Pluggable.
Philosophical.
Powerful.

A analytical analytics platform
that learns every domain it enters.

Every organisation has the same shape of pain.

  • Multiple source systems — different ERPs, different column names, different export formats. No canonical truth.
  • Reconciliation is manual — spreadsheets, ad-hoc queries, tribal knowledge. Findings don't accumulate.
  • Domain expertise is scarce — the person who knows what “normal” looks like retires, changes roles, or was never hired.
  • Every new domain starts from zero — new industry, new consultants, new six-month discovery phase.

One engine. Pluggable domain packs.
An AI colleague that knows your tenant.

The Engine
Declarative pipeline. YAML-to-SQL compilers.
Multi-tenant. Per-deployment sovereignty.
Explorer, AI colleague (evolve), CLI.

How to ingest, validate, verify, and present.
Domain-agnostic. Ships once.
The Domain Pack
Entity schemas. Source-system mappings.
Signals, theses, verdicts, Subject Matter.
Tri-lingual display text.

What to look for and why it matters.
All YAML. All swappable.
The AI Colleague
Named per tenant. Knows your framework.
Reads your signals. Drafts new ones with you.
Never bypasses the engine.

Who authors alongside you — at your pace.
Deterministic execution. With or without AI.

Make. Explore. Evolve.

Make
Compile artifacts.
Build the database.
Validate everything.
→
Explore
See the findings.
Understand patterns.
Ask new questions.
→
Evolve
A named AI colleague.
Co-authors new analytics.
The framework gets richer.

Evolve feeds back into Make. The cycle never ends.
Each turn produces a richer, more accurate analytical system.

The analytical shapes are the same everywhere

  • Balance signals — compare two aggregates. Usage vs billing. Received vs sold. Ordered vs delivered.
  • Duplicate detection — same shape everywhere. Invoices, shipments, purchase orders, identities.
  • Distribution outliers — flag what doesn't fit. Z-score on prices, quantities, cycle times.
  • Trend & temporal sequence — rolling drift, ordering violations. Costs, lead times, event sequences.
  • Taxonomy hierarchies — cost centres, product categories, regional structures. Same closure table, different labels.

The entity names change. The architecture doesn't.

Six packs in flight today.

nuMetrix · live
Hospital material flow + financial reconciliation
OPALE / SAP IS-H integrations. In production.
hrcentral · live
Workforce + payroll analytics
Multi-source affiliation reconciliation. In production.
Millésime · early
Winemaking operations
Valais domains in development.
Alptrack · early
Ski-resort operations
Lift, snow, dispatch, season-pass economics.
Interlogic · early
Freight forwarding
Multi-mode logistics reconciliation.
Lexflow · planned
Legal offices
Matter economics, time tracking, client portfolio.

The pattern transfers. The engine doesn't change. The pack ships the domain.

Open engine. Expert domain packs.

jinflow Engine
Pipeline, compilers, Explorer, AI colleague.
Source-available to customers.
Runs on the laptop or in the cloud.

The platform. Trial it locally.
Domain Packs
Analytical rules, interpretation,
regulatory context, calibrated thresholds.
Subscription per tenant.

The expertise. The revenue.
Custom Packs
Engagement to build a pack
for a new industry.
AI-accelerated authoring.

The growth path.

Each domain pack makes
the platform smarter for the next one.

Domain A
new signal types
→
Domain B
better thresholds
→
Domain C
richer DSL
→
Compound
Expertise

Calibrated thresholds. Interpretation rules. Regulatory knowledge.
Source-system expertise. All encoded in domain packs.

The framework gets better at every domain because it's been to others.

The framework
that learns every domain
it enters.

Highly automated. Deeply interactive.
AI brings the expertise. The engine makes it actionable.
Each deployment makes the next one faster.

One framework. Many domains. Infinite expertise.

jinflow.io