When Twin got here out of stealth in January 2024, AI brokers had been extra of a theoretical idea than a actuality. In the present day, the Paris-based firm 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 sort out these issues. Some firms use API-based, no-code or low-code automation merchandise like Zapier. Others depend on RPA software program, equivalent to UiPath.
With its workforce of 9 folks, Twin thinks there’s a way more environment friendly approach to deal with automation. As you’ll 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 tens of millions of invoices per 30 days. And prospects spend a number of hours per 30 days gathering invoices and importing them to Qonto.
Over the previous three months, Twin has created an computerized invoice-retrieval instrument that may velocity 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 exhibiting the agent’s actions.
If it’s essential to log in to a service to obtain invoices, the browser pauses and asks you to enter your credentials manually. When you do that, you may 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.
“If 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 tons of of 1000’s of various companies that everybody is utilizing,” Twin co-founder and CEO Hugo Mercier stated throughout a demo of the product.
“And that might be fully unimaginable with RPA since you would wish to create a single customized script per web site after which each time the web site adjustments, you would need to modify the script,” he added.
As for API-based automation merchandise like Zapier, Mercier stated that it took Zapier 10 years to help 8,000 functions on its platform. Twin already helps 1000’s of functions for its Bill Operator simply a few months after beginning work on the product.
Behind the scenes, Twin runs a Chromium-based net browser on a server. The startup makes use of OpenAI’s CUA (computer-using agent) mannequin. In truth, Twin was one of many 15 firms that obtained to strive CUA in beta.
CUA can also 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 ought to be simpler to make use of brokers that browse the online for you.
“We labored so much on making the expertise very simple. We’re actually concentrating on the tip consumer, perhaps 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 stated.
After bill retrieval, Twin thinks there are lots of industries that might profit from B2B agentic functions. For instance, brokers might 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 by which AI brokers change into 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 functions.
