Why companies need Shanc.
Context is broken in most companies.
Documentation is missing or out of date.
In 77% of organisations, data quality issues go unresolved — and lack of documentation is the most-cited reason. Getting context means tracking down the person who wrote the code, every time.
Every commit is a liability.
The average developer makes 4 commits a day — each one can change your database. Someone has to update the semantic layer.
Feeding Claude context is expensive and repetitive.
Enterprise AI queries consume millions of tokens just loading schema definitions and lineage before any reasoning begins. Without a governed context layer, you're paying that cost on every session.
Insights live in silos.
When one analyst figures something out, the rest of the team can't see it or build on it. You end up paying for the same work twice.
Nobody trusts the output.
Every SQL query and data pull still gets manually reviewed because there's no validation layer. 85% of companies cite stale data as a direct cause of bad decisions and lost revenue.
How Shanc works.
Connect your data and get working context layer in minutes.
Feed Shanc your sources
Git history, data warehouse query logs, your company knowledge base, and any documents you want included.
Connect to Claude via MCP
Shanc plugs directly into Claude as a context source. Sign in, link your data, and Claude pulls from Shanc.
Every query stays grounded
Shanc validates SQL against your semantic layer so it runs correctly.
FROM orders
WHERE region = 'EU' valid · orders_v3
grounded · safe to run
Shanc can run locally on your machine — no data leaves your environment. For continuous sync, team-level layers, and multiplayer mode, connect your full data stack.
How teams use Shanc.
From a single question in plain language to knowledge the whole company shares.
Enable self-service analytics
Connect Shanc as an MCP server to your AI assistant and ask business questions in plain language. The agent generates and validates analytical queries using documented business definitions, then returns answers grounded in your organization's data.
Understand your data
Ask how things are actually defined. For example, "how is revenue calculated?" or "where does user data come from?" returns the exact tables, sources, and logic behind it — instead of digging through scattered documentation.
Enforce data governance
The platform builds a shared knowledge base for metric definitions, business rules, and data documentation. Teams use the same definitions across dashboards, reports, and AI agents, ensuring consistent metrics and reducing conflicting interpretations.
Accelerate onboarding
New employees learn how metrics, datasets, and business processes actually work by asking questions in plain language — instead of relying on senior engineers or tribal knowledge buried in chats and meetings.
Turn personal exploration into company knowledge
When an analyst explores data with an AI agent, they often discover corrections (e.g. a revenue definition fix), clarify logic, or create useful derived views. Shanc captures this knowledge automatically and makes it available to everyone in the company.
See Shanc in action.
Cases.
Used by data teams across fintech, retail, and beyond.
Fintech
Result coming soon.
Online rental platform
Result coming soon.
Meta-search engine
Result coming soon.
Major e-commerce
Result coming soon.
AI bots builder
Result coming soon.
FAQ.
Why can't I just connect Claude to my database and ask?
You can, but Claude doesn't know what your data means. It doesn't know that rev_net is the revenue Finance uses, which table is canonical, or how two tables are meant to join. So it guesses — and a wrong answer is worse than no answer. The missing piece is context: what every table and metric actually means. Shanc builds that context and keeps it current, so Claude reasons over facts instead of guessing.
What's actually new here?
Context layers aren't new. Context layers that maintain themselves are. Normally someone hand-writes the definitions, and they go stale the next time a developer ships a schema change. Shanc reads your git history and query logs and updates the layer on its own — so it reflects your data as it is today, not as it was six months ago.
How is this different from Omni?
Omni is a BI platform. You move your analytics into it, and its context layer is built and curated by your team inside its interface. Shanc is the layer underneath — it doesn't replace your BI tool or ask anyone to switch tools. It auto-maintains the definitions from your commits and query logs, then serves them to whatever AI you already use over MCP. Omni owns the interface; Shanc owns the context and plugs into yours.
Who is Shanc for?
Data and analytics teams that want their AI to answer reliably, and the analysts, PMs, and business people asking the questions. The people who feel the pain first are usually data engineers — the ones who'd otherwise keep documentation alive by hand — and heads of data who want one trusted set of definitions across the company.
How does Shanc handle governance?
Everything resolves against one shared layer — dashboards, reports, and AI all use the same definitions, so "revenue" means the same thing everywhere. Before a query runs, Shanc validates the SQL against that layer, so answers stay grounded and safe to act on. Instead of documentation nobody trusts, you get definitions the whole company works from.
Does my data leave my environment?
No. Shanc runs locally on your machine, and no data leaves your environment. Connecting your full stack unlocks continuous sync, team-level layers, and multiplayer mode when you're ready for it.
Does Shanc replace dbt, my warehouse, or my BI tool?
No. Shanc sits alongside your stack and reads from it — git history, warehouse query logs, your knowledge base, any docs you point it at. You keep everything you already use; Shanc gives your AI the context it's missing.
What does Shanc need to get started?
Your sources: git history, data warehouse query logs, and any documentation you want included. Connect them and you have a working layer in minutes.
How do I try it?
Run it free locally to see it on your own machine, or book a demo to connect your full data stack.