Analyst bottleneck.
Every new question becomes a request, and the request waits.
Insight locked in dashboards.
The answers exist in the data, but getting them means a dashboard only analysts can use, or a request that waits days in a queue.
Dashboards answer yesterday's questions.
They show what someone decided to chart, not what you need to know now.
Access gets in the way.
Opening the data to more people risks showing them what they shouldn't see.
What it does.
One question, one answer you can open: the figures, a chart, the list behind it, and every step that produced it.
Ask
People ask what they need to know in everyday language, and follow up the way they would with a colleague: “only AW26”, “break it down by factory”.
See it in the demo →Permissions
Governance-aware access controls mean an answer only draws on data the person asking is allowed to see. Ask the same question as two people and see two answers.
See it in the demo →Sources
Each answer shows the rows, filters and tables behind it, so it can be checked rather than trusted. Click a number and land on the query cell it came from.
See it in the demo →Beyond dashboards
Business users get answers directly, with a chart drawn from the result, instead of waiting for an analyst to build or change a dashboard. Pin the questions you ask every week to a board that re-runs them.
See it in the demo →Language on top. Exact queries underneath.
The question is understood by a model; the answer comes from exact queries against governed data, so the numbers are computed, not written.
- 01QuestionUnderstand
Asked in everyday language.
- 02Access checkRules & code
Only data this person may see.
- 03QueryRules & code
Exact queries against the data.
- 04AnswerReasoning
Written from the query results.
- 05SourcesRules & code
Rows, filters and tables attached.
A number you can open and check
- Asked.
- Which open orders ship late against the promised date?
- Checked.
- Order book and shipments allowed; price lists skipped for this user.
- Queried.
- Open orders where the projected ship date is after the promised date.
- Answered.
- 214 orders, most in AW26 for the EU, with the list attached.
Illustrative example. Orders, seasons and figures are fictional.
Not retrieval. Clarify does not search documents and pass passages to a model to write a number. Every figure in an answer is a cell from a query result, and the demo shows you which one.
Where it shows up.
Problems that start with a question nobody can answer fast. Each one is a question you can ask in the demo.
Stock shortages
Anticipate shortages before they become a problem, and see which orders they put at risk.
Ask it in the demo → The use case ↗Contract compliance
See whether obligations were actually met: prices billed against prices agreed, terms, renewals.
Ask it in the demo → The use case ↗Regulatory changes
Map new rules to what the business must change: the styles and open orders each rule reaches.
Ask it in the demo → The use case ↗Revenue leakage
Find money that should have been charged: shipments not invoiced and discounts beyond contract.
Ask it in the demo → The use case ↗Maintenance planning
Service due dates next to the order load each factory has to carry, with a warning when a feed is stale.
Ask it in the demo → The use case ↗The executive briefing
Order book, late orders, on-time delivery, leakage, shortages and machine service in one answer, each number traceable.
Ask it in the demo →Real work of this kind.
Engagements where questions were answered directly from the source records.
Apparel · South Asia, global.
Order-book questions answered in under 60 seconds, previously ~3 days.
Financial control ↗Capital programmes · UK.
Answers to project-controls questions, linked to source records.
The full record ↗Within your boundary.
Runs in your environment, from managed cloud to air-gapped.
- Hosted
- Public cloud
- Private cloud / VPC
- On-premise
- Edge
- Offline
- Air-gapped
Questions.
The short answers. For anything else, start a pilot and ask us.
What is Clarify?
Clarify, formerly DotPlot, is a product from Dscvry that lets people ask questions of enterprise data in everyday language and get answers with their sources, within the access they already have.
Does it replace our dashboards?
It answers the questions dashboards don't: the new ones people would otherwise send to an analyst and wait for. Each answer comes with a chart drawn from the query result, and questions you ask every week can be pinned to a board that re-runs them, so nobody has to build or maintain a dashboard for them.
Can the model make up a number?
No figure is written by the model. The model works out which question you asked; the numbers come from exact queries against the data, and each one links to the query cell it came from. If Clarify can't answer with a query, it says so instead of guessing.
Is this retrieval-augmented generation (RAG)?
No. Clarify does not search documents and pass passages to a model. It runs exact queries against structured data, within the asker's access, and writes the answer from the results.
How are permissions applied?
The access check runs before any query. An answer only draws on rows and columns the person asking may see; if a question needs data outside their access, nothing runs and Clarify says which data was missing.
Is the demo real data?
No. The company, people, figures and rules are fictional. The queries are real: they run on SQLite inside your browser, and nothing you type is sent anywhere.
How do we start?
Leave your details on the pilot page. We agree the questions and the data to start from, and set it up within your own access rules.
Ask the sample data, then ask yours.
Open the demo and pick who you are, from the chief operating officer to the maintenance lead. When you're ready, run a pilot on your own data.