Introducing

Introducing

T

to

actions

HR

01

Sales

02

Product

03

Ops & More

http://postsign.docusign.com

twin

TwinAgent I am double-clicking the "Save" button to store the PDF employment contract in the system for future reference
TwinAgent I'm clicking the "Send" button in Docusign to dispatch the signed document to the intended recipients
TwinAgent At the Amazon checkout, I'm clicking the "Order" button to finalize the purchase and proceed with the transaction
TwinAgent For Alan onboarding, I'm clicking the "Send" button to initiate the onboarding process for the new members
TwinAgent During Swile onboarding, I'm clicking the "Save" button to secure the onboarding details in the system
TwinAgent In the Payfit onboarding sequence, I'm clicking the "Save" button to ensure the onboarding information is stored accurately
TwinAgent On Google Workspace, I am clicking the "Invite" button to add a new user to our workspace environment
TwinAgent Within Notion, I am clicking the "Invite" button to add a new user to our collaborative workspace.

HR

/

Active Tasks

/

John Doe Onboarding

Joe Smith Onboarding

avatar
Onboard Joe Smith for me

HR

Sales

Product

More

http://postsign.docusign.com

twin

TwinAgent I am double-clicking the "Save" button to store the PDF employment contract in the system for future reference
TwinAgent I'm clicking the "Send" button in Docusign to dispatch the signed document to the intended recipients
TwinAgent At the Amazon checkout, I'm clicking the "Order" button to finalize the purchase and proceed with the transaction
TwinAgent For Alan onboarding, I'm clicking the "Send" button to initiate the onboarding process for the new members
TwinAgent During Swile onboarding, I'm clicking the "Save" button to secure the onboarding details in the system
TwinAgent In the Payfit onboarding sequence, I'm clicking the "Save" button to ensure the onboarding information is stored accurately
TwinAgent On Google Workspace, I am clicking the "Invite" button to add a new user to our workspace environment
TwinAgent Within Notion, I am clicking the "Invite" button to add a new user to our collaborative workspace.

HR

/

Active Tasks

/

John Doe Onboarding

Joe Smith Onboarding

avatar
Onboard Joe Smith for me

Vision

Never do the same thing twice

We’re developing an action-driven AI sidekick to handle your boring tasks, freeing you up for the exciting stuff.

We believe that too much human brainpower is wasted on repetitive tasks; and that individuals should focus on creativity, decision-making, and communication — while AI handles the tedious execution.

That's where Twin comes in. We aim to create a reliable AI that shadows human actions on computers and autonomously completes tasks across applications, from start to finish. This way, you will never have to do the same thing twice.

Twin Labs was founded on 09.01.2023 by

Hugo Mercier

Joao Justi

Vision

Never do the same thing twice

We’re developing an action-driven AI sidekick to handle your boring tasks, freeing you up for the exciting stuff.

We believe that too much human brainpower is wasted on repetitive tasks; and that individuals should focus on creativity, decision-making, and communication — while AI handles the tedious execution.

That's where Twin comes in. We aim to create a reliable AI that shadows human actions on computers and autonomously completes tasks across applications, from start to finish. This way, you will never have to do the same thing twice.

Hugo Mercier

Joao Justi

Mission

Building the AI last mile

With three startups under our belt each and years of multitasking, finding a reliable way to delegate tasks we'd rather not handle has always been a challenge.

So, while GenAI apps primarily focus today on text-to-content use cases like content generation and knowledge search, we have decided to focus towards building the text-to-action capability of GenAI.

Our starting point is to leverage the latest advances in computer vision to develop a text-to-action system that can shadow us on our computers and learn how to use any type of apps, just like humans do.

Our goal is to build a reliable app that you can seamlessly delegate your time-consuming and repetitive tasks to, similar to delegating them to a smart intern.

You
You

Plan

Towards a reliable and hands on AI work companion

Over the last months, we delved into the daily tasks of 200+ knowledge workers, crafting a versatile system that autonomously handles common use cases reliably. It surpasses anything we've tested from open source repositories and research papers — reaching a level of reliability that can be trusted.

Yet, there's still much to be done.

twin-master-plan.md

# Here’s our plan

# Here’s our plan

  1. Release the first version of Twin based on a library of pre-trained tasks that target the [20%] of tasks consuming [80%] of the time.




  2. Address the long tail of tasks by enabling users to define their own specific tasks in a seamless way, using recording and commenting in [natural language].




  3. Leverage data from previously completed tasks and assemble them to create more complex tasks. This will allow users to [delegate] increasingly more [complex work], and to tap into the operational knowledge of other workers’ Twins.

  1. Release the first version of Twin based on a library of pre-trained tasks that target the [20%] of tasks consuming [80%] of the time.




  2. Address the long tail of tasks by enabling users to define their own specific tasks in a seamless way, using recording and commenting in [natural language].




  3. Leverage data from previously completed tasks and assemble them to create more complex tasks. This will allow users to [delegate] increasingly more [complex work], and to tap into the operational knowledge of other workers’ Twins.

  1. Release the first version of Twin based on a library of pre-trained tasks that target the [20%] of tasks consuming [80%] of the time.




  2. Address the long tail of tasks by enabling users to define their own specific tasks in a seamless way, using recording and commenting in [natural language].




  3. Leverage data from previously completed tasks and assemble them to create more complex tasks. This will allow users to [delegate] increasingly more [complex work], and to tap into the operational knowledge of other workers’ Twins.

Careers

Welcoming founding team members

We're seeking individuals enthusiastic about making AI truly practical in the real world to join our founding team. Together, let's transform our experimental prototype into a robust product for our initial customers. We have two exciting sets of challenges to tackle.

On the technology front — crafting reliable autonomous agents capable of executing tasks in a browser, learning from users and mistakes. Our aim is to make our system increasingly faster, cheaper, more capable and reliable. We're consistently exploring new techniques to boost model accuracy for relevant tasks, like incorporating self-learned paths or fine-tuning specialised language models.

On the product front — forging an interface distinct from what we’ve seen in the first wave of GenAI tools:

proactive

Proactive

Our goal is to minimize the time to completion as much as possible. Simplicity in setting up a task is crucial. We want Twin to take the lead in the conversation and notify users when necessary. Not the other way around.

action driven

Action Driven

We do not envision a world where we spend our entire day in a chat box. Natural language should be used sparingly, and Twin should focus on taking action rather than engaging in lengthy discussions.

trustworthy

Trustworthy

If Twin is uncertain or unfamiliar, it admits it, and should ask the user for validation. When Twin works with users’ apps, users should be notified. Transparency is key in building trust.

learning

Learning

Interacting with Twin should feel personal, not generic. As users share information, Twin should remember, and asking the same question twice.

Join Twin. We’re hiring developers, product designers and more.

Join Twin. We’re hiring developers, product designers and more.

Design Partners

Launching our B2B partner program

One of the major challenges of GenAI today is its lack of steerability. While viewed by some as a feature, we believe that for widespread adoption in organizations, this needs to be addressed. That's why, early in our journey, we're onboarding a select group of partners to co-design custom task libraries. These are trained to align with their internal processes, work methods, and leverage their specific tools - making sure that when we ship the first version of Twin, it seamlessly integrates into their operations.

We've started training Twin on tasks from our community. If integrating GenAI into your organization is a 2024 priority and you're keen on more than content generation, contact us. We're soon onboarding the first batch of partner companies.

Investors

We have raised a $3m pre-seed round and are proud to be backed by some of the best AI investors, founders and operators.

  • They are also on a quest to reclaim lost time

Get updates

Secure your spot for occasional development updates and early access. No spam, just the good stuff.