A new startup named Lutra AI launched today with a platform aimed at helping users create personal artificial intelligence workflows and automate repetitive tasks without the need for deep technical expertise.

Lutra is led by co-founder and Chief Executive Jiquan Ngiam, who previously worked at Google LLC and the online education provider Coursera Inc. He saw an opening to use AI to provide nontechnical users a path to build automation projects for tasks that can connect workflows.

The company’s goal is to integrate AI with already existing tools such as Slack, Microsoft Outlook and Google Workspace to allow users to describe what they do day-to-day and have an AI assistant prepare a workflow for them. This could be something such as managing incoming emails, performing financial research or summarizing and extracting data from PDF documents for a reporting system that’s done daily.

Ngiam said his time working at Coursera and Google gave him the insight that users needed something to simplify the process of automating workflows. So he got together with friends, including the company’s co-founder Vijay Vasudevan, who also worked at Google, to look at AI models that could become assistants for nontechnical users by allowing them to use conversational English to describe what they need.

“It made me think about the ability of these models to generate code and reasoning, then figure out the environment about making it more useful for non-engineers,” Ngiam told TechCrunch. “There was this question about can these models now code in a way that interconnects all the software we use to then do very useful things for us reliably and securely.”

What Lutra developed is a code-first AI assistant that allows users to describe their workflow and goals in natural language to an AI assistant, which will then ask follow-up questions to refine the automation. This means that essentially, it’s like talking to a coworker or developer who is writing code to connect apps to automate tasks.

The idea behind the AI assistant is to deliver an automated workflow to users as if they are programming in English. By describing the workflow that they want, the AI assistant guides them through the process and gives them visibility end-to-end in the code that it produces. Lutra says that because the AI models produce working software code for production-ready environments that connects enterprise data and apps, it can be done in a secure, reliable way.

Lutra recently raised $3.8 million in a seed funding round led by Coatue Ventures, with participation from Hustle Fund, Maven Ventures and a group of angel investors. The platform is currently in private beta as the team focuses on expanding it to more customers, but there is a waitlist for users interested in early access.

Image: Lutra