Onboarding Successful

Your AI Advisor for Niagara license has been activated. Follow the steps below to get up and running.

Install Modules

Copy all JAR modules into your Niagara modules folder. The archive contains:

  • aiCore-rt.jar
  • aiAdvisor-wb.jar
  • aiEngine.jar
  • bdrtLicense-rt.jar
  • bdrtLicense-wb.jar

Move all JAR files to your Niagara modules folder, e.g.:

C:\Niagara\Niagara-<version>\modules

Restart both the Workbench and station after copying the files, as the list of modules is read at startup.

Install License

  1. Open your station in Workbench
  2. Navigate to Config > Services
  3. Open the AI Advisor palette and drag LicenseService into the Services folder
  4. Open the LicenseService and set Online to true
  5. The License field will populate with your active license

Note: Use the Recheck action on the LicenseService to force an immediate online license check.

Install AI Advisor

With modules installed and the license active, complete the AI Advisor setup:

  1. Install Java — Install JDK 25 if not already present: Windows x64 (.msi) | Linux x64 (.tar.gz)
  2. Add AI Advisor Service — Add AI Advisor service to your station
  3. Configure JDK Path (only if empty) — The system attempts to auto-detect your JDK. If AiAdvisorService > Ai Engine > Executable is empty, set the Java executable path manually
  4. Add API Key — Configure at least one provider API key in Api Keys
  5. Select Provider/Model — Set Configuration > Provider and Model (default: openai / gpt-5.4)
  6. Restart AI Engine — Right-click the Ai Engine property and select (Re)Start Process
  7. Configure Navigation File — Set Configuration > Navigation File to your .nav file (default: ^NavFile.nav)
  8. Configure User Profile — Set the user's web profile to Ai Html Profile
  9. Access Chat — Log out and back in (the new web profile only applies on a fresh login), then open the station in your browser. You should see the chat button in the bottom-right corner
  10. Run /init — First send a quick "hi" in the chat; a reply confirms everything is working. Then type /init once — the AI reviews your station and builds a station.md profile so future answers are more accurate. You only need to do this once

Next steps

After /init, click the + (new chat) button and try some real questions:

  • "What equipment do I have?"
  • "Show me AHU-1 point values"
  • "Show me alarms from the last 24 hours"

When a new AI Advisor release is published, follow this short process to upgrade an existing installation.

Replace Modules

Copy the new JAR files into your Niagara modules folder, overwriting the previous versions:

  • aiCore-rt.jar
  • aiAdvisor-wb.jar
  • aiEngine.jar
  • bdrtLicense-rt.jar
  • bdrtLicense-wb.jar

Move all JAR files to your Niagara modules folder, e.g.:

C:\Niagara\Niagara-<version>\modules

Restart the station so Niagara picks up the new module versions.

Reset Defaults

  1. Right-click AiAdvisorService and invoke the Reset Defaults action (you will be asked to confirm)
  2. This restores ^ai/application.yml, ^ai/prompt.md, ^ai/chat-config.js, ^ai/style.css, and the default Tools folder to the new release's defaults
  3. The AI Engine restarts automatically. If it does not, right-click Ai Engine > (Re)Start Process

Note: That's it for the common case.

If You Customised Config Files

Reset Defaults overwrites ^ai/application.yml, ^ai/prompt.md, ^ai/chat-config.js, and ^ai/style.css. If you have edited any of these (for example custom timeouts, an extra agent, a tweaked system prompt), do this before Reset Defaults:

  1. Open the file and copy your custom values somewhere safe (or save the file under another name)
  2. Run Reset Defaults as normal
  3. Re-apply your edits to the freshly reset file
  4. Right-click Ai Engine > (Re)Start Process to load your edits

If you have not customised any of those files, skip this section — there is nothing to back up.

After the Upgrade

Re-run /init in chat if the new release changed prompt.md, the default tools, or get_navigation behaviour — the release notes will say. Otherwise your existing ^ai/station.md is still valid.

AI Advisor 1.0.30

Covers all changes since 1.0.22.

