From the Local Government edition of October 17, 2026
Goslar, Germany launches chat and phone AI assistant "Charley" on 15 October, telling residents not every answer will be correct and routing gaps to the switchboard
Stadt Goslar (Lower Saxony) · Municipal resident information and contact centre · Goslar, Lower Saxony, Germany
- Publisher
- Stadt Goslar Pressestelle
- Original publication
- 12.10.2026 (launch Thursday 15 October 2026)
- Source retrieved
- 2026-10-18
- Event date
- 2026-10-15
What happened
Goslar announced that chatbot Charley would go live on Thursday 15 October on the city website and by phone. Charley can only use data and information supplied by the administration, so its knowledge is limited and not equal to a staff member's; the city states that not every answer will be correct and that the bot can produce hallucinations. Residents can report errors, missing information or unclear answers in the chat or by email. When the bot cannot answer, phone calls are put through to the city switchboard and written queries are forwarded to the administration's email; out-of-hours phone queries are also forwarded by email. The city's digitalisation officer framed the goal as using AI while being open about its limits. Why now: the service went live on 15 October, in the same week as several other German municipal assistants.
Why it matters
Unusually candid public disclosure of hallucination risk plus defined escalation to humans by channel is a model for U.S. city communications on resident-facing assistants.
Evidence and measured results
City press release opened in full via curl and read in German; publication date taken from page metadata (2026-10-12). No usage or accuracy data published; vendor not named.
Limitations and uncertainty
Pre-launch press release; no performance or cost data; post-launch results unknown; vendor and model not disclosed.
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-10-17; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.
Sales
Role takeaway
- Customer problem
- City wants AI-assisted access to information without overpromising accuracy.
- Stakeholders
- Digitalisation officer
- City switchboard team
- Press office
- Residents and visitors
- Discovery questions
- How are error reports triaged and closed?
- What share of chats and calls escalate?
- Will results be published after launch?
- Value hypothesis
- Transparent, closed-domain assistant may answer routine queries around the clock; unmeasured.
- Potential engagement
- First-quarter evaluation using feedback and escalation logs.
- Unsupported claims
- Answer accuracy rate
- Reduced call volume
- Savings
Pre-sales engineering
Role takeaway
- Fit
- City websites with curated content and a central switchboard.
- Architecture and integration
- Closed knowledge base; chat and voice; transfer to switchboard; email forwarding.
- Prerequisites
- Curated city content
- Telephony integration
- Feedback capture
- Constraints
- Knowledge limited to supplied content
- Acknowledged hallucinations
- Vendor undisclosed
- Security
- Restricted to administration-supplied data; voice data handling not stated.
- Proof of value
- Log and categorise unanswered questions
- Measure transfer success to switchboard
- Sample answers for grounding in supplied content
Delivery
Role takeaway
- Work
- Triage feedback, close content gaps, monitor escalations and report results.
- Dependencies
- Content owners
- Switchboard
- Vendor
- Ownership
- Digitalisation officer and MachMit!Haus, Stadt Goslar.
- Skills and adoption
- Switchboard staff handle transferred queries; training not described.
- Governance checkpoints
- Feedback review cadence
- Quarterly results report
- Content ownership assignments
- Acceptance criteria
- Proposed: error reports acknowledged within a set time
- Proposed: transfer success rate tracked monthly
- Risks
- Reliance on wrong answers
- Escalation overload
- Opaque vendor terms
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?
Closed knowledge base limited to administration-supplied content, with chat and voice channels and fallback routing to switchboard and email.
Governance
Who approves, reviews and stays accountable for outcomes?
Run by the digitalisation officer and the MachMit!Haus; user feedback is the stated improvement loop, with no formal evaluation described.
Security and privacy
What data, permissions and controls need testing?
Restricting the bot to supplied content limits exposure; data handling for voice calls is not described.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
Voice access and human fallback support residents who do not use web chat; the city says Charley complements but does not replace personal advice.
Procurement
What should contracts, pricing and exit terms secure?
Vendor and contract not described.
Operating model
Which teams own the service once it runs?
Escalation by channel (switchboard for calls, email for written and out-of-hours queries) sends unresolved demand back to existing teams.
Publication history
- 2026-10-17Local Government · Issue 426 resources
Stable resource ID: goslar-de-charley-chatbot-voicebot-hallucination-disclosure-20261015