An agent is a set of written standards that AI check measures your policies against. Blissbook gives you four to start with, and you can rewrite any of them, add your own, or build them out of the guidelines your team already keeps in a Word doc.

This is the part of AI check worth spending time on. The built-in agents are deliberately general, and an agent that knows your terminology, your jurisdictions, and your house style produces recommendations your team will actually accept.

AI check is currently in beta.

You'll see both names. Agents is what they're called when you pick them for a check, and Policy Skills is what they're called on the page where you manage them. They're the same thing.

Go to your Policy Library, click Settings in the top right, then click AI skills in the top right of that page.

***TODO: INSERT SCREENSHOT***

If you don't see AI skills, either AI check isn't enabled for your organization yet or you don't have the access it needs. Ask someone on your team who is an organizational admin, or contact us.

You can also get here from a check itself: click Edit AI Agents in the window that opens when you run an AI check. It opens the same page in a new tab, so you won't lose your place.

Every organization gets these the first time AI check is enabled, already released and ready to run:

***TODO: INSERT SCREENSHOT***

Start with Legal Compliance and Brand Voice. Legal Compliance has an Applicable Jurisdictions section that stays generic until you fill in the states and countries you actually operate in, and Brand Voice can't match a voice it has never read.

Open the agent, make your edits, and click Release in the top right.

***TODO: INSERT SCREENSHOT***

Write it the way you'd brief a new hire. Name the terms you use and the ones you avoid. Say which sections every policy needs, and what reading level you're aiming for. Specific instructions give you specific recommendations, and vague ones give you noise.

Note: Releasing is the step that makes your edits count. AI check only ever runs an agent's released version, so a draft edit changes nothing until you release it. It's the same release action you use on a policy, and it doesn't send anything to your audience.

Releasing an agent doesn't re-check your policies. Run the check again on the ones you want measured against the new version.

Click Add Policy Skills and choose Create a blank Policy Skill. Give it a name, type or paste your guidance, and click Release.

***TODO: INSERT SCREENSHOT***

One agent per subject works better than one agent for everything. A short agent covering just your job-title terminology gives you cleaner recommendations, and when a recommendation misses, it tells you exactly which agent to fix.

If your standards already live in a style guide or a compliance checklist, upload it and Blissbook writes the agents for you.

Click Add Policy Skills, choose Import Policy Guidelines, then drop in one Word (.docx), PDF, or text (.txt) file up to 25 MB and click Analyze Guidelines.

***TODO: INSERT SCREENSHOT***

Analyzing takes a few minutes. You can close the window and it keeps going.

When it finishes, Review Your Skills shows what it found: how many rules it pulled out of your document, which existing agents it updated, which new agents it created, and a Not Included section listing content it couldn't turn into rules. Read that last section. It's usually background or examples rather than an actual rule, but it's also where a rule you cared about will be hiding.

***TODO: INSERT SCREENSHOT***

Note: An import replaces open recommendations on any agent it changes, and Blissbook tells you before it does. A scanned PDF with no readable text can't be analyzed, so add that content to Blissbook as a document first.

Select the agent and use the three-dot menu to Archive it. Archived agents stop appearing when you run a check and stop influencing results.

***TODO: INSERT SCREENSHOT***

Archiving is reversible. Unarchive puts the agent back with its content and version history intact. Delete Permanently appears in the same menu once an agent is archived, and that one can't be undone, so archive unless you're certain.

The same menu has Clone Policy Skill, which is the easy way to try a rewrite: clone the agent, edit the copy, release it, and archive whichever version you like less.

Your agents are the part of AI check only you can write. Spend twenty minutes on Legal Compliance and Brand Voice now, and every check you run afterwards measures your policies against your standards instead of generic ones.