NEO PI
NEO PI captures, contextualizes and preserves every reading from every sensor, machine and piece of equipment on the plant floor — and gives that history back as a single source of truth, queryable and auditable.


Key capabilities
NEO PI is not a sensor database. It is your plant’s memory: what happened, when, at what measurement quality, and under which process asset.
The name is no accident. NEO PI plays the same role a classic process information system plays in a plant — with one difference: it was born to operate inside a regulated ecosystem, integrated with the electronic batch record.
See it running
A walkthrough of the console: live dashboard, asset navigation, trends and audit trail.
Connections
When the format is proprietary: codecs
Not every manufacturer follows a standard. A codec is a declarative expression that translates a vendor’s raw payload into measurements — configured through the interface, tested before saving, with an AI-assisted draft from a sample payload. In practice: equipment sending {"temp_raw":247} starts recording 24.7 °C without a line of code and without waiting for a release.
Data goes out too: forwarding
Forwarding rules deliver readings to external systems by webhook (HMAC-signed, token-authenticated) or MQTT publication, with optional payload transformation, batched delivery, a durable retry queue and automatic shutoff when a destination keeps failing.
Context, not an identifier
Navigate by plant › area › asset instead of by a raw device identifier. Every element carries its live measurements, its properties and its permissions.

Overlaid trends
Several sensors on the same chart over any date range, with aggregations from raw to monthly and CSV export.

Integration with NEO EBR
The electronic batch record drives production: procedures, work orders, in-process controls. Historically, process values reach that record by manual transcription — an operator reads the display and types. That is simultaneously the slowest and the most fragile step of the record: subject to misreading, typing errors and delay, and it demands second-person review precisely because of that.
With NEO PI, the value comes from the historian:
- the in-process control in NEO EBR reads the measurement directly from the corresponding asset in PI
- the value arrives with its origin timestamp and quality, not the time someone typed it
- the batch record points to immutable data, traceable back to the raw event
- out-of-range deviations stand out against the full history, not an isolated point
EBR consumes PI through the Read API: a navigable namespace (site/area/asset/measurement), current-value reads, history queries with aggregations, and live event subscription over SSE — all authenticated by scoped read keys that limit each consumer to exactly the assets and measurements it should see.
That API is an open protocol, and nothing about it is NEO-specific. NEO W&D reads dispensing weights from it the same way, and any third-party system — MES, LIMS, ERP, a BI tool — consumes it over plain REST and SSE. PI is a layer your plant owns, not a captive component of one suite.
How the data flows
Data enters through any of the protocols, is preserved raw, gains asset context in the Asset Framework, and leaves by three paths.
- Machines and PLCsreactors · lines · filling — OPC-UA, OPC-DA
- Equipmentcold rooms · autoclaves · stability chambers — LoRaWAN
- IoT deviceswireless sensors · gateways — MQTT, HTTP, codecs
- Ingestionraw preserved, immutable
- Time seriestag catalog · aggregations
- Asset Framework / UNSsite › area › asset › measurement
- NEO EBRbatch record — Read API, scoped key
- NEO W&Dweighing and dispensing — same open API
- Operations and Qualitytrends · investigation
- Third-party systemsMES · LIMS · ERP · BI — REST, SSE, forwarding
What each team gains
- Immutable, permanent raw dataThe original event is never deleted or edited. Any number on screen traces back to what the device actually sent.
- Hash-chained audit trailConfiguration changes are recorded in a chain with integrity verification — retroactive tampering is detectable.
- Electronic signature (21 CFR Part 11)On sensitive operations, with a signing PIN distinct from the login password and a meaning declared at the moment of signing.
- Real real-timeReadings appear as they arrive, with no page reload.
- Failure recoveryEvents that could not be decoded stay visible and can be reprocessed after the fix — nothing is lost silently.
- Role-based permissionsWith roles the organization customizes itself.
- No rip-and-replaceFive native protocols plus codecs for everything else.
- No lock-inData leaves by API, forwarding and live subscription — PI is a layer, not a final destination.
- Unified Namespace alignedISA-95 / IEC-62264: semantic hierarchy, current state, event-driven ingestion and decoupled publication. Container deployment, multi-architecture.
- Less manual transcriptionIn the batch record — fewer errors, less rework, less review time.
- Shorter deviation investigationsHistory is contextualized and available, not scattered across dataloggers and spreadsheets.
- A base for what comes nextContinuous monitoring, trend analysis and process alarms finally have somewhere to read from.