Q

2.0

Trusted in Production ยท Highly Regulated Agency

The AI Data Hub for a Top-5 American Public Pension Fund Managing $400B+ in Assets.

Private AI, air-gapped VPC. AI Safety & Data Security guaranteed. One Hub for business and technical users โ€” conversational, in plain English.

3 weeks
Time to production โ€” first use case live
8ร— ROI
Realized return in production today
700+
Tables in the semantic catalog โ€” 15,000+ columns, 450+ relations, auto-discovered
Days โ†’ Sec
Knowledge retrieval โ€” quick access to enterprise tribal knowledge
Private LLM
AI Safety Controls ยท NIST ยท OWASP ยท ISO
Year 1

Established the data and AI foundation.

Year 1 wasn't a rollout. It was foundation work โ€” the underlying capabilities every Year 2 use case depends on. Eight pillars, all delivered.

01
01 ยท INFRASTRUCTURE
Production AWS environment

xAQUA deployed on the Authority's own AWS. Monitoring across GPU, EC2, EKS, RDS, Lambda. Auto-scaling, Splunk logging per ISO requirements, 24ร—7 availability.

02 ยท PRIVATE AI
Private LLM, air-gapped

A private LLM running entirely inside the agency's own VPC. No external APIs, no telemetry, no inference touching the public internet. Open-source LLM cuts cost without compromising the boundary.

03 ยท LLM GATEWAY
Governed AI access layer

Every LLM call carries customer ID, user ID, use-case context, and sub-context โ€” per-use-case routing, audit trails, rate limits, policy enforcement. Private AI safely usable by many applications at once.

04 ยท AI SECURITY CONTROLS
Uniform across every capability

RBAC, audit logging on every interaction, PII masking applied uniformly, ISO-aligned controls. The architecture has no path to external infrastructure โ€” that's the design, not a setting.

05 ยท SEMANTIC FOUNDATION
700+ tables ยท 15,000+ columns

Core benefits database cataloged with technical, business, and semantic metadata. 450+ relationships auto-discovered. The shared layer every agent inherits.

06 ยท DATA QUALITY FRAMEWORK
Profiling & rules engine

Multi-dimensional profiling โ€” completeness, uniqueness, consistency, validity. Custom rules engine with automated alerting. The framework Year 2 builds the formal practice on top of.

07 ยท STANDALONE RAG
Archer Bot โ€” architecture & design

Architecture for Archer, the agency's standalone RAG-powered AI assistant. User auth, RBAC, selective retrieval, source transparency, chat audit logging. The pattern every Year 2 assistant inherits.

08 ยท DATA HARVESTING
Secure NLQ-to-SQL pipeline

Secure data harvesting with RBAC, PII masking, audit logging, and multi-format export. NLQ-to-SQL over the core benefits database. The plumbing the 13โ€“15 analyst team is being phased onto in Year 2.

Year 2 ยท Scale Into the Business

An executive AI portfolio โ€” not a single bot.

Purpose-built assistants for the leaders of a $400B+ fund. Same governance, same audit trail, every output cited.

02
Chief Executive Officer
CEO Executive AI

22 use cases across board meeting preparation, strategic plan monitoring, modernization program oversight, audit & risk intelligence, legislative tracking, actuarial briefings, stakeholder communications, workforce intelligence, committee synthesis, and real-time decision support during board meetings and media inquiries. 35โ€“55 hours/week of CEO-level time savings.

Chief Investment Officer
CIO Executive AI

Investment portfolio oversight, IPS compliance, allocation analytics, asset-class drill-downs, manager performance, risk posture. Conversational access to the data and decisions that shape a $400B+ portfolio.

Investment Leadership
Investment Executive AI

For senior leaders across the investment branch: collaborative model analytics, peer benchmarking, portfolio risk reports, semi-annual CIO activity intelligence. Same-second answers on the questions that drive trustee oversight.

Actuarial Leadership
Actuarial Executive AI

Funding plan trajectory, scenario analysis, return assumption sensitivity, funding risk reports, modernization-readiness scoring. The CFO/Actuary's plain-English line into the fund's long-horizon math.

Each Assistant Runs on Three Capabilities
RAGCONVO Strategic Advisor Synthesizes across hundreds of source documents โ€” governance, policy, legislation, actuarial reports, stakeholder comms โ€” with cited answers.
CONVERSEDATAIQ Performance Advisor Calculates and visualizes from structured operational data โ€” investments, funding, ops, risk, budget, workforce โ€” in real time.
NARRATIX Executive Briefing Auto-generates a complete multi-chart fund story with data narratives, insights, and recommendations. No question required.
All inside the air-gapped VPC. Same governance, same audit trail, every output cited.
Year 2 ยท Scale Into the Business

DocIQ โ€” seven functions on one indexed corpus.

