Flag missed clock-ins and set a follow-up check for the next morning
In a hands-on test at QwenWork's public beta launch, a reporter for Chinese tech outlet APPSO had the agent spot attendance problems from clock-in and leave records, draft a group reminder and create a DingTalk to-do to check correction approvals the next morning.
Alibaba QwenWorkAdded Oct 13, 2026
What they did
The reporter gave QwenWork the attendance records and the leave sheet and asked it to identify cases such as missed clock-ins. It then wrote reminder text suitable for posting in the team group and created a DingTalk to-do for the following morning to check whether correction requests had been approved. The article stresses that the value is in these follow-up steps, not the detection itself.
How it went
Tested by the press The test shows the agent completing detection, the reminder draft and the scheduled to-do in one task, with screenshots. No accuracy or time figures are given.
Good to know
This was a short demo during a launch-day test, not an HR team's ongoing use. The article notes that this depth of access raises permission and data-boundary questions for the company.
A prompt to try
Here are this week's clock-in records <attendance file> and approved leave <leave sheet>. List every employee with a missing or late clock-in that is not covered by approved leave. Draft a polite reminder I can post in <team group> asking them to submit a correction, and create a to-do for <HR owner> at <time> tomorrow to check which corrections were approved.
Source
Runs on Alibaba QwenWork.
Want this running for you?
The Digital Agency pack is a bot team we set up and run that does this kind of work.
More in Hiring & HR
-
Draft interview scorecards from the call transcript
xAI's recruiting team says a bot matches each interview transcript or recording to the role's scorecard and drafts the feedback form in the recruiter's voice. It then asks the recruiter a few follow-up questions, such as their rating and what to probe next, before redrafting and submitting it to the ATS.
-
Source candidates overnight, then wait for approval to reach out
xAI's recruiting team describes a bot that learns from scorecards and resumes of past hired and rejected candidates, then sources new candidates overnight, adds them to the ATS as leads and drafts outreach sequences. A recruiter approves the send before the bot moves candidates to Reached Out and watches for replies.
-
Brief each interviewer, and find where candidates drop out
In the same xAI guide, one bot posts a single Slack note before each interview with who the candidate is, why the team is interested, the stage and what to focus on. Another looks across the interview loop for where candidates fail and why, and turns that into questions recruiters can ask at the first screen.
Want this running for your business?
We pick the bots, set them up in your account and run them. They do the work while you run the business.