From the Local Government edition of October 7, 2026
West Northamptonshire Council's in-house virtual assistant handles more than 2,000 resident conversations a month
West Northamptonshire Council (Digital Services) · Resident-facing website virtual assistant · West Northamptonshire, England, United Kingdom
- Publisher
- West Northamptonshire Council news
- Original publication
- 7 October 2026
- Source retrieved
- 2026-10-08
What happened
The council's Digital Services team built a 24/7 website assistant that answers questions in users' own words from council-approved information, in multiple languages. Since initial rollout it has handled more than 2,000 conversations a month, mostly about bins and collections, council tax, recycling and housing. The council reports positive feedback on speed and out-of-hours access. When it cannot answer, it points users to the right service or contact route, and residents can still reach staff.
Why it matters
Gives a usage figure for an in-house built resident assistant; U.S. counties and cities weighing build versus buy can compare volume and topic mix.
Evidence and measured results
Council self-reported usage; no accuracy or resolution data.
Limitations and uncertainty
Classified vendor-claim because it is the operator's own promotional report without an evaluation method; 'positive feedback' is unquantified; rollout start not stated; UK context.
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-10-07; 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 information across many webpages and outside office hours.
- Stakeholders
- Cabinet Member for Corporate Services
- Digital Services lead
- Customer services manager
- Information governance officer
- Discovery questions
- How many of the 2,000 monthly conversations resolve the question?
- How is accuracy checked?
- What share are referred to staff?
- Which model or platform underpins the build?
- Value hypothesis
- Out-of-hours self-service for high-volume topics may ease contact demand; not measured.
- Potential engagement
- A sample-based accuracy and resolution evaluation of one month of conversations.
- Unsupported claims
- Call or email deflection
- Cost savings
- Accuracy level
Pre-sales engineering
Role takeaway
- Fit
- Fits authorities with a large, current content estate and in-house digital capacity.
- Architecture and integration
- Website chat widget with retrieval over council-approved content, multilingual responses and referral to service contact routes.
- Prerequisites
- Current, structured web content
- Conversation logging
- Referral routing
- Multilingual capability
- Constraints
- UK GDPR
- Content currency
- In-house maintenance capacity
- Security
- Keep the assistant information-only and avoid collecting personal data in chat; not described in the source.
- Proof of value
- Score 100 sampled answers against current pages
- Measure referral rate by topic
- Test handling of personal data typed into chat
Delivery
Role takeaway
- Work
- Run quality operations for the assistant: content upkeep, accuracy sampling and reporting.
- Dependencies
- Digital Services capacity
- Service content owners
- Logging and analytics
- Ownership
- Digital Services team.
- Skills and adoption
- Content owners trained to update pages based on unanswered-question reports.
- Governance checkpoints
- Monthly quality review
- Information governance review of chat logs
- Acceptance criteria
- Monthly accuracy score from a fixed sample published internally
- Unanswered-question backlog reviewed within a set period
- Referral rate tracked by topic
- Risks
- Stale content producing wrong answers
- Volume reported without quality
- Personal data captured in logs
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?
Retrieval over council-approved content with multilingual output; build was in-house rather than vendor-supplied, model not named.
Governance
Who approves, reviews and stays accountable for outcomes?
Restricting answers to approved content and routing unanswerable questions are standard controls, but the release gives no testing or monitoring detail.
Security and privacy
What data, permissions and controls need testing?
Not described; council tax and housing queries may involve personal details that an information-only assistant should not collect.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
Multilingual and out-of-hours access; staff remain available for further support.
Procurement
What should contracts, pricing and exit terms secure?
An in-house build avoids vendor licensing but shifts maintenance and content currency to the digital team.
Operating model
Which teams own the service once it runs?
Digital Services owns the assistant; answer quality depends on keeping web content current.
Publication history
- 2026-10-07Local Government · Issue 326 resources
Stable resource ID: west-northamptonshire-virtual-assistant-2000-conversations-20261007