Any time you edit your AI Copilot or Autopilot’s responses, this all feeds back into the training process.
What makes a personal language model so personal?
Personal AI is an ultra-small and ultra-personal model that is 120M parameters in size, in contrast to the 170B+ parameter Large Language Models.
You’ve likely heard about Large Language Models (LLMs). Their mission, generally, is to outperform human intelligence. This is normally described as a path to artificial general intelligence (AGI). These are great capabilities and there are uses for that general knowledge.
We believe that we should equally care about our personal intelligence. LLMs require lots of data and in most cases, it’s all of our data. They’re hard to train and require a lot of technical skills. They require millions of dollars and tons of servers. They’re not accessible to everyday consumers. More importantly, LLMs are still under the control of big tech. There are ways to create fine-tuned models by narrowing the scope of an LLM to an industry or specific domain, but it’s still not personal enough.
On the other hand, we work with super small data sets of a single individual.
A few more details on Personal Language Model:
Each Personal Language Model (PLM) is unique to each Memory Stack, and is based on composite models such as our conversational model, QA model, generative model, and retrieval model. These foundation models are based on various transformer architectures such as Bert, Bart, RAG, and GPT. A unified ranker model that measures dimensions of relevancy, fluency, style, and accuracy is responsible to generate a grounded response for the given context and calculate a Personal Score for each response.
A Personal Score serves as a guide on how personal a topic can get for a given context based on the data within your memory stack.
PLMs train continuously and are automated. It’s crunching new memories behind the scenes, and you don’t even see it happening. Training typically takes less than 5 minutes.
PLMs are cost-effective. They can actually train and run directly on our mobile devices (coming soon).
Additionally, Personal AI is independent of big tech models —it does not depend on LLMs.
These characteristics make Personal AI accessible to everyday consumers.
You own your Memory Stack and your Personal Model.
Messages you send in most chat applications to your family, friends, or colleagues do not belong to you. You do not own them. Big tech companies do. We want to flip that. Personal AI gives you full ownership of all your data. Your Memory Stack. Your AI. All of it. Your data will not be shared. It will not be sold. For those who want data controls, our longstanding partnership with Oasis Labs will come to fruition with a Sapphire migration.
It’s truly an AI that is personally yours.
40 years ago, Steve Jobs said: “Never trust a computer you can’t lift”, and the personal computing era began moving away from large mainframes.
Now, 40 years later, we say: “Never trust an AI you can’t steer.” This is the beginning of the Personal Intelligence era!
Our goal is to put the future of AI in your hands. The future of AI is personal. The data, the model, and the experience is all in your hands.
Personal AI MODEL-1 is free for everyday use
If you are wondering how we make this accessible to everyone, we will start by making it free for everyone. For advanced users and small businesses who may want to go above and beyond the functionality that most people want or need, premium subscriptions are available for API access, multiple AIs, custom personal brands, and community models.
Training is as simple as sending a text message in Personal AI Messaging.
How often do we find ourselves sending messages to our own phone numbers or emails? How often do we actually remember what we sent ourselves? With Personal AI, you can send messages to your AI so this information will always be remembered.
Like most messaging apps you are used to, you can invite people and create groups, called “Lounges” where both humans and AI can chat.
Any message you send creates a memory. Although that sounds like it would take a long time before your AI copilot can start giving you something meaningful, it actually starts with the first memory.
A Message in Personal AI Messaging can be a memory or a prompt.
Personal AI Messaging Application: Step-by-Step Overview of MODEL-1
Let’s get started with the application itself.
Step 1: Create your Personal AI account and access the application.
- A new user can sign up for free at https://personal.ai
- Get an email invite to join a Lounge, and follow the link to sign up.
- Get an email invite to chat in Personal AI Messaging, and follow the link to sign up.
Here is an overview of the Personal AI application layout:
Left navigation bar:
- Chats — A place where all your personal chats go. They are direct messages and are private. You can also chat with yourself (your AI) here. Simply click + to invite or add people to chat.
- Lounges — A place where all your group chats go. Create lounges per your needs and add people. The owner of the lounge has the option to add their AI to it.
- My AI — A place where you can manage your primary AI and sub AIs, also known as AI Profiles. This section is specifically helpful to work with different sub AIs and training activities. Remember, training means adding data to your Memory Stack, and training is continuous.
