Every answer shows its work.
Ward connects read-only to the systems you already run. Every figure in an answer links to the row it came from, and Ward checks it before you see it.
Store #37 showing 4.2% shrinkage vs 1.8% estate average. Pattern suggests receiving dock discrepancy, not shoplifting.
- Valid data
- Efficient query
- Answers the question
- 01Rows compress into the lake
- 02Agents scan, the index skips the rest
- 03A finding
- 04The proof chain checks it
- 05Sent to the team that acts
Sample grocery dataset. Team boards stand in for the project tool your team already uses.
Hover any number. See where it came from.
Every number a business acts on should be provable. Teams lose weeks arguing over whose figure is right, and that time belongs to deciding what to do. So a figure in a Ward answer is a citation, not text. It links to its source rows and its query, and it passed three checks before the answer came back.
Dairy gross margin fell to this week, from the week before. Most of the drop is shrink at Store #37, which ran against a estate average. Receiving logged short at the dock across four deliveries, so the cause looks like receiving, not theft.
-
1Source rowsstoreskunet salescost3741022 Whole milk 1 gal$4.29$3.315241870 Greek yogurt 32 oz$5.99$4.48
-
2Query
- from
- transactions, item_costs
- filter
- department = dairy · week 45
- group
- none
- measure
- (net sales − cost) ÷ net sales
-
3Checks
- Valid data1.84M rows, no nulls in cost, week 45 complete
- Efficient queryRead 1 of 52 week partitions
- Answers the questionMargin for dairy, this week: matches the question
-
1Source rowsstoreskunet salescost3741022 Whole milk 1 gal$4.29$3.271440115 Butter 1 lb$4.79$3.52
-
2Query
- from
- transactions, item_costs
- filter
- department = dairy · week 44
- group
- none
- measure
- (net sales − cost) ÷ net sales
-
3Checks
- Valid data1.79M rows, week 44 complete
- Efficient queryRead 1 of 52 week partitions
- Answers the questionThe comparison week the answer names
-
1Source rowsstoreskureasonunits3741022 Whole milk 1 galshrink−183741870 Greek yogurt 32 ozshrink−11
-
2Query
- from
- inventory_adjustments
- filter
- store = 37 · department = dairy · week 45
- group
- store
- measure
- shrink units ÷ received units
-
3Checks
- Valid dataAdjustment reasons all in the shrink code set
- Efficient queryClustered on store, so one store read is one range
- Answers the questionStore-level shrink, the figure the answer cites
-
1Source rowsstoreskureasonunits1440115 Butter 1 lbshrink−45241022 Whole milk 1 galshrink−6
-
2Query
- from
- inventory_adjustments
- filter
- department = dairy · week 45
- group
- none
- measure
- shrink units ÷ received units
-
3Checks
- Valid dataEvery store reported for week 45
- Efficient queryRead 1 of 52 week partitions
- Answers the questionSame measure as Store #37, so the two compare
-
1Source rowsPOdeliveryorderedreceived918274Tue 06:1014096918390Thu 05:5512081
-
2Query
- from
- goods_receipts, purchase_orders
- filter
- plant = 37 · department = dairy · week 45
- group
- delivery
- measure
- ordered − received, in cases
-
3ChecksAttempt 1 rejected on efficient query. It read every plant's receipts for the year. Ward rewrote it with plant and week filters and ran the checks again.
- Valid dataEvery receipt joins to a PO
- Efficient queryRewritten with plant and week filters
- Answers the questionShortfall at the dock, which is what the answer claims
Valid data
The rows exist, the types match the measure, and the window is the one asked about.
Efficient query
The query uses the partitions and indexes it should. A full scan where a filter would do is rejected.
Answers the question
The result is checked against what was asked. A correct number for a different question does not pass.
It loops back
A failed check is not shown to you as a warning. The query is rewritten and checked again, and only a figure that passes all three is returned.
“What did the Easter promo do at Store #52?”
I can't answer that from what is connected. Store #52 has no promo calendar rows before March, so there is no Easter window to measure. Try one of these:
No guess. A dead end comes back as the next question.
Ask across every system you run. Move nothing to do it.
Live databases connect through Ward’s proxy and are joined where they sit, so a read-only replica is all Ward needs. Sources that are not databases, like exports, Stripe, logs and PDFs, sync into the lake. Query in place or sync: your choice, per source.
FreshnessSynced sources land by batch, micro-batch or streaming. Streaming rows are queryable the moment they arrive.
Compressed for the compute bill. Built so the model never does the math.
Most AI analysts hand a model a pile of rows and hope the arithmetic holds. Ward’s own data lake runs every calculation and hands the model the result. Smaller context means a smaller model bill, and less for the model to make up.
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 above are one live enterprise grocery deployment, not a benchmark. The full architecture, for the people who will review it →
An agent sees what the person who runs it can see. Nothing more.
Access is written as row- and column-level policy and applied on every query, below the model, so no prompt can widen it. People and agents answer to the same rules, and every read is logged with the reason it was allowed or denied.
One log for people and agents. The second line is the same agent, the same person, one column further, and the policy that stopped it.
A data lake and an AI analyst, for anything that sells.
