Manager tools

Quarterly check-ins and annual reviews, without the blank page.

Use AI to draft an assessment from your notes. Review the wording and choose the rating yourself.

Between reviews, keep a light record: goals, a ten-minute check-in each quarter, and what you owe each person. When a review is due, answer a few guided questions and edit the draft that comes back.

The people you write about never need an account.

How it works

Three parts, in the order they happen.

1 · Through the year

Keep the record

Goals for the year, each with a measure and a target. At the end of every quarter, a short check-in: where each goal landed, what went well, what got in the way, and a performance band for the quarter (below, meeting or exceeding expectations). Ten minutes, while you still remember it.

2 · When a review is due

Answer the guided questions

4 questions for a quarter, 7 for the year, most with a tick-list to jog your memory before you type. Notes are enough. In either, you can ask up to ten colleagues three written questions — a couple of people for a quarter, more for a year.

3 · The document

Edit the draft, set the band, export

Your notes, the record and any colleague input become a document a person can read. Every sentence is editable. The band is yours to set with a reason beside it, and the whole thing downloads to hand over.

Worked example

Watch one being written.

Explore a fictional quarterly or annual review, from notes to finished assessment. The two people and their figures are invented. The questions, tick-lists and documents are the ones the app uses, and both drafts pass its checks. Pick a period and step through what went in and what came out.

Q3 2026 · Ravi, Customer Support Lead

Four questions and two colleagues, both of whom say the same thing the record already says. The short one that gets written four times a year.

Step 1 of 5

What was already recorded about Ravi

Kept through the year, a quarter at a time. Every number the draft uses has to come from here — it may not use a figure that was never recorded.

Ravi's goals for 2026, and how each quarter landed

Set at the start of the year. Each quarter, a ten-minute check-in records where every goal stands and a performance band for the quarter.

GoalQ1Q2Q3Q4
Cut first response time on the self-serve queueTarget: Under 4 working hoursAt risk11 hoursOn track6 hoursOn track4 hours in September, holding for six weeks—
Write the billing escalation runbook and get it usedTarget: Two other people running them unaided by the end of the yearnot recordednot recordedOff trackDrafted, nobody else running escalations—
Bring repeat contacts downTarget: Under 12%not recordedAt risk17%On track13%—
Check-in bandMeeting expectationsMeeting expectationsMeeting expectations—

The latest check-in (Q3), in the manager's words

Went well
Down to 4 hours and holding.
Got in the way
Escalations still all coming to him.
Ravi needs from their manager
The review slot, from me.

Open follow-ups from 1:1s

  • I will book the review slot for the billing runbookmanager · due Sep 5, 2026 · overdue
  • Ravi will pick the two people to train on billing escalationsRavi · due Oct 31, 2026
The record · 1 / 5

Guardrails

Five things the draft may never do.

Checks that run over the finished text every time, whichever writer produced it. Both drafts above pass them.

  1. Quote a colleague

    Any run of six or more words that also appears in someone's raw answer is caught — checked against what they actually wrote, not the anonymized copy.

  2. Attribute a view to someone who was not asked

    “Colleagues felt…” is flagged when no colleague input was collected. Your own account of how someone works with others is fine; that is your observation.

  3. Call one person's view a pattern

    One reply is used, and used as one person's view. Two people agreeing is the smallest claim of a pattern that can fairly be made, and the draft says so.

  4. State a number that is not in the record

    Every figure in the prose is matched against the recorded goals, targets, results and check-ins. This is the check that most often catches something, and a plausible invented number is the most damaging thing a generated document could contain.

  5. Open a formal process

    Warnings, performance plans, dismissal and severance are processes with legal form, and the language for them is rejected outright. An assessment records; it does not initiate.

A draft that fails a check is still shown to you, with the failures listed above it. This is your private preparation, and withholding it would leave you with nothing and no idea why.