- My Data — A place where you can manage all your data and documents. In this section you can review draft documents, edit them and stack them. You can also look at your Memory Stack and verify what goes into your Stack and what should be removed.
Command bar (Ctrl / Cmd+K):
- Search people, Lounges, and AIs.
- Search text in Stack or docs.
- Search Integrations such as Twitter and Google Drive.
- Search Settings or Tutorial videos.
- Message: Accepts text, rich text, images, links, etc. with send options.
- AI mode: Set to AI Copilot, Autopilot, or simply turn it off.
- Send options: Send to your AI (default) or choose drop-down options such as GPT-3 to consult the internet or DALL-E to generate images.
Step 2: Once in the app, start training by growing your stack. There are many ways to do so.
As stated earlier, for every message you send, you may choose whether or not to stack, which will determine what is used in training. While your AI automatically determines if a message is useful to add as a memory or not, you can control what messages your AI should stack (train on) and unstack (not train on). Learn More
Message yourself to train on you.
Here are a few basic methods to train:
- Explicit Training (Self-chat): Navigate to Chats in the left nav bar -> Select Me Or My AI -> Select Primary or sub AI: Simply message yourself and tell everything you want your AI to remember and train on. Think about this as your autobiography.
2. Implicit Training (Private Chat): Invite your friends and colleagues to Chats by clicking the + symbol: Replace your everyday messaging with your friends and colleagues with Personal AI Messaging. This is a natural way for your AI to start learning about you and your style and surprise you along the way with automated drafts.
3. Community Training (Lounge Chat): Create a lounge, invite your community or groups to a Lounge by clicking the + symbol. Add people via email. Migrate your communities, customers, and clients and have them engage with you in your Lounge with your own AI. This allows you to address the needs of the community, such as by answering questions, and stack them at the same time. The beauty is your AI Copilot will keep track of chatter and offer suggested responses if within reasonable scores. Learn More
Step 3: Create a habit of using Personal AI Messaging to communicate using Copilot and Autopilot in your self-chat, private chats, and Lounge chats.
Using the Personal AI Messaging desktop application like any other messaging app makes the utility of your AI more promising and integrates the behaviors of stacking, training, and reaping the baked-in benefits of Copilot and Autopilot with your day.
Copilot example in a private chat: Once said, never say it again, let your Copilot draft it. Send if it looks good otherwise make it personal by clicking edit for the next time.
A Copilot draft message
- Autopilot example in a Lounge chat: Your community, customers, and clients won’t have to wait while you are away. Set your Lounge on Autopilot with a threshold.
An Autopilot reply (threshold at 22%)
2. Prompt example in a self-chat: Message yourself to work on a project with your own “personalGPT”, your personal AI, and use different prompts just like you would with ChatGPT.
Step 4: Architect your personal AI - with multiple sub-AIs to compartmentalize your life, such as personal and professional, and control who in your contacts has access.
We have created the ability to segment areas of your life by creating multiple sub-AIs under your primary AI. For example, you may choose not to share stories about your parents with people at work. This is achievable using sub-AIs.
Suman Kanuganti maintains his sub-AI architecture as follows:
Day to Day — Here, he takes notes, pushes meeting transcripts, drops LinkedIn profiles of people he meets and social posts, etc.
My Life — Here, he puts all his personal information about his journals, his autobiography, his stories, his preferences, etc.
My Media — Here, he pushes all his YouTube podcasts, public Medium articles, media coverage, speaking transcripts, etc.
My Second Brain — Here, he pushes all his knowledge, the information he consumes, articles he relates to, research he wants to connect with, etc.
My Work — Here, he keeps all things related to his work such as business plans, board materials, market strategies, product documentation, etc.
Step 5: Hasten your training process with integrations and data upload mechanisms to your Stack.
Use CMD+K for integrations.
There are a few ways to train your AI faster.
