Runs your review cycle without the spreadsheet. Goals and 1:1 notes live in one place, every 1:1 is summarised with its actions, the manager's review is drafted from the year's evidence, missing reviews are chased, calibration outliers are flagged before the meeting, and the cycle report goes out on Monday. Employees get a portal for their goals and self-review; managers get one for their team. Comes with Leo, a Performance Cycle Coordinator who keeps every cycle on schedule.
Installs in about 25 min, verified with a smoke test.
One named coworker, the agents it orchestrates, and the data, knowledge, and tools underneath. This is the real manifest, not a mockup.
The employee routes each request to the right worker. Specialists collaborate behind a router in the agentic team, while single-purpose agents handle focused jobs. Agents read and write the tables, ground answers in the knowledge bases, and act through your connected tools. Every write is gated and traced.
Every agent's tasks, every table's schema, every trigger. Read it all before you sign in.
Calm, precise, fair. Leo keeps the cycle on its dates, makes sure every review is written from evidence, and never lets a rating travel further than it should.
The chat on both portals. Explains the scale, the timeline and how to write goals and reviews, from the guide. Never discusses anyone's rating.
Turns a manager's raw notes into a short summary, the actions with owners, and any risk worth watching.
Reads the person's goals, their 1:1 summaries and their self-review, and drafts the manager review with examples and a suggested rating.
Decides whether a review is due soon or late and drafts the nudge for the reviewer.
Compares the proposed rating with the self-review, the goals and the review's examples, and flags what the meeting should discuss.
Counts reviews by status per department, lists overdue reviewers, calibration flags and goals at risk, and sends it to the People lead.
The rating scale, how to write goals and reviews, what calibration checks, and the timeline. Replace the starter text with your own.
Setup asks the governance question before anything runs: for example, should the employee require human approval before sending external emails?
We use analytics cookies to see which pages help and which don’t. Nothing loads until you choose. Cookie Policy
Hello there.
AI agent. It can make mistakes, and a human reviews anything that matters.