Data documentation that updates itself

Shanc documents tables, metrics and business logic, then keeps everything current as your data evolves. So your team and AI agents understand the data they work with.

Book demo Try me

Everything your data needs to be understood

Shanc documents your warehouse, keeps it current automatically, and serves that context to every agent and team.

Auto-documentation

Reads your warehouse schema, git history and existing docs, and describes every table, column and synonym in the company. Nobody has to find the developer who wrote it.

Metrics glossary

Built from your query logs. CAC, LTV, net profit, conversion — defined the way your team calculates them. Includes which filters to apply and how the tables join.

Classic token consumed
100x lessShanc token consumed

Fewer tokens

Without a layer, an agent reloads your schema and definitions into context on every question. Shanc holds that context once, so each query carries only what it needs.

Self-updating layer

Every commit and schema change is picked up automatically. No manual maintenance, no drift between the layer and the warehouse.

Governed multiplayer

Exploration sessions are written back into the layer, so one analyst’s finding reaches everyone. Findings are marked unverified until you approve them, and the agent is told which is which.

Your Agent
✻ connecting to shancconnectedwhat data do you wanna know?
>

Any agent over MCP

Shanc runs as an MCP server. Connect Claude, Codex or anything that speaks the protocol. Your warehouse, dbt and BI tools stay as they are. There’s a Shanc interface if you’d rather query there.

See Shanc in action

Book demo

Why teams need Shanc

Now Shanc builds and maintains the layer, so there’s no context to paste at the start of each session and I get 30 hours per analyst a month back

LeoAnalyst in fintech

Every analyst used to brief their own agent from memory. Now Shanc turns that context into one shared layer, and AI finally scales across our whole data team

AmaraHead of Data at a logistics scale-up

Our agents used to reload the whole schema on every query. Shanc loads the context once, so each question uses far fewer tokens and we save $30,000 per analyst a year

DanielAnalytics Engineering Lead in e-commerce

Business teams used to wait weeks for an answer to “why”. Now they self-serve answers they can trust, and I’m not left worrying they’ve acted on wrong numbers

MeiSenior Data Analyst in retail

Without a layer our agent got analytical questions wrong more often than right. Running them through Shanc, validated against real definitions, made it 2x more accurate

MarcusVP of Analytics in healthtech

Every commit and schema change is picked up automatically. Our docs finally stay in sync with the warehouse, and nobody on my team maintains them by hand anymore

JonasData Platform Lead at a SaaS company
Book demo

Shanc in numbers

View full benchmark
0%Answer accuracy on a real-world data warehouse.
0%Data documentation coverage.
0×Fewer tokens than an agent exploring schema for every question.
$0Saved per analyst each year.

Shanc is for teams whose business depends on data.

Already have data documentation?

  • Your analysts spend hours keeping it up to date, but it’s hard to keep pace with changes.
  • You spend tokens explaining the same data to AI, again and again.

No data documentation yet?

  • Answering questions about your data still depends on finding the right person.
  • Your AI spends more tokens trying to understand your data, and can still get the answer wrong.

Security & compliance

~/warehouse ▪ shanc audit
$ shanc audit --security --compliance
>
Runs in your environment

Shanc runs on your own machine or inside your cloud, alongside the warehouse it reads. Compute against your data happens where the data already lives — never on infrastructure Shanc operates, and never through a Shanc-hosted service.

Compliance & data protection

SOC 2 Type I in progress. Read-only, least-privilege access to your warehouse — Shanc never requests write scope.

On-premise deployment

For teams whose data can't touch a cloud: Shanc installs entirely within your own datacentre, including air-gapped environments. No outbound connection, no dependency on any Shanc-hosted service.

Cases

Serves consistent definitions across a large, multi-source warehouse feeding several markets.

Meta-search engineInternational

Documents a complex legacy operational schema so agents answer without an engineer in the loop.

Logistics SaaSInternational

Feeds validated context to its own agents, so answers about product data stay grounded.

AI bots builderInternational

Lets business teams self-serve on sales and inventory data against trusted definitions.

Major e-commerceEurope

Standardises client and utilisation metrics across projects into one queryable layer.

Professional servicesUK

Aligns booking, occupancy and revenue metrics across listings, so operations and finance read the same numbers.

Online rentalMiddle East

Grounds analyst queries in verified metric definitions, so transaction and revenue numbers reconcile across teams.

FintechSoutheast Asia

Gives its data team one shared glossary for engagement and retention metrics across a fast-changing product.

EdtechHong Kong
Book demo

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 and keeps it current, so Claude reasons over facts instead of guessing.

Why can't I just build this myself?

You can build a context layer — plenty of teams do. Building it isn't the hard part; keeping it alive is. The layer is accurate the day you finish it and starts drifting the next time a developer ships a schema change. Maintaining it by hand becomes a standing job: someone tracks every commit, updates definitions, re-checks joins. That's the cost Shanc removes. It reads your git history and query logs and updates the layer on its own, so you get what you'd build yourself, without the person whose whole job is keeping it from going stale.

Why not just use an LLM?

An LLM is only as good as the context it's given, and on its own it has none of yours. Ask it about your data and it fills the gaps with plausible guesses — the more fluent it sounds, the easier those guesses are to miss. More prompting doesn't fix it; it produces more confident wrong answers. Shanc gives the model a factual layer to reason over, so it works from your real definitions instead of inventing them. Same model, roughly twice the accuracy on analytical tasks.

Why not just write a skill?

A skill is a set of instructions you write for an agent. It's static, it isn't grounded in your actual schema, and it goes out of date the moment your data changes — so the agent follows the instruction confidently and still returns the wrong number. Shanc isn't instructions about your data, it's a structured layer built from your data: real tables, real definitions, real query logs, validated before anything runs and updated as the data moves.

Why not another tool on the market?

Most tools here either replace your stack or still need a person to maintain them. BI platforms ask you to move your analytics into their interface. Warehouse-native layers get curated by hand. The ones that auto-generate a layer mostly build it once and leave you to keep it current. Shanc sits under the stack you already have, maintains the layer itself from your commits and query logs, and serves it to whatever agent you already use over MCP. Nothing to migrate, nobody assigned to keep it alive.

See all FAQs

Try Shanc

Ask about your own data and get answers grounded in your real definitions — the way your agents will.

Book demo
~/warehouse ▪ shanc agentlive
>