New features

  • Azure OpenAI provider — Configuration > Provider now offers OpenAI, Anthropic, Google, Ollama, and Azure OpenAI. Pick the provider and model on the property sheet; no application.yml editing required.
  • Always-fresh query data (live subscription) — BQL queries used by both the chat tools and the dashboard pipelines now detect stale proxy-point values, subscribe to those points to force the driver to re-poll, wait for fresh readings, then return. Previously a query could hand the assistant stale values, because resolving BQL alone does not trigger station subscription. The assistant and dashboards now act on current data.
  • Node Manager dashboard — seven example pipelines — the dashboard now ships with seven worked examples instead of three:
    • ForgottenOverrides, AlarmPatterns, NetworkHealth — work on any station, no configuration required.
    • Air Handling Unit AHU1 [CONF], Electric Meter QUPSB [CONF], Chiller CH1 [CONF], Overall System Summary [CONF] — per-equipment and whole-building pipelines driven by domain-expert prompts (HVAC, electrical, refrigeration, building-supervisor).
    • Pipelines whose name ends in [CONF] must be pointed at your own equipment before use — each one's Description block lists exactly which query ORD and alarm-source filter to change. Duplicate a [CONF] pipeline once per piece of equipment you want to monitor.

Improvements

  • Rate-limit aware dashboard — when an AI node hits a provider rate limit, the dashboard queue pauses instead of hammering the API, then resumes — avoiding cascade failures and wasted calls.
  • Broader JDK auto-detection — the AI Engine launcher now finds Adoptium, Microsoft, Semeru, and Azul/Zulu JDKs (in addition to the previous set), so the engine starts reliably across more host configurations.
  • Licensing in the palette — a LicenseService now ships as part of the AI Advisor palette, so licensing drops in with the rest of the service.
  • User guide overhaul — restructured sections, a single per-model table, an Ollama setup chapter, an AI Pipelines (Node Manager) chapter, and a proper PDF (title page + table of contents).

Bug fixes

  • Fixed a station NullPointerException hang.
  • Fixed a license-fetch deadlock.
  • Fixed the thinking indicator not clearing during tool calls.
  • Fixed Hx profile CSS leaking into the host page.
  • Various fixes — internal reliability work (Fox connection-registry and login-pipeline refactors, an RPC bridge for integrations) plus assorted stability and correctness fixes.

AI Advisor 1.0.22

New features

  • Simplified upgrade process — from 1.0.22 onward, every upgrade is the same three steps: (1) replace the JARs, (2) restart station + Workbench, (3) right-click AiAdvisorService > Reset Defaults. No more property-type migrations or manual prompt copy-paste.
  • /init station profiler — run /init in chat once after install (or after major navigation-file changes). The init agent surveys your station and writes a profile to ^ai/station.md that is auto-injected into every assistant request. Makes answers dramatically more accurate, faster, and cheaper.
  • Node Manager dashboard — proactive station monitoring with AI pipelines. Pipelines run on schedule and surface as RAG (Red/Amber/Green) status cards on a single dashboard view. Ships with three example pipelines (BooleanOverrides, AlarmPatterns, NetworkHealth); supports user-defined pipelines for any use case. More out-of-the-box pipelines coming in upcoming releases.

Improvements

  • Provider and Model moved to the property sheet — previously edited in ^ai/application.yml; now live on Configuration > Provider (OpenAI / Anthropic / Google / Ollama — new) and Configuration > Model.
  • Navigation file property moved — was Tools > nav_tree > Query; is now Configuration > Navigation File. The nav_tree tool itself was removed and replaced by a smarter navigation tool that handles large stations.
  • Tool results paginate automatically — fixes truncation/timeout problems on large stations.
  • Reset Defaults moved and renamed — was Configuration > forceDefaultConfig; is now AiAdvisorService > Reset Defaults. One click restores all ^ai/* config files, repopulates Tools, and restarts the AI Engine.
  • Better debugging via conversation logs — logs now under ^ai/conversations/, tagged by agent, with tool-call results visible in summary mode. Configurable in application.yml (off / summary / full).
  • System prompt moved to a file — edit ^ai/prompt.md in any text editor instead of a giant property-sheet field.
  • Longer chat memory — assistant remembers more of the conversation before older messages drop off.

Bug fixes

  • Various stability and correctness fixes across navigation, query handling, and chat sessions.
Generating download link…
User Guide (PDF)

← Back to Baudrate