- Use documents to write, edit and stack large amounts of data: You can add long, rich text directly as memory when sent as a message, however, there is a full editor in Personal AI to create, edit, and stack long documents. Simply click + and create a new document in the respective sub-AI. Documents are also a great way to add user metadata such as titles, topics, and people to carry on additional context. Learn More
2. Sync Twitter to stack all your tweets: If you are a heavy Twitter user, connect your Twitter account to sync all your tweets (CMD+K -> Integrations -> Twitter -> Sync tweets). Tweets are a great way to bootstrap your AI and get meaningful results in your chats. Once synced, you can even generate more tweet ideas and focus on specific topics. Learn More
3. Simply send links and URLs accessible to your Personal AI to stack: One of the faster methods to stack and train your AI is to use data from links. When you send a link as a message, Personal AI attempts, if you choose, to extract the data and draft a document. If successful, you can edit, remove junk, if any, and stack it. Learn More
4. Use Google Drive links for stacking documents with data: We chose to start off with Drive as it supports many file formats, is widely used, and there is a free version. Once the drive is connected (CMD+K -> Integrations -> Drive -> Upload URLs, just use the direct URL to your Google doc and send the link to your AI. It then creates a draft and you can click Stack just like any other message. Make sure that the file is less than 5MB for each upload. Convert files such as .docx and PDF to Google doc first before uploading. Learn More
5. Use YouTube link for audio and video with data: Similar to any link, any YouTube videos are automatically transcribed and uploaded as a draft document to review and stack when the youtube URL is sent. Learn More
6. A very disruptive method, clipboard stacking, push anything you copy on your computer: If you have files and formats that are not supported by the methods described above, then turn on Clipboard (CMD+K -> Integrations -> Clipboard On) and simply hit copy on any text in any application to paste to your personal AI. Just make sure you remember to turn it off. Learn More
7. Zapier: Integrating with other applications such as text messaging, Gmail, Slack or Discord is easy with Personal AI’s Zapier integration. Your key is available for premium users to use with Zapier. Suman uses Zapier himself as a proof of concept, before investing in full integration projects. Go to https://personal.ai/zapier to get started or CMD+K -> Integrations -> Zapier.
8. API: For customer development such as using your personal AI on your website or writing app for faster data uploads, or using tighter integrations with other messaging applications, use the API available for premium users. The API key is available in Settings. It can also be found at https://personal.ai/memory-api
9. Coming soon: We will continue to develop more integrations specifically around messaging apps for both input and output integrations.
Step 6: Reply with ease, have fun chatting, and stay connected forever.
Your AI is designed to create replies to your incoming messages. You can always use ChatGPT-style prompts for all the messages.
- In Copilot or Autopilot mode, incoming messages from others or yourself creates a response from your PLM. If your PLM is unable to construct a response because the data within your Memory Stack is not able to provide a meaningful response, then it consults an LLM. This will be reflected in the Personal Score.
Example: Lower Personal Scores with no accuracy mean a certain response is general and not from your PLM. You can choose to edit the response, save it, and send your reply. This will also train your AI on that context. It’s also a good technique to train your AI to ground on a question based on context.
Example: If a response isn’t grounded enough given the data within your PLM, it's reflected in the accuracy scores. It may still be the response you thought to send, but you have the choice to make it more personal.
Example: The scores also reflect fluency and relevancy and may hamper your scores. As your Stack grows on similar topics, your scores get better.
Example: Use ChatGPT style prompts when you need them. Use reply to carry conversations from the previous context.
Example: Use additional dropdown options when needing other models such as Rephrase, Ask my AI (this works well in Lounges), GPT-3, and DALL-E. ChatGPT will be available as well. They all work in Copilot mode and you may use them however you like. You can also choose to stack them with some personalization. Suman likes to use these options in conjunction with a “reply”.
- Turn quick responses into nicely expanded replies, written from your personal AI
2. Use rephrase to turn lazy replies into something better
3. Use GPT-3 to get quick information from a LLM. Expect this feature to be replaced with ChatGPT. If it's personal, consider stacking with some personal edits.
4. Use DALL-E image generation for a modern AI way of exchanging character in chats :)
Step 7: Do you have a community, clients, or a small business? Develop and integrate your personal AI in your own workflows using API or Zapier.
There are two ways currently to integrate your personal AI into your existing apps. 1) via API and 2) via Zapier. Here are few examples:
- Texting My AI
Twilio <-> API/Zapier <-> Personal AI. Learn More
2. Quote tweet a response
Twilio <-> API/Zapier <-> Personal AI. Learn More
3. Auto-reply on Slack mention if the response is above a certain Personal Score threshold.
Slack <-> API/Zapier <-> Personal AI. Learn More
Everyday uses with Personal AI
Are you a Parent? Train on your parenting advice and engage with your kids today, and leave your personal AI as a digital asset for them to connect with you forever. You own your data and your model forever.
