Product
Sentinel is the layer where your data is connected, understood, watched and acted on, and where a person stays in charge of every consequential step. Most people use the App. The people who own the data build in the Workbench. A business gets a module when a job deserves its own screen.
There is one address, one sign-in with your company account, and one box to type in. If you can write a message, you can use Sentinel. Business people deliver value on their first day, with no data team in the loop.
The left rail is the whole map. New chat asks Mentor anything. Threads are the conversations you share with colleagues and agents. Artifacts are the documents and live dashboards built for you. Workflows are your scheduled reports. Missions are the standing crews and what they need from you.
Quick scan and ratify when you're ready.
Mentor does not recall an answer or summarise a document. It writes and runs queries against your governed data, over millions of rows, and shows the query, the tools and the source. If you doubt a figure, ask for the underlying rows.
Ask for something the data does not support and Mentor says so rather than producing a number.
Top ten vendors by purchase-order spend, last twelve months.
| Rank | Vendor | PO spend |
|---|---|---|
| 1 | Northline Industrial Supply | $1,845,619,827 |
| 2 | Harbor Valve & Fitting | $985,000,000 |
| 3 | Meridian Chemical Co. | $566,511,713 |
| 4 | Castell Logistics | $554,743,395 |
| 5 | Orsa Engineering | $529,966,000 |
Computed from purchase orders in place. Show the rows
A mission is a crew of AI specialists that meets on a schedule, reads its charter, works the data, debates, and votes. They are paid to be critics. Nothing is sent unless the crew agrees a person must act.
Silence is a valid outcome. Most days, that is what you get.
Nothing consequential happens because an agent said so. It waits, with its reasoning attached, for a person to ratify. Every decision links to the meeting that produced it, post by post. Every action is simulated first, then recorded with its cost, its outcome and an undo.
Hold the next cycle on the Line 3 lyophiliser until the port-2 transducer is calibrated.
Port 2 reads above port 1 at steady state, and the offset has grown on each of the last five cycles. Product temperature stayed below the collapse threshold throughout; the batch is releasable. The risk is the next one.
@mention a colleague or an agent in the same sentence. The agent answers with the data, the colleague answers with judgement, and the thread keeps both. When it is resolved, the conclusion is captured into the workspace's knowledge and Mentor can cite it later.
The reasoning behind a decision no longer lives in someone's head or in a chat app nobody can search. It lives next to the data it was about.
Sentinel works from email like a colleague. Forward a question, a supplier email or an attachment to its mailbox; a thread opens, the analysis runs, and the reply lands back in your inbox. Reply to the reply and the thread continues. Anyone on the CC line joins.
The reports your team assembles by hand every week are a workflow. Build it once, in the canvas or by asking Mentor to build it, and it arrives every Monday with the numbers recomputed from the data. An AI reviewer checks a generated report before it is allowed to send; a flawed one is blocked, not delivered.
Every Monday 06:00: results posted in the last 7 days against trend, pulls due in 30 days, chamber excursions. PDF and Excel to the QA leads.
Last run today · successOn batch close: assemble the release pack, review with Mentor, and email QA for sign-off.
Last run today · successDaily 07:00: open deviations older than 30 days grouped by site and owner, posted to the QA thread.
Last run today · successEverything the App shows was built here, by the people who own the data, and everything built here is immediately available to Mentor, to missions and to the App.
Raw data arrives as columns and tags with cryptic names. The element layer turns them into the nouns your business uses — a site, a line, a compressor, a purchase order — and hangs every measurement, event and document on the thing it belongs to. Mentor, missions and modules reason about elements, not columns.
A module is a set of purpose-built pages for one job, running on the same platform: the same data, the same permissions, the same Mentor button on every screen. Ask a question on any tile and the answer comes from the same governed query the tile used.
Built per deployment, in code or with Mentor, and installed per workspace. Anything reusable — a dashboard, a workflow, an agent, a model — is described in plain language, checked against the live catalog before it renders, published once through the Marketplace, and installed elsewhere as a fresh copy.
The business user and the data scientist use the same platform and land in the same place. A model built in a notebook is what Mentor answers with; a workflow built from chat is what the engineer sees on the canvas.
Ask Mentor to build it: a workflow, an alert rule, a live dashboard, a mission, a model. It authors, validates and deploys, and shows you what it made.
Open Studio: Python notebooks in the project's own environment, import sentinel to reach every source directly, scheduled runs, a model registry and pipelines to deploy into.
Connect Visual Studio Code or the editor of your choice and work on the same projects, the same data and the same deploy path, from where you already work.
Sentinel does not replace your systems of record, your warehouse or your BI. It reads them in place and becomes the layer where people and agents act on what they show. Your system of record stays the system of record.
ERPs, CMMS and EAM, MES and LIMS. Historians, SCADA and live signals. Warehouses, lakehouses and data platforms. BOMs, drawings, documents and spreadsheets. Email and attachments. Anything with an API.
Email, chat and meetings. Tickets and work orders. Document systems. Reports as PDF and Excel. Webhooks, storage and transfers. Your own API.
Your own agents connect over MCP as the signed-in user, with that person's permissions. Sentinel's agents reach out through every tool above: simulated first, ledgered, gated by the autonomy you set.
Examples, not a list. Connectors and tools are added per deployment.
If your people already live in Claude, Copilot or ChatGPT, they can keep it. Add Sentinel as a connector and their assistant gains every Sentinel tool — discover sources, query, run recipes, build a dashboard — as that user, with that user's real workspace permissions.
One product, one codebase. It runs inside your own network, in a private cloud, or hosted by Wonder DataLabs. Nothing about the features depends on where it sits, only on where your data is allowed to be.
The audit log, the ledger and every thread live with the deployment.
Autonomy is earned in layers, and every layer is visible. Each mission has a ceiling; anything past it waits for a person. Every action an agent takes is simulated first, then recorded with its cost, its outcome and an undo where the tool allows one.
Everything on this page runs on the same platform. The practical next step is a conversation about which data you want answerable first.