# Clarify: ask your data, check the answer

Clarify (formerly DotPlot) is a product from Dscvry (https://dscvryai.com/). People ask questions of enterprise data in everyday language and get answers with their sources, within the access they already have.

- Live demo (no sign-up, fictional company; starts with a choice of who you are): https://clarify.dscvryai.com/demo/
- Start a pilot: https://clarify.dscvryai.com/pilot/
- Clarify on dscvryai.com: https://dscvryai.com/technology/products/clarify/

## The problem: insight locked in dashboards

- Analyst bottleneck: every new question becomes a request, and the request waits.
- 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

- Ask: questions in everyday language, with follow-ups ("only AW26", "break it down by factory").
- Permissions: governance-aware access controls; an answer only draws on data the person asking may see.
- Sources: each answer shows the rows, filters and tables behind it, so it can be checked rather than trusted.
- Beyond dashboards: answers directly, with a chart drawn from the query result; recurring questions can be pinned to a board that re-runs them.

## How Clarify answers: language on top, exact queries underneath

1. Question (understand): asked in everyday language.
2. Access check (rules and code): only data this person may see.
3. Query (rules and code): exact queries against the data.
4. Answer (reasoning): written from the query results.
5. Sources (rules and code): rows, filters and tables attached.

The numbers are computed by queries, not written by a model. Clarify is not retrieval-augmented generation (RAG): it does not search documents and pass passages to a model.

Illustrative example (fictional): "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.

## Use cases

- Stock shortages: what runs out before the next delivery? https://dscvryai.com/use-cases/stock-shortages/
- Contract compliance: did they deliver what the contract says? https://dscvryai.com/use-cases/contract-compliance/
- Regulatory changes: what does this new rule change for us? https://dscvryai.com/use-cases/regulatory-changes/
- Revenue leakage: what should we have charged? https://dscvryai.com/use-cases/revenue-leakage/
- Maintenance planning: https://dscvryai.com/use-cases/maintenance-planning/

## Real work of this kind

- Apparel, South Asia, global: order-book questions answered in under 60 seconds, previously ~3 days.
- Capital programmes, UK: answers to project-controls questions, linked to source records.

## Deployment

Hosted, public cloud, private cloud / VPC, on-premise, edge, offline, air-gapped.

## Security

Dscvry is SOC 2 Type II and ISO/IEC 27001:2022 certified: https://dscvryai.com/security/