<-Back to All Articles
Ditto: From draft to deploy.
Introducing Style Guide Analytics and Feedback on AI Suggestions

Get real-time analytics on how your content system is being used, how it’s performing, and give feedback to the output it generates.

Now available in all Ditto workspaces: Get real-time analytics on how your content system is being used, how effective it’s performing, and give feedback to the output it generates to train it over time.

The problem: one-off guidance doesn't scale

Most teams start copy enforcement the same way. A Claude skill here. A custom agent instruction there. A markdown file passed into a system prompt. Each one solves a specific problem in the moment, but each one is completely invisible once it's deployed. You know you dropped the rules in there, but the results still aren’t what you expect, every time. And when something slips through — a tone that's off, a term that's wrong, a pattern that keeps recurring — there's no signal. Just copy that doesn't match your standard, and no way to trace why.

The fragmentation compounds fast. Everyone thinks enforcement is happening, but nobody can prove it.

Ditto style guides replace that patchwork with a single, centralized control panel for your content standards. One place to write your rules, see how they're being used, and one system that travels consistently into every tool your team works in — Figma, Claude Code, Cursor, GitHub. Not a collection of individual setups that each need to be maintained. One system.

And now, that system comes with the feedback loop it's always needed.

The solution: style guide analytics and suggestion feedback

We’re making it easy for teams to see how their content system is performing, and train the outputs it generates to keep incrementally improving the quality.

Style guide analytics surfaces usage data directly on your style guide rules. For each style guide in your Ditto workspace, you'll see:

  • How many checks have run against it
  • How many times it triggered a suggestion
  • How many of those suggestions were accepted vs. rejected
  • An overall acceptance rate percentage

This makes it possible to prove the effectiveness of the system you’ve built, while continuously sharpening it as it’s used.

Suggestion feedback lets you capture the why behind a rejection. For each suggestion Ditto generates, your team can now accept it with a thumbs up or reject it with a thumbs down along with adding a note on why. That feedback accumulates against the rule that triggered it — giving Ditto the raw material to refine guidance, update the context around a rule, or retire a rule that's no longer relevant.

Together, these features close the loop between writing down guidelines, and actually putting a content system to work.

Why this matters for agentic workflows

Markdown files and custom skills can get a team to a working first version of copy enforcement. But teams aren’t building copy enforcement for fun — we need to prove that what we’re building is actually improving the quality of the output. And as the pace of generation only increases, it becomes even more important to trust that every word getting pushed to production is on-brand, consistent, helpful, and approved.

See numbers behind your content system, to track whether enforcement is keeping pace — and take action to continuously iterate, improve, and sharpen the system over time.

Join our exclusive beta

Style guide analytics and suggestion feedback are now live in all Ditto workspaces. Want to get access to the new things we’re working on? Join Ditto’s private beta to get first access, dedicated support, and direct input on the roadmap.

Book a beta intro call →