Questions

Does the AI write my performance reviews for me?
It writes the prose from your notes. You answer 4 guided questions for a quarter or 7 for a year, and it turns those answers, with the goals and check-ins you recorded, into a document a person can read. It is given nothing else, so it cannot add a figure, invent an occasion or set the rating. Where your notes are thin, the document says what it cannot support.
Does it decide the rating?
No. It is told to leave the performance band empty, any band it returns is cleared, and the document fails its checks if a band appears without your written reason. You choose below, meeting or exceeding expectations yourself, beside a definition of each, against this person's own goals rather than their colleagues'.
Why do my answers come before the colleague input on the page?
Because the order changes what gets written. If you read colleagues' views first, you tend to write a summary of them. If you write first, you have your own account, which colleagues can confirm or contradict. So your questions sit above the colleague input and the button that writes anything, and each tick-list sits above its box to remind you what the quarter held.
What does the quarterly assessment ask, and what does the annual one add?
Quarterly: What did they actually deliver this quarter; Where did the quarter fall short of what you both expected, and what happened; What did they get noticeably better at; What did you say you would do for them that you have not done. The annual set keeps those and adds three that only make sense over a year: how they worked with other people, the one change that would make the biggest difference next year, and what next year should look like. 4 of the quarterly questions and 6 of the annual ones have a tick-list above the box, because memory favors the last few weeks and the loudest project.
What exactly is sent to the AI?
Generating a draft sends the record to Anthropic's API, and the page says so at the button. It sends your answers, the goals, targets and quarterly results you recorded, anything you ticked (marked as your account, not evidence), colleague input with the names removed, and any summary the person chose to share, marked as their own account. No email address is sent.
What is the AI told to do?
To turn notes into sentences a manager could say out loud, keep colleague input and the person's own summary apart, say what the document cannot support, state both sides of a disagreement without resolving it, and leave the band empty. Checks then run over the text to enforce the same rules.
What happens if the model fails or produces something bad?
A draft that is not the right shape is rejected and tried once more. If that fails too, Facets writes the same document from the same inputs without AI, with the same sections, and the record shows which way it was written. Then the checks run, and a draft that fails one arrives with the failure named at the top. You decide what to do with it.
Can I use the manager tools without sending anything to an AI provider?
Yes. An owner or admin can turn model-written output off for the whole workspace in Settings → Workspace, and nothing from the manager tools is then sent to a model. Facets then writes the whole document from the same inputs without AI, as it does when no model is set up or one fails. Conversation guides, agendas, suggested actions and goal wording come from their standard templates. If you need a narrower switch, such as one for a single manager, tell us through the contact page.
Is a tick counted towards anything?
No. A tick adds to no score, band or total. The counts are kept in the audit trail so that where a statement came from has an answer, and nothing reads them back. Ticking a lot does not make the document more confident either: how much it hedges depends only on what you write.
Can I edit what it writes?
All of it. You can rewrite any sentence, add or delete sections, or redraft from your updated answers. For now the editor is one box holding every field of the document, plain but complete. The checks run again on what you save, and the record notes that the text was edited by hand. Setting the band is separate from editing the text.
Can the person being assessed read it?
You can export the whole document and give it to them, and it is written to be read that way — what it cannot support first, the rationale beside the band, and a closing line saying what fed it. There is no in-app view for them yet. Separately, in some places a subject access request can reach what has been written about an employee, so assume they will read it. The app says so wherever you type about someone.
Is this connected to the team survey or the Leadership 360?
Not automatically. Those are feedback, and this is a performance record. Facets does not add survey feedback to the record, and nobody with an account can read another person's team survey ratings or comments as written. The one route is the person's own choice: after a Leadership 360, they can send you a summary, and if you attach it to their record, it is used when drafting their assessment, as the end-of-year example shows.
Where do the examples on this page come from?
The people and every figure about them are invented. The rest is the product's own: the questions and tick-list labels come from its question bank, and the documents are drawn by the same component the app uses. Both examples pass the checks a real draft must pass, run against the colleagues' raw answers, which is where a leak would show.