Governed database intelligence

Give AI access to your databases. Never raw SQL.

SchemaPilot discovers your schema, builds a reviewed semantic model, generates scored query tools your policy approves, runs reports with charts, watches for drift, and lets you deploy a Co-Pilot into your own apps. Every answer comes from an approved tool.

  • Read-only by design
  • Bring your own LLM key
  • Every execution audited
  • Embeddable in your apps
Works with the databases you already run
PostgreSQLMicrosoft SQL ServerMySQL / MariaDB
The product principle

AI may propose, interpret, explain and select. AI may not authorize, publish or execute ungoverned data access.

3
database engines
0
lines of generated SQL executed
charts and tables on every result
How it works

From raw database to governed answers in four steps

The same lifecycle for every source, no application-specific code. Each stage leaves a reviewable artifact: a snapshot, a model, a tool revision, an audit entry.

  1. 01

    Connect read-only

    Register a database with a read-only account, or paste a connection URL. Credentials are encrypted at rest with AES-256-GCM and edited or removed in place.

  2. 02

    Discover and model

    SchemaPilot profiles tables, keys, indexes and routines, proposes a semantic model with confidence scores, and lets your LLM enrich names, descriptions and metrics as a reviewable proposal.

  3. 03

    Approve scored tools

    Schema analysis writes KPI, trend, breakdown, ranking and record tools with a 0–100 usefulness score, risk level and rationale. Your governance policy auto-approves the safe ones; you review the rest.

  4. 04

    Report, ask, deploy

    Run tools with charts and tables, ask the Co-Pilot in plain language, and embed a deployed Co-Pilot in your own apps behind API keys. Raw SQL is never generated.

Platform

Everything between your database and your AI

A semantic model your team actually reviews

Physical tables become entities, attributes and metrics with business names and confidence scores. Edit anything; your overrides survive every rescan.

ordersidcustomer_idordered_atorder_itemsorder_idproduct_idqty · priceproductsidcategoryunit_priceRevenue4 keys · 3 entities

Plans, not prompts, decide what runs

Tools persist normalized query plans validated against the catalog. Approval is a human action with a revision number.

validatorplanentity · metric · filterapproved toolrev 3 · 100-row cap

Drift you can see before it breaks a report

Rescans stage immutable snapshots. Renames, drops and type changes list the exact tools they affect, and only those are suspended.

snapshot 12 · activeidcategoryunit_pricesnapshot 13 · pendingidcategory_nameunit_pricelaunched_at1 tool suspended

Choose your AI provider

Ollama is used by default. Save your OpenAI key to opt into the hosted provider; the key is encrypted with your organization id bound as associated data and decrypted only in memory for a single request.

AES-256-GCM · aad = organization idsk-••••••••7f2av2

Tools that explain their own score

Schema analysis decides what is worth asking: fact tables get KPIs and trends, lookups get lists, joins become labelled breakdowns. Each tool shows its score, risk and rationale, and your governance policy approves the safe ones automatically.

A Co-Pilot you can ship to your users

One script tag or a REST call. Publishable keys for browsers, secret keys for servers, origin allow-lists, rate limits and charts in the answers. Governed exactly like the app.

Multi-engine discovery

Tables, views, columns, foreign keys, indexes, routines, comments and bounded sample profiles from every supported engine, as immutable catalog snapshots.

Reviewed semantic layer

Entities, attributes and metrics with business names and confidence scores. Your edits survive rescans; LLM enrichment arrives as a stored proposal you accept per entity or discard.

Analysis-driven tool generation

Table roles, column roles, sensitivity, join paths and soft-delete filters decide which tools exist. Each carries a score, a risk level, a category and the reason it was written.

Auto-approval policy

Set a minimum score, maximum risk and allowed categories once. Safe aggregate tools are approved at scan time; everything else waits for a person. Apply a new policy to existing sources in one step.

Full tool lifecycle

Proposed, approved, published, suspended, retired, reactivated. Optimistic revisions mean only the exact version your team reviewed can run. AI-suggested tools are always Proposed first.

Schema drift review

Rescans stage snapshots and list the exact tools a rename, drop or type change affects. Breaking changes suspend only those tools until the review is accepted.

Reporting with charts

Run any approved tool with validated parameters. Results open as KPI tiles, trends or breakdowns with a one-click table view, in the app and inside deployed Co-Pilots.

Deployed Co-Pilots

Embed a chat widget with one script tag or call the REST API with hashed keys. Allowed origins, per-key rate limits, suggested questions and a monthly execution quota keep it governed.

Live, resumable work

Long LLM runs execute on the server with live progress. Leave the page, come back, and the result is waiting. Cancel at any time.

