> For the complete documentation index, see [llms.txt](https://guides.tability.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://guides.tability.io/docs/playbooks/run-your-okr-engagement-report.md).

# Run your OKR engagement report

See who's checking in, who's gone quiet, and who to celebrate, with the messages to act on it ready to send.

To start, share this page with your AI assistant and say:

> Run this playbook

The instructions below are for your assistant. You don't need to read or copy them.

### Instructions for AI assistants <a href="#instructions-for-ai-assistants" id="instructions-for-ai-assistants"></a>

If the user shares this page (or an article linking to it) and asks you to run it, follow the steps below from start to finish. If they only ask you to read, summarize, or edit it, do that instead.

#### Ground rules <a href="#ground-rules" id="ground-rules"></a>

* Ask one short question at a time. Deliver the first report within three questions. Reuse anything the user has already told you.
* Confirm before touching a Tability workspace. Only use a workspace the user gives you by URL. Show its name and ID and get a yes before reading from it.
* Keep names of people who missed updates private. They appear only in the report and in private nudges to the user. Public messages only celebrate.
* Judge habits, not performance. A red key result isn't an engagement problem, and an honest early red is something to celebrate.
* Base every call-out on evidence. Cite the check-in or goal behind it. Don't make up numbers, and if the API doesn't expose something (such as whether check-ins were read), say so instead of guessing.
* Stay read-only. Don't write to Tability or change settings; give the user the steps.
* Draft messages for the user to send; don't message anyone else.
* Verify scheduled jobs. Read them back before saying they worked.
* If something is blocked, keep the work done so far, tell the user the exact next step, and carry on with what you can.

#### 1. Set the scope <a href="#id-1-set-the-scope" id="id-1-set-the-scope"></a>

Start with a brief intro and ask:

> Which Tability workspace should I report on, and for which team or plans?

Confirm the workspace, then ask only what you still need, such as:

* The period to cover. Default to the last four weeks.
* The expected check-in cadence. Default to weekly.
* When the team meets, so the report can land the day before.
* Whether this is a one-off or a weekly report.

#### 2. Pull the engagement data <a href="#id-2-pull-the-engagement-data" id="id-2-pull-the-engagement-data"></a>

For each person who owns key results in scope, collect:

* **Check-ins:** how many were due, done on time, late, or missing.
* **Overdue:** key results where they've missed two or more check-ins in a row.
* **Streak:** their current run of on-time check-ins.
* **Comment quality:** whether comments are empty, one-liners ("it's good"), metric-only ("moved from X to Y"), or useful (what happened, why it matters, and what's next).
* **Confidence:** yellow three or more times in a row; green while progress stalls; red flagged early, especially with a request for help.
* **Team engagement:** comments and @mentions on teammates' check-ins, and whether they read teammates' check-ins, if available.

Also total the team's figures for this period and the one before, to show the trend.

If the team isn't using Tability yet, there's nothing to report. Tell the user, and offer the expectations note from step 4 to get started.

#### 3. Build the report <a href="#id-3-build-the-report" id="id-3-build-the-report"></a>

Write the report in this order:

1. **Headline:** check-in completion this period against the last, the number of people overdue, the share of useful comments, and one line on the direction.
2. **Celebrate:** up to five people, each with the reason and evidence: long streaks, early honest reds (and the help that followed, if known), well-written check-ins (quote a line), helpful comments on teammates' goals, and turnarounds from red or yellow to green.
3. **Nudge (private):** people with overdue check-ins, the key results affected, and how long they've been missing. Longest gap first.
4. **Coach (private):** people with repeated yellows, green with stalled progress, or thin comments, each with one specific suggestion.
5. **Process signals:** if a problem is widespread rather than individual, name the likely cause:
   * Many missing check-ins: expectations aren't clear, or OKRs aren't discussed in meetings.
   * Many thin comments: there's no check-in format.
   * Long yellows and few reds: people don't feel safe marking red.
   * Little commenting on teammates' goals: progress isn't visible or discussed.

Save it as {team-name}-okr-engagement-{date}.md using the outline at the end of this page. Share it with a short summary: the headline numbers, who to celebrate, and who needs a nudge.

#### 4. Draft the follow-ups <a href="#id-4-draft-the-follow-ups" id="id-4-draft-the-follow-ups"></a>

Draft these for the user to send:

* **Shout-outs** for the team channel or meeting. For a streak: "Congratulations to \[name] for not missing a check-in in \[X] weeks. Thanks for keeping our goals on track." For an early red: "Thanks to \[name] for flagging the issues with \[key result]. We were able to get \[help], and now it looks like we'll get back on track."
* **Private nudges** for each overdue person: friendly and specific, naming the key result, offering help, and asking them to fill in missed check-ins so the record is complete.
* **Coaching notes** for each person in Coach, with a short example of a better check-in.
* **Team meeting agenda:** shout-outs first, then red and yellow key results, then what's stuck and where people need help.

For each process signal, recommend a fix and give the user the steps:

* **No check-in format:** add a custom check-in prompt (admin settings > Customise > Custom check-in prompt; admins and workspace owners only). Suggest one format, such as What / So what / Now what, or Did this week / Will do next week / Blockers.
* **Long yellows:** cap repeated yellows (open the plan, select ... > Plan settings, and enable the At risk limit), and draft a note explaining that red means "I need help", not "I failed".
* **Unclear expectations:** draft an expectations note: update weekly in about 15 minutes, read teammates' check-ins, and discuss OKRs in a weekly or fortnightly team meeting. Mention that overdue check-ins show under Dashboards > People, so the team knows updates are tracked.
* **Low visibility:** add an OKR slot to team meetings, and share company OKR progress at all-hands using Presentation mode or an export to PowerPoint or Google Slides.

#### 5. Make it weekly <a href="#id-5-make-it-weekly" id="id-5-make-it-weekly"></a>

If the user wants a weekly report and this tool can run scheduled tasks, create one that runs the day before the team meeting. It should repeat steps 2–4, compare against last week, and send the report and drafts to the user only. Give it the latest report file and everything it needs, since it won't remember this conversation.

If the scope covers several teams, add a monthly task that suggests a team to highlight: no missing updates, good collaboration, and progress on goals.

If scheduling isn't available, give the user a prompt to run themselves each week.

#### 6. Wrap up <a href="#id-6-wrap-up" id="id-6-wrap-up"></a>

Share the report and a short summary: the headline numbers, who to celebrate, who to nudge, the drafted messages, any settings to change, and when the next report runs.

#### Report outline <a href="#report-outline" id="report-outline"></a>

```markdown
# {Team}: OKR engagement report, {date}

Period · Plans · Workspace · Check-in cadence

## Headline

## Celebrate

## Nudge (private)

| Person | Key result | Last check-in | Missed in a row |

## Coach (private)

## Process signals and fixes

## Drafted messages

## Settings to change

## Schedule and links
```

END OF PLAYBOOK
