Calibration assistant
Flags what to discuss in calibration: rating spreads, ratings without results, 9-box and hike mismatches.
How it works
For HR during calibration of a review cycle and its hike sheet. The agent checks the numbers and flags managers who rate much higher or lower than the others, final ratings far from the suggested weighted rating, ratings not backed by goal or KRA results, 9-box placements that contradict the rating, and hikes that don't follow the hike rules or the rating or go over the budget. Department, gender and tenure patterns are shown only as group counts, for groups of five or more, and never as a judgement about a person. Each flag comes with its numbers and a question to discuss. It never changes a rating, a 9-box placement or a hike.
About 1 credit per check; nothing when there is nothing to flag
What it reads
- The cycle's calibration: self, manager, peer, KRA, suggested and final ratings, potential
- Managers' goal ratings
- Department, gender and joining date from People (for group counts only)
- The hike sheet, hike rules and budget (with the compensation permission)
When it starts
- When HR runs it from Agents or asks the Employee assistant
What it can do
- Flag ratings, 9-box placements and hikes to discuss
What it never does
- Change a rating, a potential or a hike
- Judge a person by gender or any other group
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 Calibration assistant do?
For HR during calibration of a review cycle and its hike sheet. The agent checks the numbers and flags managers who rate much higher or lower than the others, final ratings far from the suggested weighted rating, ratings not backed by goal or KRA results, 9-box placements that contradict the rating, and hikes that don't follow the hike rules or the rating or go over the budget. Department, gender and tenure patterns are shown only as group counts, for groups of five or more, and never as a judgement about a person. Each flag comes with its numbers and a question to discuss. It never changes a rating, a 9-box placement or a hike.
Can the Calibration assistant change data on its own?
No. It never does the following: change a rating, a potential or a hike; judge a person by gender or any other group.
How much does the Calibration assistant cost?
About 1 credit per check; nothing when there is nothing to flag. 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
Drafts your OKRs and check-ins, and your self review when a cycle is open. You edit and confirm.
Prepares a manager's 1:1 with a report, or your own side of it, and turns meeting notes into follow-ups you confirm.
Who could step into a job, who is ready for promotion, and which critical roles have no ready successor.