AI check reads a policy against your own writing standards and comes back with specific recommendations you can apply in one click. Run it before a policy reaches your employees and you catch the compliance gap, the off-brand paragraph, and the sentence nobody will understand while they're all still easy to fix.

AI check is currently in beta.

A few things need to be true first:

Note: AI check runs on policies only, and not on archived ones. It never runs on documents, pages, or templates, and your audience never sees any part of it.

Open the policy from your policy library, go to the AI Check tab in the policy details panel, and click Run AI Check...

***TODO: INSERT SCREENSHOT***

A window opens asking Run an AI Check on this Policy? Under Select your Agents, every agent is already ticked. Untick any you want to skip, then click Run AI Check. The check starts right away.

***TODO: INSERT SCREENSHOT***

If you want to change what the agents look for before you run anything, click Edit AI Agents. That opens the Policy Skills page in a new tab, so your selection here is still waiting when you come back.

Select the policies you want in the policy library using the checkboxes on the left, then click AI Check... in the toolbar. The same window opens, and the title tells you how many policies you're about to check.

***TODO: INSERT SCREENSHOT***

Each policy gets its own check, so results come back one at a time rather than all at once. Policies you only have view or comment access to are left out, along with any archived policies in your selection.

A banner appears at the top of the policy reading AI Check is running. Editing is disabled until the AI Check finishes. While a check is queued or running, the policy draft is read-only, so the text your recommendations are anchored to can't move under them.

***TODO: INSERT SCREENSHOT***

Checks usually take a few minutes, and a long policy checked against a large set of agents takes longer. If one doesn't finish, the panel tells you: The last AI Check didn't finish. Try running it again.

Note: Editing locks the moment a policy is queued, not when its check actually starts. If you check 20 policies at once, expect several of them to be read-only for a while.

When the check finishes, the AI Check tab shows the result, the date it was last checked, which agents ran, and a result for each one.

***TODO: INSERT SCREENSHOT***

A policy lands in one of five states:

Note: These are separate from the phases you see in a policy review, which track what your colleagues decided. A policy can be Approved by your reviewers and still sit at Rework Needed here.

Each recommendation appears as a card in the AI Check panel, showing which agent raised it and why. Hover a card to see your options.

***TODO: INSERT SCREENSHOT***

You can also reply on a card to leave a comment, and type @ to tag a colleague the same way you would on any policy comment. Useful when a recommendation is really a question for Legal.

***TODO: INSERT SCREENSHOT***

Agents surface issues for you to judge. They don't approve a policy, and their recommendations aren't legal advice, so read each one before you apply it. For how Blissbook handles your content when AI features run, see AI governance at Blissbook.

Note: If the policy text changed after the check ran, some recommendations no longer match anything and get skipped. Apply All tells you when that happens, and re-running the check gets you a fresh set against the current text.

Open recommendations never stop you from releasing a policy. You can publish with them still outstanding and come back to them.

When an agent gets something wrong, tell us. Hover the card and click the flag icon to open Report this recommendation.

***TODO: INSERT SCREENSHOT***

Pick what's wrong with it - This isn't accurate, Doesn't apply to this policy, It's pointing at the wrong text, The suggested wording is worse, We already cover this elsewhere, The severity is wrong, or Something else. Add detail under Anything else?, which is required if you choose Something else, then click Send Report.

Also reject this recommendation is ticked by default, so reporting a bad recommendation also clears it from your policy. Untick it if you'd rather keep the recommendation and decide later.

Each recommendation can be reported once. Reports come to our product team, and they're how the built-in agents get better.

Run a check as often as you like. Once every recommendation is handled, the panel shows Resolved and you can check the policy again.

Note: Starting a new check discards any recommendations you haven't accepted or discarded yet, and Blissbook warns you first with Existing AI recommendations will be discarded. Accepted and discarded recommendations can't be brought back, so finish a set before you re-run.

Editing an agent doesn't re-check anything on its own. After you release a change to an agent, run the check again on the policies you want measured against the new version.

The AI Check column sits to the right of the policy name and appears on its own the first time you run a check. It shows the result of the most recent check, or Checking and Queued while one is in flight. Hover a cell to see when the policy was last checked and what's still open.

***TODO: INSERT SCREENSHOT***

The column sorts worst-first by default, so whatever needs attention comes to the top. Filter it by Passed, Resolved, Rework Needed, At Risk, or Not Checked to work through one group at a time, and save that as a view if it's a list you'll come back to.

At the bottom of the library, the AI Check bar breaks your whole policy set down by result. It's the quickest way to see how much of your library has been checked at all, and clicking a segment filters the table to it.

***TODO: INSERT SCREENSHOT***

Once you've been through your library once, this stays small: check a policy when you write it, check it again when you change it, and let the column tell you what's left.