Referral matcher
Suggests which employees are best placed to refer someone for an open job, and drafts the ask.
How it works
Pick an open job. It suggests the employees best placed to know someone for it, from what your company already has: people in the same department or kind of role, people who did this work or worked at other companies before (from their profile in People: experience and education), and people whose earlier referrals were hired. Every suggestion shows its reasons, and the scoring is fixed rules, not AI. It never looks at anyone's contacts, phone book or social networks. You pick who to ask: it drafts a short message per person with the job's referral link, and each one goes out (bell and email, and WhatsApp for people who turned it on) only when you confirm it. Employees can also ask the assistant which open roles they could refer for and how their own referrals are doing.
Suggestions are free; about 1 credit to write the ask for a job
What it reads
- The job's title and skills
- Employees' role, department, past employers and education in People
- How earlier referrals went in Recruit (hired, in process)
When it starts
- When a recruiter asks, for a job they pick; employees ask about open roles and their referrals
What it can do
- Suggest who could refer for a job, with reasons
- Ask chosen employees for a referral, with the job link (after you confirm)
What it never does
- Read anyone's contacts or social networks
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 Referral matcher do?
Pick an open job. It suggests the employees best placed to know someone for it, from what your company already has: people in the same department or kind of role, people who did this work or worked at other companies before (from their profile in People: experience and education), and people whose earlier referrals were hired. Every suggestion shows its reasons, and the scoring is fixed rules, not AI. It never looks at anyone's contacts, phone book or social networks. You pick who to ask: it drafts a short message per person with the job's referral link, and each one goes out (bell and email, and WhatsApp for people who turned it on) only when you confirm it. Employees can also ask the assistant which open roles they could refer for and how their own referrals are doing.
Can the Referral matcher change data on its own?
No. It asks a person to confirm before it will: ask chosen employees for a referral, with the job link. It never does the following: read anyone's contacts or social networks.
How much does the Referral matcher cost?
Suggestions are free; about 1 credit to write the ask for a job. 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.