How do AI Employees source and draft candidate outreach every day?
An outbound sourcing AI Employee that runs each day, finds candidates on a professional network for each open role, checks your ATS so no one already in the pipeline gets a duplicate reach out, and drafts a personalized outreach email referencing each candidate's real background, then hands every draft to the recruiter to review and send.
×Filling an open role isn't just reading the applications that arrive. The best candidates for a lot of roles aren't applying anywhere; they're already employed and not looking. Finding them means searching a professional network by hand, checking the ATS to make sure whoever you found isn't already in the pipeline, and writing an intro that actually references their background instead of a generic template. Done well, it's hours of work per role. Done under time pressure, it gets skipped and the role stays open longer. The usual shortcuts make it worse. A generic sourcing tool exports a list of profiles with no reference to the pipeline, so recruiters rediscover people who are already in the ATS. A templated outreach message goes out to everyone in the list with a name swapped in, and candidates who get a lot of these can tell instantly. Neither problem gets fixed by working faster. They get fixed by connecting the systems that already have the answer.
The candidate sourcing AI Employee runs once a day, scoped to an open role. It searches a professional network for candidates matching that role's profile, checks the role's ATS pipeline so it never proposes someone already there, and drafts a personalized outreach email for each new match, referencing that candidate's real background, not a template. Every draft lands in the recruiter's inbox for review; the AI Employee never emails a candidate and never touches the ATS.
See exactly how the work gets done.
Runs on a daily schedule
Once a day, a fresh run scoped to one open role sources and dedupes against the current state of the pipeline. Nothing carries over from the day before.
Carries the role's sourcing profile as a skill
What 'a match' means for this role travels with the AI Employee as a skill and memory: the title, seniority, skills, and any other criteria worth searching for, alongside the outreach angles that make a message worth opening. When the role's bar changes or a message pattern gets better replies, write it down and the next day's batch reflects it.
Connects to your systems, with permissions you set
It searches the professional network for candidates matching the role's profile, checks the ATS pipeline so anyone already applied, contacted, or passed on gets skipped rather than resurfaced, and drafts to Email a personalized message per new candidate, held for the recruiter. It connects with permissions you set; credentials stay in memory, never written to disk, never exposed to the model.
Stops at the draft
It never sends an outreach email itself and never adds, moves, or tags anyone in the ATS. It sources and drafts only. Its job ends at the draft in the recruiter's inbox.
Hands the batch to the recruiter
Each morning brings a small batch of new candidates for the open role, each with a drafted email that references their real background and a note on why they matched. The recruiter reads each one, edits where they want, and sends it themselves, or adds the candidate to the ATS themselves, if they choose to. Nothing leaves your environment except the drafts.
Runs in your environment
Every run happens in your own infrastructure, scoped to one open role. Your data never leaves it; only the drafted emails do.
Pauses for a named human's signature
The AI Employee never sends outreach itself and never adds a candidate to the ATS. Every draft pauses for the recruiter to review, edit, and send, and the ATS is theirs to update.
Dedupe before draft
It checks the role's ATS pipeline before drafting anything, so a candidate already applied, contacted, or passed on never gets a duplicate reach out.
Credentials stay protected
The ATS and professional network credentials connect with permissions you set; they stay in memory, never written to disk, never exposed to the model.
You own every rule
The sourcing profile, the outreach angles, and the per system permissions are yours, versioned and changed on your terms, not in a vendor dashboard.
Sourcing for an open role now starts with a batch already searched, deduped against the pipeline, and drafted with a real reference to each candidate's background. The recruiter's day starts with review instead of research, and every send and every ATS change still stays with them.
Every day
New candidates sourced and deduped per open role
Zero
Duplicate reach outs to candidates already in the pipeline
3 systems
ATS, professional network, and Email in one AI Employee
Our free AI audit shows you where AI fits, what your security risks are, and gets your first AI employee working.
How do you answer HR policy questions without pulling someone off their work?
Reads the HR inbox every 15 minutes, drafts replies grounded in documented policy, and escalates anything legal, personal, or comp related to Slack. It never sends and never makes a policy call.
×
How do you schedule a whole interview loop without the back and forth?
Finds candidates ready to schedule, checks the panel's real Calendar availability, and drafts a slot proposal plus an invite per interviewer. It never sends and never touches a hiring decision.
×How do you screen every applicant against the same rubric fairly?
Reads each application against the role's written rubric, writes a structured screen with a score and supporting quotes, and proposes interview slots for strong matches, leaving every advance or reject call to a person.
×