Reshaping SaaS Localization
With Automation and Risk-Based Thinking

Recognize That Governance Comes First

When a content designer joined a European human resources and payroll SaaS, she was surprised about the “localization” workflow. “There’s no localization team. If someone needs a translation, they post translation requests in a Slack channel called ‘translation,’ and product managers do the translating themselves in Phrase. We’ve asked for a dedicated localizer, but nothing has happened.”

Without ownership, quality faltered. In one infamous case, “We used the French word collaborateurs — meaning ‘employees’ — and someone translated it into English as ‘collaborator.’ That triggered panic from the UK team.”

Her fix was not flashy AI — it was governance: a Google Sheets glossary with a Chrome plugin, updated quarterly, so designers and developers could at least access approved terminology.

Best Practice: Don’t let localization run on ad hoc goodwill. Define ownership, document standards, and centralize terminology before scaling up.

Automate Where It Hurts Least

Machine translation (MT) now often serves as the first step — a safety net if content must go live fast. As Teresa Toronjo, localization manager at Malt, explains, “We also apply MT as a first step, so there’s always a fallback if content needs to go live quickly. Translators then have 48 hours to review and edit the MT. Once confirmed, their revisions overwrite the MT content in the system.”

Some teams go further, using AI-driven quality prediction scores to decide which segments need human review. The result: Linguists can focus on high-impact work — in-context reviews, MT engine tuning, and style guide improvements — rather than blanket- reviewing everything.

For another senior localization specialist, MT runs through XTM — DeepL for most European languages, Microsoft Translator for Asian ones — but “several steps still require manual work: pre-processing, post-processing, tagging, quality assurance (QA) after review, and final implementation.” Even developers have to create manual tickets and apply changes themselves.

Best Practice: Let automation handle low-risk, high-volume segments. Save human expertise for content that shapes user trust or has legal implications.

Make AI Part of the Plumbing

At Yango and InDrive, Yana Kolesnikova built pipelines that batch-schedule user interface (UI) translations, integrate Crowdin with GitHub, and run AI-assisted QA to catch issues. “It became clear that we either had to hire more people or automate parts of the process to reduce repetitive effort,” she said.

AI now works across multiple stages:

• Source preparation — rewrites unclear keys before translation.
• Quality control — scripts flagging inconsistencies.
• Tone optimization — adapts voice for various markets.

Best Practice: Integrate AI into your infrastructure, rather than using it as a surface add-on. Automate source preparation, QA, and tone optimization so AI becomes an invisible, reliable part of your localization pipeline.

Approach Localization as a Design Feature

For some teams, localization is no longer the final step; it’s embedded in product design from day one. At Yango, for instance, the localization team works closely with developers, designers, and product managers to ensure that every feature is designed with multilingual markets in mind. Glossaries are integrated directly into the computer-assisted translation (CAT) tool, enabling automatic terminology checks. Annotated Figma screenshots provide translators with visual context, while tone and style are tested through A/B experiments before a release.

Yango’s product localization branch runs on a continuous localization model: Developers commit new strings to repositories, which are automatically batched twice a week and sent to Crowdin for translation. This batch-based workflow ensures predictable delivery dates and eliminates the chaos of ad hoc microtasks. Developers know exactly when to submit strings if they want them included in the next release, and linguists receive all the context they need to work efficiently.

Automation supports more than just scheduling. Custom QA scripts detect issues like mismatched variables, incorrect characters, or even the accidental use of Cyrillic letters in English text. Integration with Figma allows visual assets to be pushed directly into the localization platform, linking each string to the precise UI element where it appears. For markets requiring special adaptation — such as right-to-left languages — the team maintains design and QA guidelines covering layout mirroring, currency formatting, and date conventions.

Tone of voice is treated as a design parameter, not an afterthought. Based on user testing, the Spanish version of the app adopts a more conversational style, improving user engagement and eliminating previous complaints about stiffness. Linguists follow detailed tone and style guides, and brand-specific naming glossaries ensure consistent messaging across markets and product lines.

As Kolesnikova puts it: “I’d push for a culture that sees localization as part of the product design, not a final step.”

Best Practice: Treat localization as a product feature. Involve linguists from the design stage, provide full visual context, and embed glossaries into tools to ensure consistency, relevance, and efficiency from the first line of code.

Review by Risk, Not by Habit

Treating every string equally is a fast track to burnout. Leading teams prioritize review based on business impact, visibility, and legal stakes.

Booking.com’s PREDICT model is one example, matching QA depth to defined risk. Toronjo applies a similar system at Malt. “Regarding quality, I care deeply — but only as far as it impacts the user experience. ‘Best quality’ depends on the content type; a help article doesn’t need the same quality as a legal document or a product feature. We have a tiered system. Tier 1 features are either AI-related, like our AI-powered search, or revenue-related, such as quote approval workflows. These get prioritized in our quality checks.”

Best Practice: Map your content to risk tiers. This ensures your best reviewers focus where quality really moves the needle.