The Ziggy intelligence platform

A modern Enterprise Intelligence Platform deployed in days not months

Own the platform, own the code, plug and play with your own LLM

From enterprise data to trusted AI context

Output plane
AI Agent
ML Models
Reporting
MCP
Control plane
Glossary
Ontology & semantic layer
Governance, ownership & stewardship
Data retention
Context plane
Modeling
Classification
Data quality
Lineage & impact
Runtime ontology
Data products
Infrastructure plane
Connections
Introspections
Pipelines
Your data estateDatabasesData platformsERP and CRMSpreadsheets...many more

Ziggy UI

Take a look at Ziggy

Run the video or click on a button to see a brief overview of each area.
more coming...
Select a chapter

Ontology

Ontology and Logical Modeling

You can create your ontology from scratch but Ziggy lets you design and build an ontology from your existing physical estate in minutes, which you can then fine tune - just by chatting.
Scroll to read the whole chat

Build an ontology for Brightfield from its existing data. Use the warehouse's mart tables as the authoritative source, and map each concept back to the source system it starts in.

Looking up Brightfield's systems and the warehouse
Profiling the 20 mart tables and their 359 columns
Matching mart columns to the source systems' tables
Grouping the tables into business domains
Drafting concepts, definitions and synonyms
Working out relationships from the keys
Checking every column has exactly one owner

Here is a first ontology for Brightfield: 5 domains, 33 concepts, 359 properties and 49 relationships. Every mart table is the authoritative source of at least one concept, and 26 concepts also point back to the source table they start in.

DomainConceptsSteward
CommercialProduct, Brand, Category, Customer, Store, Order, Invoice, Sell-out, Sell-through, Promotion, Promotion Plan, Promotion Result, Price AgreementLuis Ortega
Supply ChainSite, Plant, Distribution Center, Shipment, Inventory, Forecast, Service Level, OTIF, Fill RateHannah Brooks
FinanceGL Account, GL Amount, Cost Center, Fiscal Calendar, Standard Cost, Trade SpendOmar Haddad
ConsumerConsumer, Consumer CaseGrace Liu
PeopleEmployee, Sales Region, Sales TerritoryGrace Liu

Two choices worth checking:

  • Customer and Consumer are separate. A customer is the retail chain that buys from Brightfield; a consumer is the shopper who buys from the retailer.
  • Consumer and Price Agreement have no mart table. The mart leaves out personal data and negotiated price terms, so these two map only to their source systems.

It's all in a changeset, so nothing is live yet. Anything to change before it goes to the stewards?

Add three business terms that have no data behind them: TPR, Sell-in and KAM.

Adding three Business Terms to the glossary

Added as Business Terms: each has a definition and synonyms but is never mapped to data.

TermAbbreviationDomainDefinition
Temporary Price ReductionTPRCommercialA promotion mechanic: the shelf price is cut for a limited time, funded by Brightfield
Sell-inCommercialWhat Brightfield sells to its customers: orders, shipments and invoices
Key Account ManagerKAMPeopleThe Brightfield employee who owns the relationship with a customer and plans its promotions

Fill rate is also called case fill. And give the fiscal calendar the abbreviation 4-4-5.

Updating Fill Rate and Fiscal Calendar

Done.

ConceptChange
Fill RateSynonyms "case fill" and "case fill rate" added
Fiscal CalendarAbbreviation 4-4-5, and "4-4-5 calendar" added as a synonym

A search for "case fill" or "4-4-5" now finds them, in the glossary and when you ask me.

Looks good. Send it for approval.

Submitting the changeset to Luis, Hannah, Omar and Grace

Sent. Each steward reviews the domains they own: Luis has Commercial, Hannah Supply Chain, Omar Finance, and Grace Consumer and People. Once they approve, the ontology is live: it shows in Explorer and the glossary, and I use it to answer questions about Brightfield's data.

Ask anything about your data

Once finished, you can see your Ontology in the UI, or chat about it with MCP or Claude Code.

