Policies and versions
What the platform is allowed to do in Phase 1, which versions are live, and how every change is tested before it reaches production.
Step 23 of 24 · Presenter note
What the AI is allowed to do in Phase 1: new, fuzzy and AI-corrected content is always reviewed, hard-fail rules block release, and every change runs the regression suite.
Review policy for Phase 1
Locked in Phase 1| Unit type | What happens | Human review |
|---|---|---|
| Approved exact match | Reused without AI, after terminology, protected-content and integrity checks. Shown as context. | Context only |
| Exact match in a hazard statement (High criticality) | Reused, but shown for confirmation | Confirm |
| Exact match with a conflict or context warning | Routed to review | Required |
| Fuzzy match | Used as evidence for the AI; never approved as output | Required |
| New AI translation | Translated with terminology and context | Required |
| AI-corrected unit | Corrected by the loop, history visible | Required |
| Hard fail or unresolved finding | Mandatory human correction | Required |
Reducing human review needs a calibrated quality score and sign-off by Quality and Legal. That is Phase 3.
AI correction loop
Proposal for Phase 1: 2
Hard-fail rules
§17.4- HF-01Changed safety-critical number or unit
- HF-02Omitted warning, prohibition or condition
- HF-03Altered protected identifier
- HF-04Invalid tag or placeholder that breaks the target system
- HF-05Missing translation unit
- HF-06Duplicated content that changes instructions
- HF-07Obsolete source version
- HF-08Unsupported publication output
- HF-09Source ambiguity that prevents reliable translation
- HF-10Critical terminology violation
- HF-11Failed reconstruction integrity
Live versions
| Component | Version | Since | Approved by | Regression |
|---|---|---|---|---|
| Translation model | private-llm 2027-06 (EU tenant) | 2 Aug 2027 | Priya Raman | Passed · 1,240 units |
| Prompt template | tr-dita-install v1.4 | 16 Aug 2027 | Priya Raman | Passed · 1,240 units |
| Evaluator | gtl-qe 0.9 | 16 Aug 2027 | Priya Raman | Passed · 400 seeded defects |
| Hard-fail rules | v3 (11 rules) | 1 Jul 2027 | Quality | Passed |
| Segmentation rules | acolad-compat-srx 1.0.2 | 14 Jun 2027 | Localization engineer | Passed · leverage −0.6 pp |
| Parser | dita-xliff 1.3.0 | 14 Jun 2027 | SIS | Passed · 212 topics round trip |
| Terminology | TermWeb 2027.09 + local L-214 | 1 Sep 2027 | Luca Bernasconi | 4 conflicts open |
Proposed change
Prompt tr-dita-install v1.5
Adds style rules for hazard statements. Submitted by Priya Raman, Tue 14 Sep.
- Regression suite
- 1,240 benchmark units in 9 languages
- Passed
- 1,236
- Regressions
- de-DE 2, th-TH 1, ar 1: prohibited term reintroduced in 3 units, one tag moved
AI service
- Private model, EU tenantHealthy · 138 ms median per unitLive
- Fallback modelNone, by policy. No unapproved model is ever used silently.None
- On an outageWork queues and resumes; GTL is alerted after 15 minutes.