PlatformKandi
Ask for the work. Approve it.
Sixty tools on your desk, and approval cards for anything that matters.
Kandi
How it runs
Ask
Source, draft, schedule or probe, in chat or Slack.
It works
Plans the steps and runs them itself.
You approve
Email never leaves without a card. Approve, edit or reject.
Logged
Every run recorded, tool by tool, with timings.
Built in
The morning list
A nightly sweep writes what's stuck. It executes nothing.
Schedules
Do it once, then weekly. Same approvals.
Where you are
In the app, in Slack, and on your careers site.
Questions buyers ask
Does it ever contact a candidate on its own?
Email never sends without an approval card — scheduling, replies and auto-batches all wait for one. Voice campaigns are prepared by the agent and launched through the calling flow you configure.
Can I see what it did while I was away?
Yes. Every run is logged — each tool it used, in order, with timings — and every message and call it produced is on the record.
Do different recruiters get different setups?
Agents are configured per organisation: which tools each one holds and which actions wait for a card. The approval boundary itself doesn't vary by seat.
What model is behind it?
It routes to different models by task and that changes as better ones ship. What stays fixed is the approval boundary, which is enforced in our own code rather than by the model.
See it on one of your own roles.
Bring a clinical role. See how the platform handles sourcing, outreach and initial screening for your team.