From the Citizen Engagement & Services edition of November 9, 2026
Indiana Secretary of State relaunches INBiz business portal on AWS with 'Liz' bilingual AI assistant and AI document intake, organized around plan-start-manage-grow after 6,717-response CX study
Indiana Office of the Secretary of State · State business registration and licensing portal · Indiana, United States
- Publisher
- StateScoop
- Original publication
- 2026-11-09
- Source retrieved
- 2026-11-10
What happened
StateScoop (Nov. 9, 2026) reports that Indiana's Secretary of State relaunched the INBiz business services portal after migrating legacy Microsoft workloads to AWS; MTX Group led application modernization into modular services with new UI, payments and cross-agency integrations. The portal adds 'Liz', a bilingual English/Spanish AI assistant built with Google and Google Public Sector that answers from approved state sources, and mavQ intelligent document processing that classifies submitted documents and routes some for employee review. Design followed a nearly nine-month CX study (6,717 survey responses, 76 interviews and co-creation sessions, 50-state benchmarking) and organizes services into plan, start, manage and grow. The platform has 1.4 million+ users (about 800,000 businesses) and processed 614,774 filings and 92,500 new registrations in FY2025. Remaining integrations will be phased after the CIO's departure. GovTech's same-day account says SOS divisions receive roughly 15,000-20,000 calls a month and that agentic AI supports document review for licensing applications.
Why it matters
A statewide business licensing and registration front door adding a grounded bilingual assistant and AI intake is squarely in the CE permitting/licensing and digital front door scope, with published baseline volumes against which outcomes can later be judged.
Evidence and measured results
Trade press interview with the departing CIO (self-reported); corroborated by a GovTech article the same day. No outcome metrics for Liz or document AI are reported.
Limitations and uncertainty
Launch timing is inconsistent between sources: StateScoop says the portal launched 'last week' while GovTech says it officially launched in October. Claims of accuracy and ROI are the CIO's own; no measured call deflection, assistant accuracy or processing-time results.
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-11-09; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.
Sales
Role takeaway
- Customer problem
- Business owners navigating fragmented, jargon-heavy services across agencies, with high call volumes to the Secretary of State.
- Stakeholders
- Secretary of State and CIO
- Business Services and Securities divisions
- Department of Revenue
- Department of Workforce Development
- Discovery questions
- What baseline call and filing-time data exists before relaunch?
- Which document types are auto-classified versus routed to staff?
- How is assistant content approved and updated?
- Value hypothesis
- A lifecycle portal with grounded bilingual help may reduce calls and filing errors; unmeasured so far.
- Potential engagement
- A post-launch outcome-measurement plan tied to FY2025 filing and call baselines.
- Unsupported claims
- Call deflection
- Assistant accuracy
- ROI or cost savings
Pre-sales engineering
Role takeaway
- Fit
- Fits states modernizing business registration and licensing portals with AI-assisted help and intake.
- Architecture and integration
- AWS-hosted modular portal, cross-agency integrations, Google-built assistant over approved content, mavQ document classification with human routing.
- Prerequisites
- Legacy workload migration
- Approved content sources
- Document taxonomy and routing rules
- Constraints
- Multi-vendor stack
- Phased remaining integrations
- Agencies keep separate systems
- Security
- Document how business filings and identity documents are processed, hosted and retained by AI services.
- Proof of value
- Bilingual answer accuracy test
- Document classification and review-rate measurement
- Processing time versus FY2025
Delivery
Role takeaway
- Work
- Complete phased integrations and stand up outcome reporting through a CIO transition.
- Dependencies
- AWS hosting
- Vendor partners
- Agency integrations
- Ownership
- Indiana Secretary of State IT and product directors until a new CIO is named.
- Skills and adoption
- Train staff to manage CMS content and review routed documents.
- Governance checkpoints
- Content approval process for Liz
- Document AI review thresholds
- Leadership handoff plan
- Acceptance criteria
- Assistant accuracy measured in English and Spanish
- Routing accuracy measured on a sample
- Filing times reported against FY2025
- Risks
- Leadership gap stalls phases
- Unmeasured AI claims
- Vendor coordination overhead
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?
Lift to AWS as prerequisite, modular services, cross-agency integrations with Revenue and Workforce Development, a Google-built assistant over approved content, and mavQ document classification with human review routing; CMS lets staff control content.
Governance
Who approves, reviews and stays accountable for outcomes?
Leadership transition: CIO departed with phased work outstanding and no new CIO until the Secretary of State-elect takes office; continuity of AI governance is unstated.
Security and privacy
What data, permissions and controls need testing?
Business filings and identity documents flow through AI document processing; the articles do not describe data handling, model hosting or retention.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
Spanish-language assistant extends language access for business owners; document automation aims to reduce back-office load for staff handling 15,000-20,000 monthly calls (GovTech).
Procurement
What should contracts, pricing and exit terms secure?
Multi-vendor build (AWS, MTX Group, Google Public Sector, mavQ, Tomorrow Partners for CX research per GovTech); a separate securities case system was custom-built for lower total cost of ownership.
Operating model
Which teams own the service once it runs?
Shift from transaction-by-transaction service to lifecycle stages across agencies, while agencies keep separate systems and responsibilities.
Publication history
Read preserved resource versions (JSON)Stable resource ID: indiana-sos-inbiz-relaunch-liz-bilingual-assistant-document-ai-20261109