Catch drafts that break your writing rules
Stand up a **Style check** agent. Paste outbound draft. Compare against your glossary and banned-phrases context. Emit **violations table + severity + fix hints**. Run **before** approval steps ([Set up a content review pipeline](/tutorials/set-up-a-content-review-pipeline)) so reviewers argue substance, not hyphen wars.
Plus: three Admin-Agent passes: compare two drafts for glossary regressions, propose **glossary patch bullets** from your last five violation logs, and draft a friendly **creator cheat-sheet** paragraph for Slack when the same mistake repeats.
| Audience | Everyone · Admins |
|---|---|
| Time | ~10 min |
| Prerequisites | A real source for your writing rules exists ([Add your first context file](/tutorials/add-your-first-context-file): product names, casing, words to avoid, and examples of on-brand sentences). Agent basics ([Create an agent from scratch](/tutorials/create-an-agent-from-scratch), [Give your agent its job description](/tutorials/give-your-agent-its-job-description)). Helpful: [Set up a content review pipeline](/tutorials/set-up-a-content-review-pipeline) when checks slot ahead of publish. |
| You'll end up with | One **Style check** agent with output sections **PASS_OR_FAIL**, **Violations**, **Suggested fixes**, and **Glossary gaps**. Plus a habit: **you** paste drafts **because you prompted**. Optional workflow step ([Run a workflow](/tutorials/run-a-workflow)) before human sign-off. |
When a tutorial shows italic text in quotation marks, it usually mirrors a label or helper string inside Auxot. Product copy changes between releases — if something reads differently in your workspace, trust what you see on screen.
Callouts with a Worth knowing gold accent are meant as must-read context before you move on. Blockquotes that open with Tip are lighter, optional depth.
Why this matters
Writing rules stop being read once they’re stored in a folder nobody opens. Teams still ship “Auxot’s” vs “Auxot is”, revive banned competitors’ framing, or bury required disclaimers, usually five minutes before send.
This agent does not silently read every file in your company. You paste the draft because you prompted: same human-in-the-loop pattern as the rest of the series. Its job is simple, mechanical comparison work: quote the offending snippet, cite which glossary line it broke, propose a neutral rewrite. You accept or reject fixes (Set up a content review pipeline).
Pair with customer-facing comms (Ship clear customer communications) and internal answers (Build an internal Q&A agent for your team) so one glossary feeds both outward copy and what teammates hear in Slack.
Consistency is a context file. Checking is a prompt.
Quick start
- Freeze a glossary slice. Under ~800 words in one context file if possible; prefer pointers over novels (Add your first context file).
- Create the Style check agent. Charter: no opinion on strategy; only glossary alignment; UNKNOWN when rule missing; stop invented policies.
- Paste one risky draft. Marketing paragraph plus support macro; redact customer names.
- Read the Violations table. If severity feels random, tighten rubric in charter and rerun.
- Slot before approval. Workflow step order: draft → style check → human approve (Run a workflow).
Done? Ten saved reports: dated, showing shrinking repeat violations; evidence for Run a quarterly review of your agents.
The agent can do that?
1. Compare two drafts for regressions
Chat → Admin Agent:
Glossary excerpt: […]. Draft A: […]. Draft B: […]. Table with rows Rule / A status / B status / note. Flag **REGRESSION** if B worse. Max eight rows.
Why it’s non-obvious: Iteration loops sometimes unfix voice; side-by-side catches regressions after you paste both versions.
2. Glossary patch bullets from violation logs
Violation tables (paste five): […]. Current glossary excerpt: […]. Output <=10 bullets **ADD / TIGHTEN / DEPRECATE**. Each cites occurrence count. Markdown, no full rewrite.
Why it’s non-obvious: Guides improve from repeat misses; structured deltas beat hallway agreements (Keep your context files honest and fresh).
3. Creator cheat-sheet blurb
Top three recurring violations this month: […]. Draft <=90 words, supportive tone. Ends with link to glossary doc. Plain markdown, no shame language.
Why it’s non-obvious: Private nagging scales poorly; one channel note reduces repeat coaching (Collect useful feedback on your agents when friction shows up as complaints).
Go deeper
Locale work
Adaptation checks claims and locale tone (Adapt copy with human review): run style check on adapted output too; two passes, two purposes.
Skills
Promote stable rubric language (Create a Skill): attach glossary; fewer pasted blocks.
Maintenance
When glossary meaning shifts: announce agent behavior deltas (Update your agents without breaking the team). Stale rules produce false positives the team learns to ignore.
Privacy
Paste only what review needs: scrub identifiers; align handling (Run a data privacy review before you ship).
Walkthrough
Step 1: Pick one channel pilot
Support macros beat whole blog archive; tight scope trains the rubric.
Step 2: Seed ten intentional violations
Synthetic draft: retired product name, wrong casing, and banned hype word; confirm table catches all three.
Step 3: Tune severity labels
BLOCK vs WARN vs FYI: align with who can override; document in charter.
Step 4: Pair with review pipeline
Reject loop once; confirm style feedback reaches drafting agent description (Set up a content review pipeline).
Step 5: Monthly glossary retro
Merge patch bullets you trust; archive old excerpts; note date in context header.
What’s next
- → Add your first context file. The glossary lives here; agents read it because you attached it.
- → Set up a content review pipeline. Slot style check before the human rubber-stamp moment.
- → Build an internal Q&A agent for your team. Same vocabulary should back internal answers; one guide, two surfaces.
- → Ship clear customer communications. External announcements benefit first; pair checks before send.
- → Adapt copy with human review. Claim integrity plus voice; stack checks when stakes get higher.
- → Automate weekly checkups on your agents. Voice rules and glossary files need the same clock as agents; rot shows up in Settings before it shows in brand.
Reference
- Pages in Auxot: Chat, Settings → Agents, Settings → Context Files, Skills, and optional Workflows
- See also: Adapt copy with human review, Automate weekly checkups on your agents, Run a workflow, Update your agents without breaking the team, Keep your context files honest and fresh, Run a quarterly review of your agents, Collect useful feedback on your agents