From the Citizen Engagement & Services edition of November 4, 2026
Novosibirsk puts a university-built AI assistant on its city services portal that answers only from 38 official regulations
Novosibirsk City Hall and Novosibirsk State University (reported by IT Russia) · Municipal digital front door · Novosibirsk, Russia
- Publisher
- IT Russia
- Original publication
- 2026-11-04
- Source retrieved
- 2026-11-05
- Event date
- 2026-11-04
What happened
IT Russia reported on Nov. 4 that an AI assistant built by Novosibirsk State University on its SIGMA platform went live on the city's Novosibirsk Online portal, rebranded in late October. It helps residents find municipal services, including links to the federal Gosuslugi portal, and answers only from 38 official regulations, without internet access or outside information. The city says it is meant to reduce district administration workload. A related staff tool, SIGMA Regulations, is said by its developers to cut documentation search time by at least half. No usage or accuracy figures are reported.
Why it matters
A city-university build of a closed-corpus service assistant, a design choice U.S. cities weigh against vendor bots that index the whole website. Transferability is limited: different legal, procurement and data regimes.
Evidence and measured results
Trade news report quoting a city official; no measured outcomes; the staff-tool time saving is a developer claim.
Limitations and uncertainty
Non-US deployment; single secondary report; no accuracy, usage or cost data; the 'at least half' figure is a developer claim about a staff tool.
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-11-05; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.
Sales
Role takeaway
- Customer problem
- Residents struggle to find which municipal service applies and how to obtain it.
- Stakeholders
- City communications and IT department
- District administrations
- University partner
- Legal or regulations office
- Discovery questions
- Which documents must the assistant rely on?
- Who updates the corpus when rules change?
- How do residents reach staff for out-of-scope questions?
- Value hypothesis
- A closed-corpus assistant may give more reliable answers on a narrow set of services; untested here.
- Potential engagement
- A corpus-scoping and answer-test workshop for a small set of services.
- Unsupported claims
- Workload reduction
- Accuracy rate
- Transferability to U.S. procurement
Pre-sales engineering
Role takeaway
- Fit
- Fits cities that want a narrow assistant over a defined rule set.
- Architecture and integration
- Retrieval over 38 regulations, no internet access, links to service portals.
- Prerequisites
- Curated document set
- Citation display
- Out-of-scope handling
- Constraints
- Non-US legal context
- No published metrics
- Corpus may go stale
- Security
- No retention or logging terms reported; confirm before any comparable deployment.
- Proof of value
- Out-of-scope refusal test
- Citation accuracy on test set
- Update latency after rule change
Delivery
Role takeaway
- Work
- Maintain the regulation corpus and monitor answers.
- Dependencies
- University platform support
- Regulation owners
- Portal team
- Ownership
- City communications and informatization department.
- Skills and adoption
- Staff need to review unanswered questions and flag rule changes.
- Governance checkpoints
- Corpus change review
- Quarterly answer audit
- Scope expansion decision
- Acceptance criteria
- Proposed: every answer cites a corpus document
- Proposed: corpus updated within a week of a rule change
- Risks
- Stale regulations
- Partner support ends after pilot
- Residents misled on out-of-scope questions
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?
Answers are restricted to a fixed corpus of 38 regulations with no web access, with links out to service portals; no transactions.
Governance
Who approves, reviews and stays accountable for outcomes?
A closed corpus limits hallucination scope but needs a process to update the regulation set when rules change.
Security and privacy
What data, permissions and controls need testing?
No data retention or logging terms reported.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
Aimed at reducing district administration workload; no language or accessibility details.
Procurement
What should contracts, pricing and exit terms secure?
Built through a university cooperation agreement signed April 2026 rather than a commercial vendor.
Operating model
Which teams own the service once it runs?
The communications and informatization department owns the portal; the university supplies the platform.
Publication history
Read preserved resource versions (JSON)Stable resource ID: novosibirsk-online-portal-ai-assistant-38-regulations-20261104