Operational and industrial workflows
Operus
Ask your operational data a question. Get a checked answer.
Operus gives operations teams a secure natural-language interface to production databases and ERP-connected data. It turns questions into validated, permission-aware queries, recurring reports, and decision flows without code.
Demonstration
Demo with synthetic data
A planner asks a question in plain language. Operus writes and checks the SQL, runs it, and shows the flagged products on a control chart.
All names, values, and records in this demonstration are invented. It illustrates the workflow and is not a screenshot of a deployed system.
Operus
Conceptual demo, synthetic dataNumbers come from the database, not from the language model.
Which products had abnormal scrap rates this week?
How the answer was built
Question understood
Scrap rate this week, compared with each product’s own baseline
Schema read
quality.weekly_scrap_vs_baseline, production.products
SQL generated
SELECT product_code, plant, scrap_rate, baseline_12w, z_score FROM quality.weekly_scrap_vs_baseline WHERE week = '2026-W37' AND plant IN ('A', 'B', 'C') AND z_score >= 3 ORDER BY z_score DESC;Validated
Scope and permissions checked before running
- Read-only
- Plants A to C only
- Role: quality planner
Ran on the database
0.4 s, 214 products checked, 3 rows
Result
The answer appears here once the query has run.
3 of 214 products are 3σ or more above their 12-week baseline. PX-2210 in Plant B has the largest deviation.
- Products checked
- 214
- Flagged
- 3
- Plants
- A to C
3σ band around the 12-week baselineBaseline
Flagged products
Select a product to see its chart.
Capabilities
What Operus does today
- 01
Natural language to validated SQL
Questions are translated into scoped SQL that is validated before it runs, not into free-form text answers.
- 02
Schema-aware answers
Schema, metadata, and table relationships inform every answer, so results follow how the data is actually built.
- 03
Permission-aware access
Identity and role context travel end to end. Users only see data their permissions allow.
- 04
Production data orchestration
Built for PostgreSQL and ERP-connected production data, from shop-floor metrics to multi-company visibility.
- 05
Anomaly surfacing
Questions such as “find products with abnormal scrap rates” return the rows, the rule used, and the query.
- 06
Reusable decision flows
Saved queries and reporting flows answer recurring operational questions without rebuilding them each week.
How it works
- 1
Connect
Operus reads schema and metadata from PostgreSQL and ERP-connected sources.
- 2
Ask
A planner asks in plain language: “Show monthly production efficiency by plant.”
- 3
Validate
The question becomes scoped SQL, checked against permissions before it runs.
- 4
Review
Results come back as a table, with the query visible for anyone who wants to check it.
- 5
Automate
Useful questions become saved flows for weekly reviews and executive reporting.
Built for
- Plant and operations managers
- Quality, purchasing, and supply teams
- Group-level leadership across companies
Safeguards
- Deterministic execution: the database computes results and the language model does not invent numbers.
- Read scope and row-level permissions are enforced before a query runs.
- Every answer keeps its query, so results can be audited and reproduced.
- Local or controlled deployment inside the organisation’s infrastructure boundary.
Boundaries
- Operus answers from connected data. It cannot see systems that have not been connected.
- Automated flows recommend and report. Changes to production systems stay with people.
Related reading
Measuring time saved by AI tools
Claims that AI saves hours are easy to make and hard to check. A practical approach to measuring what actually changes before, during, and after rollout.
Connecting AI tools to health records
Most clinical AI projects that stall do so at the interface, not the model. Why integration should be designed first, and what FHIR and SMART on FHIR do and don’t solve.
Request a demo
Request a demo
Operus is already selected. Change it if you’d like to see something else.