Natural language

Don’t just ask a question, have a conversation with any capability on the Ziggy platform

There’s no question you can’t ask, no change you can’t make. Query, edit, add and ask questions like Is my data estate compliant with the CPG regulations for product callbacks? Or just ask how to use the product.
Parts of the chat may be sped up for demo purposes

Ask anything about your data

Three ways to get AI-ready data

Buy six tools, build your own, or run one system

The old way

Six vendors

$1M–$10M a year · 7 contracts

Catalog and governance, data quality, modeling and ontology, pipelines, AI and context generation.

Time to live

9+ months

In-House build

Build it yourself

$1M · a team of 5 FDEs

Requires deep domain expertise from every data practice. You get sucked into early delivery before it’s ready. And will it really work in the end?

Time to live

18 months

Ziggy

One single system

From 50K

Starter Kit

Yearly

From 100K

Source Code

One-time fee

Complete AI data readiness in one AI-native solution, represented logically in an ontology graph, with the source code.

Time to live

Days

Speed

Enterprise Data Management platforms are notorious for “high effort, low value”.

Flip the script and finally scale delivery of superior data quality and context wrapped in your own best practices. In days, not months.
Select a chapter

Compliance

Regulatory reports compliance

See if your data estate provides all the information required to deliver BCBS, ESG, HIPAA (etc.) compliance. Then discuss how to fix and chat your way to completion.
Scroll to read the whole chat

We are US consumer packaged goods (CPG) food and beverage manufacturer. Which US regulatory compliance reports could we produce from Brightfield's existing data? Give me two tables: one for reports the current data fully supports, and one for reports it doesn't, saying what data is missing for each.

Looking up Brightfield's systems
Reading the ERP, supply chain, CRM and finance schemas
Reading the HR, point of sale, trade promotion and warehouse schemas
Querying the product range, ledger accounts, HR records and store states
Checking which stores are in tax and bottle-deposit areas

Brightfield's current data fully supports 3 US compliance reports. Another 19 need data it doesn't hold: 4 small gaps, 5 medium and 10 serious.

Two dates are close. The FDA food facility registration renewal window closes on 31 December 2026, and the data has the plant and warehouse addresses but not the other details the form asks for. California's food additive ban starts on 1 January 2027, and with no ingredient lists you can't check which products it hits.

Fully supported (3)

ReportForBuilt from
Price and promotion fairness self-check (Robinson-Patman Act)FTCDiscounts, promotion funding and display fees for each chain, by channel
Answers to requests to see or delete personal dataState privacy laws (California and others)Consumer contacts, complaints and rebate claims; HR records for California staff
Sales by destination state, for state income-tax apportionmentState tax departmentsInvoices by delivery store, 43 states

Not supported (5 of 19)

ReportGapWhat's missing
State additive bans and warnings (California, West Virginia, Texas); FDA Red No. 3 banSeriousIngredient list for each product
Nutrition Facts, allergen and "healthy" claim checksSeriousRecipes, ingredients, nutrient values and allergens
Supplier traceability records, including FSMA 204 for the peanut-butter pretzelsSeriousIngredient and packaging suppliers, and what each delivered, by lot
Recall list of stores that got a lotMediumLot code on store deliveries (lots can only be traced as far as the warehouse today)
FDA food facility registration renewalSmallDUNS numbers, owner and emergency contacts, FDA food category codes

I'd close the four small gaps first: each needs only one or two new fields, and together they unlock four reports.

Yes, list them

Closing the four small gaps takes 8 new fields: 2 on drink products, 1 on stores, 3 on plants and warehouses, 1 for the company, and 1 new list of declared emergencies.

