Human review
Choose reviewers, route translations to decision pools, and configure the quality gate and timeout in the engine's Pipeline tab.
Most of your content can ship the moment the engine returns it. Some can't. A regulated disclosure, a medical instruction, a headline that carries the brand – for those, you want a person to read the translation and sign off before it goes live, not after a customer files a complaint.
The usual way to get a human into an automated flow is the painful way: hold the request open while someone reads, or build your own review queue, or hand-wire a translation vendor's API. This stage does it inside the job. When Human review is enabled, the async job runs the engine, then pauses on a person – your own team or an external professional – and resumes with their edit, carrying that output forward to any stages that follow.
It runs after Rephrase and before Post-edit in the localization pipeline. Enable and configure the stage in the engine's Pipeline tab. New to the pipeline? Start with the overview.
On this page
How the pause works #
After the core translate step – and after Rephrase, when that stage is on – the job hands the AI translation to a human for review. The reviewer reads it, then either approves it as-is or submits an edited version. The job continues with that decision, carrying the translation forward to later stages. If no decision arrives before the timeout, the job continues with the preceding translation.
Who does the reading is set per language and directory: the engine's Human review settings send each one to a decision pool – your own team or an external provider. The pause, resume, and carry-forward behavior is identical either way, and translations no pool covers ship without review.
Internal Review #
Your own team reviews translations directly in the Lingo.dev dashboard. Pending reviews appear in the Queue (/orgs/<org-id>/queue) as Human review items, and reviewers are notified when new items arrive. A reviewer opens an item, edits whichever keys need it, then clicks Approve as-is or, once something is edited, Approve with edits – the button counts them, as in Approve with 2 edits. The job resumes with their output.
There is no claim or lock. Which decision pool a review goes to decides who is emailed about it; anyone with Review translations can see and decide any open review.
Internal Review comes with the Enterprise plan. Reach for it when your team has the language expertise in-house and you want full control over the final wording, with no third party in the loop.
Permissions #
Internal review is not open to everyone in the organization – the review queue is permission-gated, so a translation in review is visible only to the people you grant access. An organization admin assigns access through roles (Settings → Roles):
| Permission | What it unlocks |
|---|---|
Review translations (engine:review_translations) | See Human review items in the Queue, edit them, and approve them as-is or with edits |
Manage reviews (org:manage_reviews) | Review history and statistics for internal reviews. Without it, decided reviews stay hidden in the Queue |
The two permissions are deliberately separate. A reviewer needs only Review translations – that single grant is the whole job: edit, approve as-is, approve with edits. Manage reviews is for whoever oversees the operation; it adds the review history across the org but does not include queue access on its own. Grant both to a lead who reviews and reports; grant only the first to someone who only works the queue.
External Review #
When you don't have in-house reviewers for a locale, route it to an external decision pool – on Lingo.dev's account or your own provider account, such as BLEND – and the translation is submitted to a qualified professional translator instead. The job pauses the same way; it resumes when the provider returns the edited translation.
There is no tier to pick – the marketplace grades the translator itself. External Review is billed per word: through your Lingo.dev plan on Lingo.dev's account, or by the provider on your own account.
An external review shows up in the Queue as well; opened, it names a Qualified translator as its reviewer. Someone with Review translations can open it and take it over: pick Approve as-is or Approve with edits, and the job finishes there instead of waiting for the translator. The Take over this review confirmation says what it costs before you commit – taking over is free only while no translator has started; once one has, the translator fee stands whether or not you use their work.
This is the candor worth being explicit about: External Review is a real human translator on the other end, with the turnaround and cost that implies. It is not a faster model. Use it where a person's judgment is the point – regulated text, high-stakes copy – and lean on the AI-only path for the bulk of your content that doesn't need it.
Quality gate #
Open the Human review settings and choose a Review level. You can save the level while human review is off. The engine keeps it when you turn human review off and back on.
When human review runs, Strict, Medium, and Lax use the quality gate to check new translations covered by a route. Everything skips the gate. The level determines which findings require review:
| Level | What it means | What goes to review |
|---|---|---|
| Everything | Every new translation goes to a reviewer. | Every new translation covered by your decision pools; the gate is off. |
| Strict | Review anything a careful editor would change. | Any finding: minor, major, or critical. |
| Medium | Review translations that get the meaning or your guidelines wrong. | Major or critical findings. |
| Lax | Review only broken or misleading translations. | Critical findings only. |
These choices apply within your decision-pool coverage. A translation the gate could not check goes to review too. A translation with no finding at the selected severities continues without human review.
Each finding quotes a span from the translation and gives a one-sentence explanation in English, a category (accuracy, terminology, guidance, fluency, or style), and a severity:
- Critical: the reader would be misled or could not use the text. It is in the wrong language, untranslated, garbled, or cut off; it says something different from the source or the opposite; or it gets a fact wrong, such as a number, date, amount, or name.
- Major: the main point survives, but part of the meaning is lost, added, or distorted, or the translation breaks a required glossary term or instruction. A reviewer must fix it before it ships.
- Minor: the meaning is intact, but a reviewer would still change it: a spelling, grammar, or punctuation mistake, an awkward or literal phrasing, or a slip in tone or register.
Reviewers see the findings next to the translation in the Queue. The gate checks for the same errors at Strict, Medium, and Lax. Changing the level applies to new jobs, not jobs already running.
If the gate lets a translation skip human review, there is no human output for Post-edit.
Timeout #
A human stage introduces a risk the AI stages don't have: the human might never respond. A reviewer is on vacation, the provider is backed up, the item is forgotten. Left unbounded, the job would wait forever.
So the wait is bounded. You set how long the workflow waits for the human output – Timeout, in hours, in the Human review settings. It applies to both review modes. If the timeout expires with no response, the job continues with the preceding translation. The default is 48 hours.
On timeout, the workflow can continue without a human decision. For content that requires human approval before publication, verify that a reviewer supplied a decision. A longer timeout gives reviewers more time; it does not require approval before the job completes.
Timeout is per stage, not per job
The timeout governs only how long this stage waits for a human. It is independent of how long the rest of the job takes.
Enabling the stage #
- Open the engine's Pipeline tab and enable Human review.
- Open the step's settings. Under Decision pools, choose who reviews each language and directory. See Route an engine's review to pools for coverage and conflict rules.
- Set Timeout and choose a Review level.
- Select Save settings.
If a card points to an unavailable pool, select an active pool. Use run evidence to inspect review progress and the translation the run returned.
A human edit can drift from your engine rules
A human translator may phrase something in a way that conflicts with your glossary, brand voice, or rules – they're translating well, not memorizing your config. To reconcile the human's edit back to your engine rules automatically, enable the next stage, AI review – Post-edit in the Pipeline tab. It runs only after a human stage that actually produced output.