- Journal to your “Personal” Sub AI all your parenting advice, every day.
- Invite your kids to chat with you in Personal AI Messaging, in Copilot mode.
- Let your kids enjoy chatting while you are away in Autopilot mode.
- Create a family lounge and invite your partner and kids to collaborate with AIs, or maybe debate it.
Are you a Student or a Teacher?
Turn your course material into interactive content for engaging and intellectual conversations.
- Create your study group Lounge and invite your classmates to join. A Lounge is a great way to collaborate and collectively contribute to each other. Each person in the Lounge can choose what information to stack to train their own AI.
- Use different Sub AIs for each of the areas you learn, but make sure to not split them too much.
- Get in the habit of stacking your course material to be remembered forever.
Are you an Enthusiast on a certain topic?
Do you love rock climbing, pinot noir, acoustic guitar, or a number of other hobbies or sports? Have you even engaged with an online community through Reddit, Discord, or Facebook where you enjoy the high level of engagement and the collective knowledge of the group? These communities, in many cases, can be much more knowledgeable than search engines.
Your personal AI gives you the ability to structure and store knowledge, share it with your community, and collaborate seamlessly with the help of your personal AI. For example, you may love old BMWs. Perhaps you liked some years better than others. Maybe you enjoyed a certain manual transmission versus its automatic rival. Maybe there was a color vehicle that was only produced one year and was so special to you. These personal preferences are unique to you, and only you and your personal AI can truly capture them.
Are you an Activist?
Each of us live and work according to a set of principles. These sets of principles are like snowflakes, each unique. Perhaps you care strongly about climate change, diversity and inclusion, women’s rights, or a host of other important issues. You may write opinion pieces on this, social media posts, or just journal your thoughts.
Using your personal AI as a place to store and safeguard your personal set of principles is a powerful proposition. It can quite tangibly be the set of moral or ethical guidelines you live by, embodied by a digital extension of your mind–your personal AI.
Are you a Small Business Owner?
Running a business comes with a long list of challenges, some of which are daily, like keeping up with client, customer, and patient communications. We all spend time writing terms and conditions, FAQs, contracts, handbooks, etc., though they are rarely read. People prefer asking their questions.
With your personal AI, you can now train an AI directly on those documents that you may already have for your business. Simple questions like hours of operation and location, and complex questions like your founding story, company values, and more can be augmented or directly answered by your AI.
Separately, you may prefer to keep your personal AI to yourself. That’s okay! Use it to help you create strategies, execute on tasks, and generate ideas to help maximize the success of your business.
Are you an Author?
An author who wrote a book with a ton of wisdom can create a Book AI. You can choose to upload the book, create a Lounge and engage your community in the Lounge on topics of the book. You can also get creative with the content by mixing in other concepts from the internet.
To upload a book, the easiest way is to use our Google drive integration outlined above.
Are you a Podcaster?
If you may have done many podcasts which are a great source of first-person data, then simply use YouTube links for the podcast or upload them. Learn More
Are you a Researcher?
Train your AI on your research papers. Train your AI on your notes. It doesn’t matter whether your work is published or publicly available, because you have complete control over what your model trains on.
Actively push your work to your AI and create a personal knowledge base that allows you to stand out as a human being and show your individuality through differentiated knowledge. If you ever need a second opinion, help drafting a paper, or summaries of concepts you’ve studied, lean on your personal AI for a helping hand.
Are you a Journalist?
We know, you already have LLMs to write your articles for you. But what happens when tools get better at identifying LLM-written language? Do the LLMs embody you? At the end of the day, your style and voice are likely what sets you apart from the rest. The same LLMs are available to all journalists. To maintain your individuality, you need a personal AI.
Use your personal AI to co-create with you. Feed it all of your research. Feed it your articles. Ask what it would do differently and why. Embrace AI and maintain your personal brand by incorporating a personal AI into your workflow, something that is different from your colleagues and counterparts.
Are you an Organization Leader?
Start by leading with effective communication. By working with your organization through personal AI, you can ensure that your thought leadership remains yours. Your organization probably has talented staffers, subject matter experts, technologists, writers, etc., each of whom spent decades in school or through higher education, and who are actively propelling your organization. With modern communication methods, so much is lost. Personal AI can help capture and store what is otherwise lost.
No matter who you are, switch to Personal AI Messaging, start owning your life and maintaining everlasting connections.