When Twin got here out of stealth in January 2024, AI brokers had been extra of a theoretical idea than a actuality. At this time, the Paris-based is releasing an automation agent in partnership with Qonto, the fintech startup that gives enterprise financial institution accounts to greater than 500,000 prospects throughout Europe.
If you wish to automate repetitive duties, there are already a number of methods to deal with these issues. Some corporations use API-based, no-code or low-code automation merchandise like Zapier. Others depend on RPA software program, equivalent to UiPath.
With its group of 9 folks, Twin thinks there’s a way more environment friendly method to deal with automation. As you could have guessed, it concerned synthetic intelligence and pc use fashions.
Bill Operator, Twin’s first product designed for Qonto, is an efficient instance of why it is sensible to make use of synthetic intelligence. Qonto handles thousands and thousands of invoices monthly. However prospects spend a number of hours monthly gathering invoices and importing them to Qonto.
Over the previous three months, Twin has created an computerized bill retrieval instrument that may pace up this course of. When customers launch Bill Operator, Twin first fetches the listing of transactions with lacking invoices. It then reveals the listing of companies that it must entry to obtain invoices subsequent to a browser window displaying the agent’s actions.
If you might want to log in to a service to obtain invoices, the browser pauses and asks you to enter your credentials manually. As soon as that is finished, you possibly can click on on a button to let the agent proceed its work.
After that, Twin’s Bill Operator routinely finds your listing of previous transactions, downloads invoices and attaches the PDFs to the transactions in your Qonto account.
“Once you do this on the scale of Qonto, you principally must cowl a really, very lengthy tail of companies. Hundreds, tens of 1000’s and shortly lots of of 1000’s of various companies that everybody is utilizing,” Twin co-founder and CEO Hugo Mercier mentioned throughout a demo of the product.
“And that may be fully inconceivable with RPA since you would wish to create a single customized script per web site after which each time the web site modifications, you would need to modify the script,” he added.
As for API-based automation merchandise like Zapier, Mercier mentioned that it took Zapier 10 years to assist 8,000 purposes on its platform. Twin already helps 1000’s of purposes for its Bill Operator simply a few months after beginning work on the product.
Behind the scenes, Twin runs a Chromium-based internet browser on a server. The startup makes use of OpenAI’s CUA mannequin (CUA stands for Laptop-Utilizing Agent). The truth is, Twin was one of many 15 corporations that obtained to attempt CUA in beta.
CUA can be the mannequin that powers OpenAI’s Operator, its prosumer product that permits you to enter a immediate to let an agent carry out an motion for you. Along with higher efficiency, Twin believes it must be simpler to make use of brokers that browse the net for you.
“We labored lots on making the expertise very simple. We’re actually focusing on the tip consumer, possibly people who find themselves not tech-friendly. They don’t should immediate or configure something. You simply log into your accounts, launch it, and it navigates to seek out the invoices,” Mercier mentioned.
After bill retrieval, Twin thinks there are numerous industries that would profit from B2B agentic purposes. For instance, brokers may routinely handle orders for an e-commerce firm, classify the catalog of a market or retrieve data for name heart brokers.
Twin is pitching a future wherein AI brokers grow to be cheaper, quicker and extra correct throughout all kinds of duties. Now, let’s see if the startup can flip the core agent platform that powers Bill Operator right into a product that builders can begin utilizing in their very own purposes.