From the Citizen Engagement & Services edition of November 6, 2026
Ukraine Ministry integrates on-prem Gemma 3 27B into ePermit licensing review for veterinary licenses, recommending issue, reject, or manual review while officials retain decisions
Ministry of Economy, Ecology and Agriculture of Ukraine (Google DeepMind case study) · National digital permitting and licensing portal · Ukraine
- Publisher
- Google DeepMind Gemmaverse
- Original publication
- 2026-11-06
- Source retrieved
- 2026-11-07
What happened
A Google DeepMind Gemmaverse case study describes Ukraine's ePermit service on the Diia portal integrating Gemma 3 27B for license application review after Qwen 2.5 7B VL extracts text from scanned documents and registry data are combined. Legal constraints require closed infrastructure with no external API calls or cloud dependencies; the model runs on-premise via vLLM on NVIDIA H100 GPUs in a Ukrainian datacenter. Gemma recommends one of three outcomes to the assigned official—issue the license, reject, or further manual review—for veterinary licenses initially, with expansion to other types planned. Officials quoted say Gemma balanced reasoning and on-prem deployment; the write-up claims dramatically cut processing time, no latency issues, and fewer rejections/resubmissions/workload, without publishing numeric baselines. Decisions are described as auditable via logged inputs, outputs, and rules.
Why it matters
Licensing/permitting AI with an explicit on-prem, no-external-API constraint and human final decision—transferable operating constraint for SLED agencies that cannot send applicant documents to public clouds.
Evidence and measured results
Vendor case study with named ministry CDTO/AI advisor quotes; impact claims lack numeric baselines or independent evaluation; retrieval date used as publishedAt because the page is undated.
Limitations and uncertainty
DeepMind marketing page; 'dramatically' faster processing without numbers; veterinary-only production scope; English typos in ministry name on the page.
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-11-06; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.
Sales
Role takeaway
- Customer problem
- License applicants wait days for incompleteness findings while officials grind document checks by hand.
- Stakeholders
- Ministry CDTO / AI advisors
- Licensing officials
- Applicants
- Datacenter/security teams
- Discovery questions
- Which license types allow AI recommendations?
- What is the closed-infrastructure boundary?
- How are overrides audited?
- Value hypothesis
- On-prem AI may speed triage if recommendations match officials; unquantified on this page.
- Potential engagement
- A shadow-mode agreement study on veterinary applications before expanding types.
- Unsupported claims
- Numeric processing-time reduction
- Cross-license generalization
- That open weights remove all vendor dependence
Pre-sales engineering
Role takeaway
- Fit
- Fits governments that must keep license packets on-prem without public-cloud LLM APIs.
- Architecture and integration
- Qwen-VL extraction + Gemma 3 27B on-prem vLLM/H100 recommending issue/reject/manual review to officials.
- Prerequisites
- On-prem GPU capacity
- Registry data access
- Audit logging of recommendations
- Constraints
- Vendor case study evidence
- Veterinary-only scope
- No published baselines
- Security
- Enforce no-external-API controls and protect applicant PII in logs and training sets.
- Proof of value
- Shadow-mode agreement with officials
- Time-to-first-feedback vs baseline
- Override rate by reason
Delivery
Role takeaway
- Work
- Stand up evaluation sets per license type and train officials on recommendation review.
- Dependencies
- Model ops / GPU platform
- Registry stewards
- License program owners
- Ownership
- Ministry digital leadership with program officials as decision owners.
- Skills and adoption
- Officials need practice reviewing AI rationales and recording disagreements.
- Governance checkpoints
- Shadow-mode exit criteria
- Type-expansion gate
- Periodic audit-log review
- Acceptance criteria
- Proposed: no auto-issue until evaluation gates pass
- Proposed: every override reason logged
- Risks
- Silent automation of denials
- Drift on Ukrainian legal language
- GPU capacity shortfalls
Implementation considerations
Lighthouse Advisory interpretation across the operating dimensions a public-sector buyer must settle before this evidence becomes a design. Each note answers the question under its heading for this specific source.
Architecture and integration
What must connect, and where does the AI sit in the workflow?
Vision LLM for scan OCR plus Gemma 3 27B decisioning on-prem with registry joins; three-way recommendation to a human official; multimodal fine-tuning planned.
Governance
Who approves, reviews and stays accountable for outcomes?
Human official retains decision; auditable logs of inputs/outputs/rules; evaluation framework planned as types expand.
Security and privacy
What data, permissions and controls need testing?
Closed infrastructure mandate—no external APIs or cloud—addresses sovereignty; applicant document handling still depends on ministry controls not fully specified here.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
Aimed at faster feedback to applicants and lower official workload; public accessibility of ePermit UX not discussed.
Procurement
What should contracts, pricing and exit terms secure?
Open-model on-prem path rather than SaaS API; GPU datacenter capacity required; no commercial contract terms disclosed.
Operating model
Which teams own the service once it runs?
Officials still decide; AI triages completeness/consistency/eligibility; ministry developers fine-tune for Ukrainian language and document terms.
Publication history
Read preserved resource versions (JSON)Stable resource ID: ukraine-epermit-gemma-onprem-veterinary-license-review-20261106