Not a chatbot. Not an OCR vendor. The unified document intelligence platform the Frankenstack of point tools has been pretending to be. One ingestion. Seven destinations.

03
๐Ÿ’ฌ
DOCIQ CHAT
Q&A ยท Cited Answers

Grounded Q&A with page-level citations on every claim. Hybrid BM25 + vector retrieval. Per-domain agents (Pension, HR, Legal, Finance, IT). Effective-date awareness for amended documents. Refuses to fabricate if retrieval is below confidence.

โœ๏ธ
DOCIQ CREATE
Generation from Templates

Generate SOPs, BPAs, RACI matrices, test cases, requirements specs, briefing memos, audit responses, and board papers โ€” from your sources, in your templates. Four-stage wizard with an approval state machine and immutable audit trail.

๐Ÿ”ง
DOCIQ EXTRACT
Structured Data from Unstructured

Turn PDFs, scans, emails, forms, contracts, transcripts, HTML, JSON, XML, and spreadsheets into clean structured data with confidence scores you can route on. Custom schema designer. Low-confidence rows auto-route to human review. Inline corrections save back as ground truth.

๐Ÿ›ก๏ธ
DOCIQ MASK
Sensitive Data Protection

Automatically identify and mask sensitive data across your corpus. PII, PHI, financial identifiers, and custom sensitivity patterns you define. Multiple modes โ€” redaction, pseudonymization, tokenization, format-preserving encryption. Role-based selective reveal. Every mask logged.

๐Ÿ“š
DOCIQ LIBRARY
Governed Knowledge Store

The governed home for every output, template, and schema. Versioning, supersession chains, pinning, cross-collection search. Permissions inherited from source-system ACLs. Audit-ready by default.

โš–๏ธ
DOCIQ REVIEW
Contract Review ยท ~90s

Coverage check, risk scan, redline draft in ~90 seconds. Bootstraps a playbook from your historical contracts. Counterparty-specific learning suppresses recurring false positives. Tracked-changes DOCX export โ€” send straight to counterparty.

๐Ÿ›‚
DOCIQ COMPLY
Continuous Compliance

Living map between regulations (HIPAA, SOX, GDPR, FedRAMP, ISO 27001, PCI-DSS, ERISA, custom obligations) and your policies, procedures, controls, and contracts. Audit-evidence package generation in seconds.

One ingestion. Seven destinations.

A document indexed for Chat is instantly a source for Create. A correction in Extract becomes ground truth for the next Chat answer. A masking policy applied once protects every downstream function. Shared substrate, not stitched APIs.

Federated, not migrated.

DocIQ runs on documents wherever they live โ€” S3, Azure Blob, GCS, SharePoint, OneDrive, Google Drive, Box, Confluence โ€” at the same time, with one search, one permissions model, one audit log. Your bytes never leave the source.

Year 2 ยท Scale Into the Business

Augmenting the business โ€” across the agency.

Beyond the executive portfolio and DocIQ โ€” four more initiatives that change how the agency operates day to day.

04
Data Harvesting at Scale
Augmenting the analyst SQL team

The 13โ€“15 analyst SQL team being phased onto AI-assisted query generation. Three-layer QA โ€” automated harness validation, tiered human review, continuous feedback. Sensitive queries always require human sign-off. Analyst expertise redirected to complex analytical work.

Data Quality Practice
The agency's first formal DQ practice

Rule library across six quality dimensions, monitoring dashboards, steward workflows, governance with domain ownership and remediation SLAs. Modernization-readiness scoring by domain.

Self-Service GenBI
Reporting without the IT queue

Natural-language querying (ConverseDataIQ), automated narrative reporting (Narratix), and an Analytics Data Lake. Department-by-department rollout across actuarial, member services, employer reporting, compliance. Predictive analytics into actuarial scenario modeling.

Modernization Program Intelligence
Live AI oversight on a $500M+ program

Live operational intelligence: call-center recovery, member adoption, defect burn-down, M&O budget. Automated AI enrichment of post-go-live incident records โ€” categorization, clustering, root cause analysis, Known Error Database, release prioritization.

In Year 1 we established the data and AI foundation โ€” private AI inside the agency's air-gapped VPC, the LLM Gateway, the semantic catalog over 700+ tables, the data quality framework, secure data harvesting, and the standalone RAG architecture for Archer. In Year 2 we scaled that foundation into the business โ€” executive AI for the CEO, CIO, and investment and actuarial leaders; the full DocIQ document intelligence suite; analyst-team augmentation; the agency's first formal DQ practice; and live operational intelligence across the $500M+ modernization program.

Run xAQUA in your own VPC.

If you're a public agency, regulated enterprise, or modernization leader looking at AI that respects your data residency and audit posture โ€” we should talk. The platform is designed for the bar this story sets.