How Ward gets from a question to a figure you can check.
Ward queries your systems where they live. Its own data lake runs the math and checks every result. The AI only turns your question into queries and writes the answer, and each figure links back to the row it came from.
Seven steps, and the model is in two of them.
Most of the work happens in the data lake, where it is cheap and exact. The model is used for the two jobs only a model can do: reading the question and writing the answer.
Connect
Live databases connect through Ward’s proxy on a read-only credential, and a read-only replica is enough. Exports, Stripe, logs and PDFs sync into the lake by batch, micro-batch or streaming. You choose per source.
Store
Synced data lands as Parquet-based columnar storage on a custom fork of Apache DataFusion. Columns compress far better than rows, so the same data takes less disk and less memory to scan. Streaming rows are queryable the moment they land.
Index
Ward keeps its own index format for lookups and query planning, and partitions and clusters the same table at once. A question about one store and one week reads that store and that week.
The model writes the queries
The model reads your question and the schema it needs, and writes queries in Ward’s JSON query format. It does not see your tables and it does not calculate anything.
The lake computes
Ward runs the queries, joining live tables through the proxy and synced tables in the lake as one database. Every figure in the answer is computed here, under the asking user’s row- and column-level policies.
Three checks, or it loops back
Each figure is checked for valid data, an efficient query, and whether it answers the question asked. A failure rewrites the query and checks again. Context windows stay small, so checking adds little to the model bill.
The answer, with its citations
The model writes the sentence around the computed figures. Each figure is a citation linked to its query and source rows, and every access along the way is logged with the policy that allowed it.
Live databases are joined where they sit.
An enterprise will not turn the ocean liner for a few percent. The proxy means it does not have to: point Ward at a read-only replica and ask across every system as one database.
FreshnessSynced sources land by batch, micro-batch or streaming. Streaming rows are queryable the moment they arrive.
Compression is where the compute bill goes.
Columnar storage, Ward’s own indexes, and partitioning with clustering on the same table. The result is a large lake on a small server.
Columnar and compressed
Parquet-based storage on a custom fork of Apache DataFusion. Columns compress far better than rows, so the same data takes less disk and less memory to scan.
Its own index format
Ward keeps its own indexes for lookups and query planning. A question about one store and one week reads that store and that week, not the table.
Partitioned and clustered at once
The same table is partitioned and clustered together, so a query can skip whole partitions and then read a narrow range inside the one it keeps.
The model never does the math
The AI turns your question into queries and writes the answer. The lake computes every figure. The model sees the question, the schema and the result, never your tables, so there is less to pay for and less to make up.
The figures are one live enterprise grocery deployment, not a benchmark. We do not name the operator.
The model orchestrates. The lake computes and verifies.
| Job | Done by | Why |
|---|---|---|
| Read the question | The model | Language is what models are for. |
| Write the queries | The model, in Ward’s JSON format | Structured output the lake can validate before it runs. |
| Compute every figure | Ward’s data lake | Exact, cheap, and nothing for a model to invent. |
| Check every figure | Ward, before the answer returns | Valid data, efficient query, answers the question. Failures loop back. |
| Write the answer | The model, around computed figures | Each figure stays a citation linked to its rows. |
| Decide who sees what | Cedar policy, below the model | No prompt can widen it. Access control → |
You choose the model providers, and a policy decides who may change them. The model receives the question, the schema it needs and query results the asking user may see, never your tables.
Your cloud, ours, or on-prem.
Isolated per tenant
Customer data is physically separated per tenant. Only schemas and settings are separated in the application.
Inside your account
Ward runs next to your systems, so the proxy reaches your replicas without leaving your network.
Including air-gapped
Runs with no outbound connection, on scheduled updates you bring in.
Not shipped yet, and labelled that way.
What reviewers ask about the architecture.
Not your live databases. They connect through Ward's proxy and are joined in place, so a read-only replica is enough and nothing is moved. Sources that are not databases, like exports, Stripe, logs and PDFs, sync into Ward's data lake. You choose per source.
Parquet-based columnar storage on a custom fork of Apache DataFusion, with Ward's own index format for lookups and query planning, and partitioning and clustering on the same table.
Live databases are as fresh as the replica Ward reads. Synced sources land by batch, micro-batch or streaming, and streaming rows are queryable the moment they arrive.
One live enterprise grocery deployment queries 5 TB and 5B records on a 16 GB server, and is heading toward 100B records. That is a deployment, not a benchmark.
Your cloud, Ward's, or on-prem, including air-gapped deployments with scheduled updates. In Ward's cloud, customer data is physically isolated per tenant.
You do. Ward offers starter schemas for common sources if you want a head start, and nothing about your schema is locked to Ward.
Where to go from here.
The proof chain
Hover a figure in a sample answer and see its rows, its query and its checks.
Try it →Access control for data and agents
Row and column policy, agents that inherit the user, and an access log with reasons.
Read it →The data lake
Ward's own engine, query in place or sync, and what it reads.
Read it →Free to deploy, 5% of model spend
Verification is included. Setup is one-time, from $0.
See the numbers →Send this to whoever will review it.
Then connect one read-only source and check the first figure yourself.
Read-only to start · your LLM keys · SOC 2 Type II underway · or book a call directly
Find out what your data has been hiding.
Tell us about your operation. We’ll show you the problems Ward catches, and the ones your current tools miss.