Inside the Dashboard: Charlie Cochrane’s AI-Powered Batch Update, Ontology & Point Mapping for Building Integrators

What does the Device and Point Ontology workflow do?

Building data is only useful if it’s structured correctly, and that’s still one of the biggest problems in smart buildings today. Devices come in with inconsistent naming, unorganized point structures, and little standardization across systems. Before teams can build analytics, automate workflows, or deploy AI, someone usually has to spend hours, sometimes weeks, manually tagging and organizing data.

That process does not scale.

The Device and Point Ontology workflow in KODE OS turns one of the slowest parts of deployment, structuring raw device and point data, into one of the fastest.

Once a data source is connected, users land directly in the Devices page, where all discovered equipment is centralized. From there, ontology classes, area mapping, and point-level classification can all be applied in bulk, with AI assisting at the point level.

Instead of organizing equipment one point at a time, teams can structure entire systems in minutes, with a standardized device and point model ready for analytics, automation, and operational workflows from day one.

How can I use it?

The workflow is designed to mirror how deployment teams actually bring buildings online, moving from discovery to structured, trended data without manual cleanup work.

Here’s how the workflow operates inside KODE OS:

Land directly in your Devices page after discovery

Every piece of discovered equipment appears in one centralized view, ready for classification and organization.

Filter and select equipment in bulk

Charlie filters the device table down to all VAVs in the system, selects them simultaneously, and opens batch update instead of configuring devices individually.

Apply ontology classes at scale

Inside batch update, ontology classes such as VAV can be applied across every selected device at once.

Map devices to areas in the same step

Devices can also be mapped to physical areas like Floor 1 or a specific building zone, so location context is built into the system immediately.

Use AI to map points automatically

Inside Model Devices, users can multi-select points and apply AI Suggest.

Instead of manually identifying every sensor, command, or status point, KODE OS analyzes:

• Point names
• Values
• Behavioral patterns

The platform then automatically assigns the correct ontology structure to each point.

Validate immediately

Once mapping is complete, teams can jump directly into any device and begin trending points immediately using clean, organized device-level data.

There is no separate cleanup phase before the system becomes usable.

The deployment workflow becomes repeatable, scalable, and consistent enough to support portfolio-wide rollouts instead of one-building-at-a-time deployments.

Batch updating device ontology

Traditionally, assigning ontology classes and organizing devices into areas has been a repetitive manual task.

KODE OS removes that friction.

After filtering down to a specific device family on the Devices page, Charlie selects every VAV simultaneously and opens batch update. From there, ontology classes and area assignments can be applied across all selected devices in one workflow.

Instead of manually tagging devices one-by-one, hundreds of devices can be standardized in seconds.

That operational consistency matters.

When every VAV, AHU, or meter follows the same structure across buildings, teams can:

• Benchmark systems consistently
• Deploy portfolio-wide logic faster
• Standardize reporting
• Scale analytics across sites
• Troubleshoot equipment without rebuilding data structures building by building

Without standardized ontology, operations stay fragmented.

AI-assisted point mapping

Device-level classification is only half the challenge. The real complexity exists at the point level, where devices expose dozens of values with inconsistent naming conventions.

Inside the Model Devices workflow, Charlie multi-selects points within those VAVs and applies AI Suggest.

Instead of manually identifying every point, KODE OS evaluates:

• Point naming
• Point values
• Behavioral patterns

The platform then automatically assigns the appropriate ontology structure.

The result is structured, standardized data without the manual overhead typically associated with large-scale integrations.

For deployment teams, this removes one of the most time-consuming parts of bringing buildings online.

Once ontology mapping is complete, teams can immediately validate devices and start interacting with live data. Charlie jumps directly into a device and begins trending points with organized visibility already in place.

That matters because structured data is what enables everything that comes next:

• Reliable analytics
• Faster troubleshooting
• Consistent portfolio reporting
• Scalable automation
• AI-ready operational workflows

Why this matters

Most platforms treat ontology as a separate manual project outside the deployment process.

KODE OS treats it as part of deployment itself, accelerated through batch actions and AI-assisted workflows.

That difference changes deployment speed in a meaningful way:

• No manual point-by-point tagging
• No inconsistent ontology between buildings
• No long gap between discovery and a usable system

As buildings scale, manual data structuring becomes a bottleneck. It slows deployments, creates inconsistencies, and makes portfolio-wide standardization difficult.

KODE OS reduces that overhead by combining:

• Batch device updates
• Area mapping
• AI-assisted point classification
• Immediate validation workflows

The result is faster deployment, cleaner operational data, and systems that are ready for analytics and automation significantly earlier in the process.

For enterprise portfolios, that speed compounds quickly.

One structured workflow replaces hundreds of repetitive actions, and every building that comes online does so with the same standardized model underneath it.

See it in action

From batch device updates to AI-assisted point mapping, this workflow is what enables rapid deployment inside KODE OS.

In this edition of Inside the Dashboard, Charlie walks through how teams classify devices, map them to areas, and standardize point-level ontology in just a few clicks.

If you want to learn more about how KODE OS structures building data in minutes instead of weeks, making systems usable faster without the traditional deployment overhead, let’s connect on LinkedIn or book a demo with our team.