Complete audit trail

Every execution, Co-Pilot conversation and lifecycle move is logged with typed arguments and a sanitized outcome. Never credentials, never result rows.

Choose your AI provider

Ollama is used by default. Save an OpenAI key to opt into the hosted provider for your workspace; it is encrypted per tenant and removable at any time.

Secure accounts

Six-digit codes for email verification and password reset, every other session signed out on a password change, and card-backed trials through Stripe.

Security model

Built for the teams that said no to text-to-SQL

Execution authority belongs to deterministic policy and approved, versioned tool contracts. The language model is a planner, never an executor.

  • Source accounts must be read-only; connectors open read-only sessions and never execute routines.
  • Every identifier is dialect-quoted, every value is parameter-bound, results are capped at 100 rows.
  • Generated tools persist normalized query plans; previews are compiled, never trusted.
  • Breaking schema drift suspends exactly the tools it affects until a human accepts the review.
  • Your LLM key is encrypted per tenant and never shared across workspaces.
compiled preview · approved tool, revision 3
SELECT "products"."category" AS "category",
SUM("items"."quantity" * "items"."unit_price") AS "revenue"
FROM "public"."order_items" AS "items"
INNER JOIN "public"."products" AS "products" ON …
WHERE "items"."ordered_at" >= @start_date
GROUP BY … ORDER BY "revenue" DESC LIMIT @__limit;
plan validated against catalog snapshot
join backed by discovered foreign key
arguments bound, never interpolated
audited: user, args, outcome, duration

Illustrative example of a compiled preview; your tools are generated from your own schema.

Pricing

Plans that grow with your data estate

Every plan starts with a 7-day free trial. Add a card, cancel before the trial ends and you pay nothing. Bring your own LLM key; we never resell model usage.

Starter

For a single team bringing its first database under governance.

$49/ month
Start free trial
  • 3 connected databases
  • 5,000 governed executions / month
  • 3 deployable Co-Pilots
  • 90-day audit retention
  • Email support
  • Every supported database engine
  • Schema discovery & semantic model
  • Governed tool generation
  • Schema drift review & impact analysis
  • Bring your own LLM key
  • AI Co-Pilot included
Most popular

Pro

For data teams running governed analytics across several systems.

$149/ month
Start free trial
  • 10 connected databases
  • 50,000 governed executions / month
  • 10 deployable Co-Pilots
  • 90-day audit retention
  • Priority support
  • Everything in Starter
  • LLM-assisted semantic enrichment
  • AI Co-Pilot included

Business

For organizations standardizing AI access to enterprise data.

$399/ month
Start free trial
  • 50 connected databases
  • 500,000 governed executions / month
  • 50 deployable Co-Pilots
  • 365-day audit retention
  • SLA-backed support
  • Everything in Pro
  • Dedicated onboarding
  • AI Co-Pilot included

Need more than 50 databases, SSO, or a private deployment? Compare every plan.

FAQ

Questions teams ask first

Something else? Write to us.

Can I put the Co-Pilot in my own application?

Yes. Deploy a Co-Pilot bound to one data source, restrict it to selected approved tools, allow the origins it may run on, and embed it with a single script tag or call the REST API with a secret key. Every answer still goes through the same approvals, quota and audit trail as in the app.

What happens when my schema changes?

Checking for changes stages a new snapshot and lists every tool a rename, drop or type change would break. Only those tools are suspended, until you accept the review (which migrates the semantic model and regenerates tools) or dismiss it.

Does SchemaPilot write SQL from my questions?

No. Questions are routed to tools that your team has already approved. Each tool is a normalized query plan validated against the discovered catalog; the SQL you see is a compiled preview, never the execution authority.

Which databases are supported?

PostgreSQL, Microsoft SQL Server and MySQL / MariaDB today. The connector layer is pluggable, so additional engines can be added without changing the governance model.

Which AI provider is used?

Ollama is used by default. You can explicitly save your OpenAI key in Settings to use OpenAI for your workspace. The key is encrypted with a per-tenant binding and decrypted only in memory for each request.

What data is sent to the LLM?

Only tool names, descriptions and parameter names for routing, the parameter contract for argument extraction, and at most 20 aggregate rows for answer wording. Never schema, SQL, credentials or row-level data.

Can I try it before paying?

Yes. Pick any plan and start a 7-day free trial. A card is required so the plan can begin automatically when the trial ends; cancel before then and nothing is charged. The Co-Pilot unlocks once the paid plan starts. Billing is handled by Stripe.

Bring your first database under governance today

7 days free on any plan. Cancel before the trial ends and you pay nothing.