2026 Roadmap

Our Transformation Journey

A phased approach to building the future of industrial analytics - from licensed tools to AI-first platform

2026 North Star

By end of 2026, your company runs a single internal "Industrial Data + AI Platform" where:

  • PI is a data source, not "the product"
  • SWAPP becomes the default workbench (explore - trend - stats - ppm - insights)
  • AI is embedded in every workflow (search, analysis, root cause, report, automation)
  • Scadanerve proves a PI alternative path (sensors - agents - open time-series)
Strategy

Portfolio Logic

How our projects fit together in a layered architecture

1

Connectivity & Extraction (Foundation)

piwebapi: stable, secure, scalable PI extraction API

pipolars: high-performance dataframe layer (Polars) + domain helpers

2

Product Platform (Work App + Extension system)

swapp (core): auth, navigation, permissions, workspaces, saved views, audit, API gateway

swapp.explorer: AF explorer, asset hierarchy, attribute discovery, tag/point finder

3

Replacing licensed "apps" with modules

swapp.trend: TrendMiner-like UX + context charts + event overlays + smart comparisons

swapp.stats: Minitab-like guided stats + DOE-lite + capability + hypothesis tests

swapp.ppm: legacy PPM workflows (KPIs, availability, heat rate, alarms, tickets)

4

Strategic independence (PI alternative path)

scadanerve: sensors-to-agents pipeline (OPC UA/Modbus/MQTT - historian - feature store - agents)

Timeline

Quarter-by-Quarter Roadmap

Detailed deliverables and success metrics for each phase

Q1

Platform Skeleton + Trust

January - March 2026

Goal: Make PI data reliably usable via your own APIs, with security & governance.

piwebapi v1

  • Minimal API service, pagination, caching, retry/backoff, throttling
  • Standard endpoints: points, summaries, recorded, interpolated, metadata, AF mapping
  • Observability: logs/metrics/traces + SLIs (latency, error rate)

pipolars v1

  • read_pi() and read_af() wrappers returning Polars LazyFrames
  • Time zone handling, resampling, interpolation, quality flags, unit normalization
  • "Industrial transforms": rolling stats, event windows, downtime masks

SWAPP core (MVP shell)

  • SSO/auth, role-based access, workspace concept, saved queries, export
  • Extension framework skeleton (how trend/stats/ppm plug in)

AI baseline

  • "Data Copilot v0": natural language - PI query builder (safe, explainable)
  • Prompt + template repo (versioned), usage logging, red-teaming basics

Success Metrics

  • 5-10 critical tags/AF elements served reliably through piwebapi
  • <1% failed requests on normal load
  • First SWAPP users can browse assets and pull timeseries without PI UI
Q2

Explorer + Trend as Daily Driver

April - June 2026

Goal: Deliver the first "daily driver" replacement use-cases (trend + exploration).

swapp.explorer v1

  • AF tree browsing, favorites, search, attribute/element compare
  • "Open in Trend" & "Open in Stats" deep links

swapp.trend v1

  • TrendMiner-like UX: multi-tag plots, time shift compare, overlays, annotations
  • Context layers: alarms/events/maintenance windows
  • Team sharing: "saved views", comments, snapshot links

AI inside Trend

  • Auto-insight: "what changed?" (change-point detection + narrative)
  • "Explain this trend": generates hypotheses + shows supporting evidence links

Success Metrics

  • 50-150 recurring internal users (operations/performance)
  • SWAPP Trend used in at least 3 recurring meetings (daily/weekly)
  • 20% less dependency on licensed trending tool for pilot plants
Q3

Stats + PPM Slice

July - September 2026

Goal: Replace the "analysis workbench" and connect to business workflows.

swapp.stats v1

  • Guided analysis flows: correlation, regression, outliers, distributions
  • Capability & control charts where relevant
  • Notebook-like "analysis recipes" saved as reusable templates

swapp.ppm v1 (slice)

  • 1-2 high-value PPM workflows: Unit KPI dashboard (availability, efficiency, heat rate, curtailment)
  • Loss accounting / performance deviations
  • Integrate maintenance/ticket references (even if read-only initially)

AI inside Stats & PPM

  • "Ask the dataset" (RAG over metadata + safe compute functions)
  • Auto-generated reports (weekly plant summary) with citations to charts/queries

Success Metrics

  • One "Minitab-like" flow fully adopted by performance engineers
  • At least one monthly report generated primarily from SWAPP
  • Clear business KPI improvements (hours saved / faster RCA)
Q4

Scale + Scadanerve Pilot

October - December 2026

Goal: Harden the platform, scale adoption, and prove strategic optionality beyond PI.

Platform hardening

  • Multi-plant scaling, tenant boundaries, cost controls, strong auditing
  • Data governance: catalog, lineage, classification, retention rules
  • MLOps/LLMOps: model registry, evaluation harness, prompt/version governance

Scadanerve pilot (real plant slice)

  • Edge ingestion: OPC UA/Modbus - MQTT/streaming
  • Open historian/time-series store + AF-like asset model (your "open AF")
  • Agent layer: anomaly detection + alert explanation + recommended actions
  • "Bridge mode": Scadanerve and PI side-by-side to prove parity & value

Commercialization readiness

  • Packaging SWAPP as internal product: onboarding, documentation, SLA, support

Success Metrics

  • SWAPP is default interface for at least one technology fleet (e.g., wind or hydro)
  • Scadanerve shows a working pipeline from sensors to insights without PI UI
  • Vendor/license dependency risk reduced (measured, not just claimed)
AI Strategy

AI-First Capabilities

What "AI-first" means in SWAPP - implemented in three tiers

Tier A

Assist

Fast wins
  • NL - query builder (PI/AF search, time windows, summaries)
  • Auto chart descriptions + anomaly highlights
  • "Explain differences" between periods/plants/units
Tier B

Analyze

Repeatable intelligence
  • Root cause assistant: hypothesis generation + evidence scoring
  • Pattern library: recurring failure signatures (vibration, stator temp drift, etc.)
  • Automated feature extraction pipelines (pipolars recipes)
Tier C

Act

Agents with guardrails
  • Ticket drafts, recommended checks, suggested setpoint investigations
  • Runbooks: "if X then do Y" with human approval gates
  • Continuous monitoring agents per asset class
Governance

Phase Gates

Key decision points tied to outcomes

End Q2 Gate

Explorer + Trend adopted by pilot plants; 50+ recurring users; clear productivity gains documented

End Q3 Gate

Stats workflows in use; at least one PPM dashboard live; one monthly report generated from SWAPP

End Q4 Gate

Multi-plant scaling proven; Scadanerve pilot running in bridge mode; governance/audit controls active

Ready to Join the Journey?

Get in touch to learn how SWAPP can transform your industrial data operations

Explore Modules View Architecture