Talent pool rediscovery
Finds strong past candidates for a job: silver medallists, people turned down for timing, and applicants to similar jobs.
How it works
Pick a job. It looks through your company's past candidates in Recruit for strong matches: people who reached a late round but weren't hired, people who didn't move on for timing rather than skill (notice period, position filled, on hold, they declined), and people who applied to similar jobs. It ranks them against the job description with the reasons, and shows when each was last in touch and why they didn't move on. It leaves out anyone who asked not to be contacted, is blacklisted or in a cooling-off period, was hired, or hasn't been heard from in two years. You pick who to add: they go into the job's pipeline as prospects, or get an invite to the first round, only when you confirm. It never contacts anyone by itself, and candidates' names and contact details aren't sent to the AI model. Only your own company's candidates are searched.
About 2–6 credits per search, depending on how many resumes it reads
What it reads
- The job's title, description, skills and rounds
- Your past candidates' resumes, profiles and how far they got in earlier jobs
- Recruiters' reasons for past decisions, blacklist and cooling-off periods
When it starts
- When a recruiter asks, for a job they pick
What it can do
- Rank past candidates for a job with reasons
- Add chosen candidates to the job's pipeline or invite them to the first round (after you confirm)
What it never does
- Contact a candidate by itself
Safe by design
- One assistant, many agents. Ask the Employee assistant in the app or on WhatsApp; it calls the agents your company has hired that you may use.
- Hired, not switched on. Your admin hires each agent from the catalogue and chooses who can use it.
- Agents propose, people confirm. Anything that changes data, like a leave request, waits for a person to confirm it.
- Same access as the user. An agent sees only what the person asking is allowed to see.
- AI processing in India. Agents run on models hosted in India (AWS Mumbai).
- Budgets and a hard stop. Set a monthly credit limit per agent; agents stop when credits run out.
- Every run recorded. Admins see each run, the credits it used and what it did.
Frequently asked questions
What does the Talent pool rediscovery do?
Pick a job. It looks through your company's past candidates in Recruit for strong matches: people who reached a late round but weren't hired, people who didn't move on for timing rather than skill (notice period, position filled, on hold, they declined), and people who applied to similar jobs. It ranks them against the job description with the reasons, and shows when each was last in touch and why they didn't move on. It leaves out anyone who asked not to be contacted, is blacklisted or in a cooling-off period, was hired, or hasn't been heard from in two years. You pick who to add: they go into the job's pipeline as prospects, or get an invite to the first round, only when you confirm. It never contacts anyone by itself, and candidates' names and contact details aren't sent to the AI model. Only your own company's candidates are searched.
Can the Talent pool rediscovery change data on its own?
No. It asks a person to confirm before it will: add chosen candidates to the job's pipeline or invite them to the first round. It never does the following: contact a candidate by itself.
How much does the Talent pool rediscovery cost?
About 2–6 credits per search, depending on how many resumes it reads. Credits are a paid add-on to any flowwork.ai plan at ₹100 (US$ 1.19) per 1,000 credits, and new companies get 500 free trial credits for 30 days.
Where is the data processed?
Agents run on AI models hosted in India and see only what the person using them is allowed to see. Admins see every run and the credits it used.
Other agents
Answers job seekers on your careers site from your published jobs and FAQ; candidates can check their status and ask to move an interview.
Turns a short brief into a complete job, in your company's style, ready to review.
Explains your Recruit reports: what changed, where hiring slows down and where to look.