Six parts, each usable on its own. Connects read-only, and runs in your cloud, ours, or on-prem.
Data lake
Its own engine. Query in place or sync.
Ward's own data lake engine: columnar, indexed, partitioned and clustered, with live databases joined in place.
Read more →Connectors
540 sources. Read-only by default.
Managed ingestion from warehouses, lakes, SaaS APIs, databases and flat files.
Read more →Semantic layer
One definition of revenue. Enforced.
Metrics, dimensions and grain defined once and enforced everywhere, including in what agents are allowed to compute.
Read more →Agent runtime
The warden of your data and your agents.
Agents on your own data that run with the permissions of the person who starts them, with every access logged.
Read more →Query and chat
Ask in English. Every answer shows its work.
Natural language across every source, with each figure linked to its query and source rows.
Read more →Governance
The answers your security review needs.
Row- and column-level policies applied in real time, per-tenant isolation, and one access log for people and agents.
Read more →One take, from an empty source list to a model in the graph.
Recorded against a running tenant. Nothing is sped up and nothing is cut except the login screen.
One enterprise deployment, and the arithmetic behind the rest.
What is running and what is modelled sit in separate boxes, so you can judge each on its own.
Live against POS, ERP and inventory.
Ingestion, the data lake and the reasoning on top, running on production systems. Stockouts, shrink, fill rate and assortment are where it starts, because that is where the dollars are.
We do not name operators or publish their numbers without permission. Reference calls get arranged while you are still evaluating. How the engagement is going →
Where 200 basis points would come from.
Four signals, worked out for a mid-market multi-store estate. Nobody has booked a dollar of it yet.
Retail is where Ward is deployed, not what Ward is. The retail build →
Ward is built on a platform these nine companies already run in production. They use the platform, not Ward.
Already evaluating something else?
Each page gives the other product its credit first, then answers the same question both ways with the proof chain visible.
Free to deploy. The number is on the page.
- Every connector and the semantic layer
- Unlimited agents and users
- Row and column policies, access log, SSO
- Proof chain checks on every answer
- Each call goes to the cheapest model that clears the bar
- Per-message cost on every answer
- Budgets and hard caps per department and user
- The only recurring fee Ward charges
- Self-guided: $0
- Guided, two weeks: $7,500
- Managed, six weeks: $20,000
- Program, multi-entity: from $50,000
Verification is included. Every figure is checked on a small context window, so the checking adds little to the model bill. No seats, no license, no annual plan. How the 5% is metered, and the setup packages with a named engineer, are on the pricing page.
What a technical evaluation asks first.
The model never does the math. It turns your question into queries and writes the answer, and Ward's data lake computes every figure. Each figure in the answer is a citation linked to its query and source rows, and it is checked three ways before the answer returns: the data is valid, the query is efficient, and the result answers the question asked. A figure that fails is not shown with a warning. The query is rewritten and checked again. When the data is too thin to answer, Ward says so and suggests questions it can answer.
Very little. Verification is included, and because the lake computes the figures, the model works on small context windows: the question, the schema it needs and the query results, never your tables. That keeps both the answer and the checking cheap. You pay 5% of the model compute that routes through Ward, on your own provider keys, and nothing per check.
You choose the model providers, and a policy decides who is allowed to change them. What a model sees is limited by the same row- and column-level policies as the person asking: it receives query results that person is allowed to see, never whole tables. Routing specific tasks to specific models is on the roadmap.
Nothing to deploy. The console, every connector, every agent and every user are free. Ward bills 5% of the model compute that routes through it, metered on your own provider keys, and that is the only recurring fee. Setup is a one-time package if you want a named engineer for training and guidance, and the smallest one is $0. There is no license and nothing is priced per seat.
No. Live databases connect through Ward's proxy and are joined in place, so a read-only replica is all Ward needs and nothing is moved. Sources that are not databases, like exports, Stripe, logs and PDFs, sync into Ward's data lake. Query in place or sync: your choice, per source. Revoking the credential returns you to exactly where you started.
Depends what you run today. Ward includes ingestion, its own data lake engine, transformation, the semantic layer, query and chat, and agents under policy, so the first things teams retire are usually a managed pipeline tool and a separate metrics layer. Columnar storage with its own indexes keeps compute small: one live deployment queries 5 TB and 5B records on a 16 GB server. It does not replace your source systems, your CDP or your data science platform.
What the person who runs it can reach, and no more. Agents run with the permissions of the user who starts them, under the same row- and column-level Cedar policies, applied in real time below the model, so a crafted instruction cannot widen them. Every access is logged with the policy that allowed or denied it.
Only with an explicit grant, per table and per action, and you can require a human approval on each one. Findings are routed to the team that acts on them, awaiting approval, rather than acted on silently. Read-only is the default and most teams never leave it.
Where you choose: your cloud, ours, or on-prem, including air-gapped deployments with scheduled updates. In Ward's cloud, customer data is physically isolated per tenant; only schemas and settings are separated in the application. Sign-in is SSO through your OpenID Connect provider.
Connect one source and see what comes back.
Read-only, and nothing migrates. Hover the first number Ward gives you and check it yourself. Deploying is free; you pay 5% of the model compute it uses.
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.