<?xml version="1.0" encoding="UTF-8"?><ns2:project xmlns:ns1="http://gtr.rcuk.ac.uk/gtr/api" xmlns:ns2="http://gtr.rcuk.ac.uk/gtr/api/project" xmlns:ns3="http://gtr.rcuk.ac.uk/gtr/api/fund" xmlns:ns4="http://gtr.rcuk.ac.uk/gtr/api/person" xmlns:ns5="http://gtr.rcuk.ac.uk/gtr/api/project/outcome" xmlns:ns6="http://gtr.rcuk.ac.uk/gtr/api/organisation" ns1:created="2026-07-08T08:44:08Z" ns1:href="http://gtr.ukri.org/gtr/api/projects/D4CF6F24-5B81-4645-B5B4-49420B16B7AE" ns1:id="D4CF6F24-5B81-4645-B5B4-49420B16B7AE"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/persons/4E04A413-10E3-44EF-8BB2-B38BECDC8D5D" ns1:rel="PM_PER"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/C1D646BF-FF07-4CDF-B37F-E46C8D320BE7" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/C1D646BF-FF07-4CDF-B37F-E46C8D320BE7" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2021-02-28T00:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/D5A2CFD3-E04F-48EA-9CC3-089A7E216DE3" ns1:rel="FUND" ns1:start="2019-08-31T23:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">31918</ns2:identifier></ns2:identifiers><ns2:title>Automated RPA</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Collaborative R&amp;D</ns2:grantCategory><ns2:leadFunder>Innovate UK</ns2:leadFunder><ns2:abstractText>Robotics Process Automation (RPA), the use of software to perform repetitive office work (e.g., customer on-boarding, KYC), promises to dramatically boost competitiveness by cutting costs, eliminating human error, and increasing delivery speed. Not surprisingly, RPA is a top strategic priority for most enterprises.

However, deploying RPA is tremendously expensive: teams of analysts and developers require months to put in place a single automation, with a price tag of up to &amp;pound;100,000\. These costs derive from three highly manual steps: (1) identify suitable processes for automation; (2) describe identified processes at a click and keystroke level; (3) translate these descriptions into RPA programs.

We have a new vision for RPA: automatically generate programs from human observation. We propose to turn recordings of clicks and keystrokes into RPA programs, automating Steps 1-3 above. We brought a product to market automating Step 2 in early 2018; this project focuses on Steps 1 and 3\.</ns2:abstractText></ns2:project>