From the Emergency Services edition of October 25, 2026
Taiwan's NARLabs says its POSEIDON AI, linked to Taipei's 119 dispatch system, has handled over 3,000 fires and brings pressurized water supply forward by over 6 minutes
National Applied Research Laboratories, National Center for Research on Earthquake Engineering (NCREE); Taipei Water Department; Taipei City Fire Department · Fire service dispatch and water utility coordination · Taipei, Taiwan
- Publisher
- Central News Agency (CNA)
- Original publication
- 2026-10-20
- Source retrieved
- 2026-10-26
- Event date
- 2026-10-20
What happened
At an October 20 NARLabs press conference reported by CNA, NCREE said its POSEIDON AI assistant connects to Taipei's 119 high-performance dispatch system, takes fire reports as they arrive, maps the fire location to a water-supply zone and booster station, drafts a firefighting water-supply plan and notifies the Taipei Water Department within one minute. NCREE says that since going live in February 2026 it has helped handle more than 3,000 fires and on average brings emergency pressurized water supply forward by more than 6 minutes. The researcher stressed that AI is an assistive tool and final judgment stays with people. NARLabs also announced a building damage-grading model trained on 8,000 photos that grades a photo in one second, to be used by Hualien County, and a free anonymous public version. POSEIDON and damage grading carry only customization fees.
Why it matters
U.S. fire departments and water utilities coordinate hydrant pressure by phone during large fires; POSEIDON is an operating example of dispatch data automatically triggering utility action, relevant to CAD integration and utility mutual-aid planning, though from a single Taiwanese city.
Evidence and measured results
National news agency report of an agency press conference; the 3,000-fire and 6-minute figures are NCREE's own; no baseline method, comparison group, fire outcomes or published evaluation are given.
Limitations and uncertainty
Agency-reported figures without method or independent validation; how the 6-minute gain was measured is not stated; 3,000 'cases' are fire reports received, not necessarily large fires needing pressure boosts; Taipei-specific water network.
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-10-25; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.
Sales
Role takeaway
- Customer problem
- During larger fires, low hydrant pressure is often found on scene and the water utility is called late to boost supply.
- Stakeholders
- Fire chief or operations chief
- Emergency communications director
- Water utility operations manager
- City CIO or CISO
- Discovery questions
- How does your fire department request pressure support from the water utility today, and how long does it take?
- Is CAD incident location already shared with the utility?
- Who owns booster station decisions during an incident?
- Value hypothesis
- Automatic dispatch-triggered utility notices might shorten time to adequate water pressure on working fires (interpretation, based on Taipei's agency-reported figures).
- Potential engagement
- A bounded assessment of dispatch-to-utility data flows and a pilot design for one pressure zone.
- Unsupported claims
- A 6-minute gain in U.S. systems
- Reduced fire losses or injuries
- Independent validation of Taipei's figures
Pre-sales engineering
Role takeaway
- Fit
- Fits cities where the fire department and water utility share a service area and the utility can adjust booster stations remotely.
- Architecture and integration
- CAD event feed triggers a zone-mapping service that drafts a supply plan and notifies utility operations; humans approve actions.
- Prerequisites
- Geocoded CAD fire events
- Hydraulic zone and booster station model
- Secure messaging link to utility operations
- Constraints
- Separate utility ownership and governance
- Critical-infrastructure security requirements
- Taipei-specific evidence
- Security
- Segregate the CAD-to-utility link, log every automated notice and keep control actions manual.
- Proof of value
- Time from fire report to pressure support before and after
- Share of notices that led to action
- Pressure effects on neighbouring zones
Delivery
Role takeaway
- Work
- Map water zones, connect CAD events to utility operations and run a time-stamped pilot in one district.
- Dependencies
- Utility hydraulic model
- CAD vendor integration
- Interagency agreement
- Ownership
- Fire communications lead jointly with the water utility operations manager.
- Skills and adoption
- Utility operators learn to act on automated fire notices; dispatchers learn when to escalate manually.
- Governance checkpoints
- Interagency notification protocol sign-off
- Cybersecurity review of the link
- Post-pilot performance review
- Acceptance criteria
- Proposed: measurable reduction in time to pressure support
- Proposed: no unplanned pressure drops in adjacent zones
- Risks
- False or duplicate triggers
- Cyber exposure of utility systems
- Over-reliance on automated plans
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?
Event-driven integration: CAD/dispatch feed triggers a model that maps incident location to water network zones and pushes a plan to the utility.
Governance
Who approves, reviews and stays accountable for outcomes?
Cross-agency automation between a fire department and a water utility requires agreed notification protocols and a rule that people make final operating decisions, which NCREE says applies.
Security and privacy
What data, permissions and controls need testing?
Uses incident location and water-network data rather than caller content; a live link between dispatch and utility control raises critical-infrastructure security questions not discussed.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
Removes manual phone coordination between dispatchers and utility staff for routine water-supply requests; utility operators still act on the plan.
Procurement
What should contracts, pricing and exit terms secure?
NARLabs charges only customization fees, so agencies abroad would need a comparable public research partner or vendor to build zone mappings for their own network.
Operating model
Which teams own the service once it runs?
Shifts water-pressure support from a request made after crews find low pressure to an automatic notice at the time of the fire report.
Publication history
- 2026-10-25Emergency Services · Issue 494 resources
Stable resource ID: cna-narlabs-ncree-poseidon-taipei-119-fire-water-supply-ai-3000-fires-6-minutes-20261020