ReportField to addAdded toWhere the answer comes from
Bottle depositsContainer: aluminum can, plastic bottle or glass bottleEach drink productPack specification
Sweetened-drink taxesSweetener: sugar, artificial, both or noneEach drink productIngredient label
Sweetened-drink taxesInside the taxing city's limits: yes or noThe 33 stores in Seattle, Philadelphia, San Francisco and OaklandEach store's location checked against public city boundaries
Price-gouging checkDeclared emergencies: state, counties, start and end dates, allowed price riseA new listPublic emergency declarations
FDA registrationFDA registration number and DUNS numberEach plant and warehouseFacilities team; Dun & Bradstreet
FDA registrationEmergency contact: name, phone and emailEach plant and warehouseFacilities team
FDA registrationFDA food categoriesEach plant and warehouseWorked out from what each site makes or stores
FDA registrationOwner or operator: legal name, address and contactThe company, onceLegal team

Everything else these reports need is already there, such as drink sizes, pack counts, store states, prices over time and site addresses. I'd add these fields to the Brightfield data so all four reports can be built and shown in Ziggy.

Shall I add them?

Ask anything about your data

For in-house teams

Accelerate your build with the Ziggy Source Code

Free yourself from SaaS vendors and take control of cost and capabilities. Just one or two people can develop Ziggy into your own future without the risk and delays of a ground-up, in-house build.

AI Harness

AI Native
Ziggy was designed from the ground up to be built and maintained with AI (i.e. Claude Code).
Tests
Tens of thousands of intent based automated tests (e2e, unit) are created automatically whenever code changes are made.
Skills
A wide range of Skills, from coding rules, token optimization, code reviews and security scans to user doc generation.
Frugal
Ziggy is optimized to minimize token usage without sacrificing quality. Fable, Opus and Sonnet and effort level automatically chosen for each plan phase.
  • Zero lock-in

  • Never wait on a roadmap

  • Extend with Claude Code

  • Self-documenting

  • Training and support

Security

Security baked in

We all know how easy it is for security gaps to appear with the smallest change. Ziggy has security baked into every code change to secure it both from outside attack and leaks within Ziggy itself.
Scroll to read the whole chat

Review the two fixes to the read-only SQL check before we merge them.

Running an arm's-length security review of the change

The review found that the two fixes weakened the read-only check: one Serious problem and four Medium ones. The new comment-and-quote reader now decides what counts as code, but each database's rules for it were written on the premise that they could only ever make the check stricter.

Security findingHow bad
On MySQL and MariaDB, a hidden second statement with a DELETE now passes the whole check. Only the database driver's default setting stops it running.Serious
On Postgres and SQL Server, nested comments can hide a second statement from the text check; only the parser still catches it.Medium
On SQL Server, ]] inside a bracketed name can hide code; only a parse error catches it.Medium
Some per-database comment and line-ending rules are guesses that now let text through rather than refusing more.Medium
A metric measure was promised to refuse any semicolon, but now accepts one inside a quoted value or comment.Medium
On Databricks, words inside an optimizer hint are no longer checked. Nothing is reachable through it today.Small
Product findingHow bad
SQL ending in ; -- a comment is still refusedSmall
Two efficiency tidy-ups (the same text read several times; one list repeated)Small

Four test gaps: nested comments, decoy /*! text, a bare carriage-return line end, and ]].

Patching these one by one would keep trusting a reader that can disagree with the database. My recommendation is a safer design for the one fix round:

  • Undo both fixes, so the check is exactly as strict as before.
  • For pipeline SQL steps only, remove the comments before the check, and send the database the same comment-free text that was checked.

If the reader ever misjudges a comment, the worst case is that text is dropped or refused. Nothing unchecked can reach the database. That fixes the ESG pipeline steps and the comment-word problem. A semicolon or write word inside a quoted value would stay refused, as before.

Shall I do the fix round that way?

Ask anything about your data

Replace

Rip and Replace

Coming up on your SaaS renewal? Instead of building your own, let Ziggy be your base. Built by data domain experts for data experts.

Build a repeatable data and AI practice.

Partner with Ziggy →

Ready to see it live?

Book a demo, start a trial, or talk to us about partnering.

Book a live demo