Turn Fragmented Enterprise Data into Unified Intelligence

StringQL combines query language + graph database + vector search + AI to investigate across enterprise systems, public data, and documents. Built for compliance, audit, fraud detection, and AI agents.

  • Query across enterprise systems (SAP flagship), public data, and documents
  • Graph + timeline + vector search in one reasoning stack
  • Built for compliance, audit, fraud detection, and AI agents

Join 500+ SAP customers on the waitlist

How StringQL Works

StringQL is a complete reasoning infrastructure stack:

┌─────────────────────────────────────────────────────┐
│ StringBoard (Command Center)                        │
│ • Causal Graph  • 4D Timeline  • Interactive UI     │
├─────────────────────────────────────────────────────┤
│ StringRL (Audit Engine)                             │
│ • Deterministic reasoning (not probabilistic)       │
│ • Single verifiable result with audit trail         │
│ • RCA keywords: INVESTIGATE, TRACE, VERIFY, INFER   │
├─────────────────────────────────────────────────────┤
│ StringDB (Temporal-Graph)  │  PageIndex (Librarian) │
│ • Stores causal flow       │  • Grounds AI logic    │
│ • Timeline + Graph queries │  • Evidence provider   │
├─────────────────────────────────────────────────────┤
│ Data Sources (On-prem & Cloud)                      │
│ SAP S/4HANA · Emails · Logs · Docs · data-zoo.de    │
└─────────────────────────────────────────────────────┘

Reasoning You Can Audit. Logic You Can Trust.
Unlike GenAI (probabilistic guesses), StringRL provides deterministic proofs backed by evidence.

Built for AI Reasoning

🤖

Structured Results

Graph paths (not unstructured JSON) prevent LLM hallucination on relationships

🧠

Explainability

Every match includes the reasoning (WHY, not just WHAT)

🔁

Autonomous Monitoring

"Watch for pattern X, alert when confidence > 80%"

Example: AI Agent Investigation Flow

  1. 1. Agent receives tip: "Vendor 12345 might be suspicious"
  2. 2. Agent queries StringQL: MATCH (v:Vendor {id: 12345})-[*1..3]-(e) RETURN e
  3. 3. StringDB returns: Connected entities + relationships + fraud risk scores
  4. 4. Agent reasons: "3 shell companies, same address, circular payments detected"
  5. 5. Agent escalates: "High confidence fraud pattern, recommend investigation"

Why graph queries enable better reasoning: Relationships are explicit → No hallucination | Results are structured → Easy to chain reasoning steps | Patterns are reusable → Build institutional knowledge

Reasoning as a Service (RaaS)

The API for Trust

We are not another Generative AI API. We are the first "Audit Engine as a Service," designed for developers building high-trust enterprise systems that cannot afford hallucinations.

📥

Ingestion API

POST /v1/index

Feeds the engine with unstructured data (Emails, Logs, Docs) to build the verifiable evidence foundation.

  • Automatically indexes all data sources
  • Normalizes formats (PDF, DOCX, TXT, CSV, JSON)
  • Creates searchable evidence library
💡

Reasoning API

POST /v1/reason

Takes a StringRL query and returns a deterministic JSON Audit Trail, complete with a Causal Graph and deep links to original evidence.

  • Single verifiable result (not probabilistic)
  • Complete audit trail with evidence links
  • No hallucinations via PageIndex grounding

From Probabilistic Guesses to Deterministic Proofs.

Request API Access

Cypher You Know. Superpowers You Don't.

StringQL = Cypher + Timeline + Causality for investigation reasoning

STANDARD CYPHER (Neo4j)
MATCH (po:PurchaseOrder)
  -[:TO]-> (vendor:Supplier)
WHERE po.amount > 50000
RETURN po, vendor
ORDER BY po.amount DESC
Returns:
✅ Graph matches
❌ Missing: WHY they match
❌ Missing: WHEN (timeline context)
❌ Missing: Confidence scores
STRINGQL (Cypher + Timeline + Causality)
INVESTIGATE root_cause
FROM PurchaseOrder('PO-45892')
WHERE status = 'DELAYED'
TRACE causality
  BETWEEN Vendor AND Approval
TIMELINE [last_30_days]
VERIFY logic_path
  WITH PageIndex.Source
RETURN audit_trail,
       evidence,
       confidence
Returns:
✅ Complete audit trail with timeline
✅ Evidence links to source documents
✅ Causal graph (WHY it happened)
✅ Confidence scores + verification
QUERY RESULT
Executed in 1.2s • 23 matches found
⚠️
PO #45892 → Vendor "Apex Trading GmbH" (€125,000)
Approved by: John Miller (limit: €50K) • Vendor flagged: EU Sanctions List
⚠️
PO #45891 → Vendor "Global Solutions Ltd" (€78,500)
Approved by: Sarah Chen (limit: €25K) • Vendor flagged: OFAC Sanctions
+ 21 more matches

Same Cypher you know, investigation superpowers you don't.

StringQL adds Timeline (temporal reasoning) and Causality (explain WHY) to every query. Queryable. Auditable. Trustworthy.

Learn StringQL Syntax →

StringRL: Investigation-Native Keywords

RCA-specific commands that automatically trace root causes, build audit trails, and verify AI logic against raw evidence.

INVESTIGATE root_cause FROM

INVESTIGATE root_cause FROM PurchaseOrder('PO-123')

Automatically traces all causal paths and builds comprehensive audit trail showing timeline, evidence sources, and confidence scores.

TRACE causality BETWEEN

TRACE causality BETWEEN Email('E-456') AND Delay('D-789')

Establishes evidence-based causal relationship between two entities using temporal precedence and logical dependency.

VERIFY logic_path WITH

VERIFY logic_path WITH PageIndex.Source

Validates AI-generated logic against raw data from PageIndex. Ensures no hallucinations—every claim backed by source.

INFER missing_link WHERE

INFER missing_link WHERE context = 'logistics'

Infers logical steps based on verified timestamps and workflow knowledge. Clearly marks inferred (vs observed) data.

For SAP Developers: Automate RCA for incidents (Delays, Disputes, Errors) with 80% time reduction

Explore All Features

Built for Enterprise Investigation Teams

SAP audit, compliance, procurement fraud, and supply chain risk management

Procurement Fraud Detection

"Who approved these 50 purchase orders to the same vendor?"

Visualize approval chains and vendor relationships from SAP MM/FI data. Enrich vendors with data-zoo.de to detect shell companies and conflicts of interest.

SAP Audit Trail Analysis

"Show me all changes to vendor master data in the last 6 months"

Import SAP change documents (CDHDR/CDPOS) and visualize entity evolution. Track who changed what, when, and whether it was properly approved.

Vendor Due Diligence

"Are any of our suppliers on sanctions lists?"

Bulk-enrich your supplier base with data-zoo.de. Screen against OFAC, EU sanctions, check beneficial ownership, and assess financial health.

Revenue Leakage Investigation

"Which customers have credits but no corresponding invoices?"

Graph-based queries across SAP SD/FI reveal financial anomalies that table-based queries miss. StringQL makes complex cross-module queries simple.

Join the Waitlist

Be first to access SAP connector + data-zoo.de enrichment.
Early access members get 50% off first year.

Join 500+ SAP Customers →

No credit card required · Launch Q2 2026