CONTENT CREATION
Back-Translate Changed UI Strings in a PR and Block on Meaning Drift
On every pull request that touches localization files, back-translates each changed translated string to the source language and posts a PR check that fails when the round-trip…
How it runs
The automated pipeline, trigger to output.
- TriggerPull request opened or updated touching locale filesGitHub
- ActionFetch PR diff and extract changed target stringsGitHub
- ActionBack-translate each target string to source languageOpenAI
- LogicScore equivalence; flag drift and placeholder mismatches
- OutputPost PR check status and inline review commentGitHub
What it does
Watches pull requests for changes to your translation catalogs (JSON, PO, or XLIFF), back-translates each modified target string into the source language with an LLM, compares it to the original source string, and reports drift directly on the PR as a status check.
When to use it
When translators or AI translation tools touch strings frequently and you want a gate that catches meaning changes (negations dropped, tone flipped, placeholders mangled) before the locale ships. Ideal for teams shipping multilingual UI on a fast release cadence.
How it works
- 1A pull request opens or updates, triggering on changes under your `locales/` path.
- 2The flow pulls the diff from GitHub and extracts each added or modified target string with its source key.
- 3For each string, the LLM back-translates the target back into the source language.
- 4A comparison step scores semantic equivalence and flags entries below the threshold or with placeholder mismatches.
- 5The result is posted as a GitHub commit status (check) plus an inline review comment listing the drifted strings, blocking merge until resolved.
Set it up
What you configure once, before turning it on.
- 1Connect GitHubRepos, issues, pull requests, actions.
- 2Connect OpenAIModels, embeddings, files.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Content Creation workflows
Build a Dropbox B-roll library from exported blog drafts
Triggers when a new blog draft file lands in a Dropbox folder, generates a Replicate B-roll clip for each paragraph.
Generate B-roll clips when a blog post is marked Ready in Notion
Watches a Notion blog database for posts flipped to 'Ready', splits the body into paragraphs, and generates a short B-roll video clip for each paragraph with Replicate.
On-demand: turn a blog URL into narrated B-roll clips
Accepts a blog URL via webhook, scrapes the article, generates a B-roll clip per paragraph with Replicate and a voiceover with ElevenLabs.
On-Demand Screenshot Freshness Report from a Slack Command
A writer requests a freshness check in Slack for a specific docs page; the workflow inspects every screenshot on that page, scores each by age and version gap.
Sync a Figma master frame into localized hero renders
Pulls the current master hero frame and its text layers from Figma, generates a localized image variant for each locale defined in Airtable.
Research-driven localized hero banners tuned per market
An agent researches cultural and seasonal cues for each target market, adapts the master hero concept to fit local context, generates a tailored image per locale.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.