ENERGY MONITORING - FULL

Full Track: Meter It All

You chose complete control. Build your energy intelligence from scratch.

This track assumes nothing. You design the metering architecture, create the surface hierarchy, and author every query.

What you will build

Component	Scope
Connections	Building, floor, line and equipment meters
Surfaces	A hierarchy from campus to equipment
Warm queries	An energy analytics library
Team	Access for operations, sustainability and finance
MCP	Any AI client reading the library

Phase 1: Design the metering architecture

Step 1.1: Map your hierarchy

Before creating connections, map what you will monitor:

Campus / Facility
├── Building 1
│   ├── Floor 1
│   │   ├── Production Line A
│   │   └── Production Line B
│   └── Floor 2
│       ├── Office Space
│       └── Data Center
├── Building 2
└── Utilities
    ├── Chiller Plant
    └── Compressed Air

Step 1.2: Identify metering points

Level	Meters	Data
Campus	Main utility meter	Total consumption, demand
Building	Building submeters	Electrical, gas, water
Floor	Distribution panels	Circuit-level consumption
Equipment	Individual meters	Machine-specific usage

Step 1.3: Create connections

Ask Azi in the main panel:

"Create connections for the building meters, the production line submeters, and the chiller plant."

She proposes them. Accept each one, then Deploy: a connection is built, and registered as a device on Fathym's shared IoT hub (or your own, once your workspace has its IoT fabric), only when someone deploys. Each connection's Connection Info tab then shows the credentials your meters or gateway send with.

Phase 2: Create the surface hierarchy

Step 2.1: Campus surface

"Create a surface for campus-wide energy monitoring, fed by every building's meters."

Azi proposes a Campus-Energy surface wired to those connections. Accept it; it is live at once.

Step 2.2: Building surfaces

Surface	Fed by	Purpose
Building-1-Energy	Floor, HVAC and lighting meters	Building breakdown
Building-2-Energy	Production, office, support meters	Building breakdown
Utilities-Energy	Chiller, compressed air, steam	Central utilities

Step 2.3: Production surfaces

Surface	Fed by	Purpose
Line-A-Energy	Motors, conveyors, line HVAC	Line-level allocation
Line-B-Energy	Motors, conveyors, line HVAC	Line-level allocation

Your surface hierarchy decides how finely your queries can break consumption down. Design it to match your reporting.

Phase 3: Build the query library

Query	Purpose	Read
daily-consumption	Daily kWh by building	Daily
monthly-cost	Monthly cost by line	Monthly
peak-demand	Peak demand analysis	On demand
baseline-comparison	Current against baseline	Monthly
sustainability-scope2	Scope 2 emissions	Quarterly

Step 3.1: Daily consumption by building

"Create a warm query for daily electricity consumption broken down by building."

Data
| where EnqueuedTime > ago(30d)
| extend Payload = todynamic(RawData)
| where tostring(Payload.meterType) == "Electric"
| summarize DailyKWh = sum(todouble(Payload.kWh)) by Day = bin(EnqueuedTime, 1d), Building = tostring(Payload.building)
| order by Day asc, Building asc

Step 3.2: Cost allocation by line

"Build a query that allocates this month's energy cost to each production line by its share of consumption."

let Readings = Data
| where EnqueuedTime > ago(30d)
| extend Payload = todynamic(RawData)
| extend Line = tostring(Payload.productionLine), KWh = todouble(Payload.kWh);
let Total = toscalar(Readings | summarize sum(KWh));
Readings
| summarize LineConsumption = sum(KWh) by Line
| extend Percentage = LineConsumption / Total * 100
| extend AllocatedCost = Percentage / 100 * 50000 // monthly energy budget
| order by AllocatedCost desc

Step 3.3: Scope 2 emissions

"Create a query for Scope 2 emissions using our grid emission factor."

Data
| where EnqueuedTime > ago(365d)
| extend Payload = todynamic(RawData)
| where tostring(Payload.meterType) == "Electric"
| summarize TotalKWh = sum(todouble(Payload.kWh)) by Month = startofmonth(EnqueuedTime)
| extend EmissionFactor = 0.42 // kg CO2 per kWh - use your grid's factor
| extend Scope2Tonnes = TotalKWh * EmissionFactor / 1000
| order by Month asc

Phase 4: Give your team access

The owner adds teammates in Workspace -> Team Members: enter their email and click Invite. They are members at once. No AI can invite members, and the role picker in that window is not saved - what a member can change is set by access rights.

Team	What they need
Engineering, IT	Workspace.Deploy to build connections; Workspace.Access.Manage to manage access
Sustainability	Membership: any member can save and accept queries; some changes need a management right (see Permissions)
Finance	An API key from APIs -> API Keys, carrying only the rights its reports need
Operations	Membership, to read the surfaces and queries

Access rights apply to the whole workspace; there is no per-surface permission. See Permissions.

Phase 5: Connect any AI over MCP

The OpenX MCP Server is at https://openx.fathym.com/ox-api/mcp. Sign in through the browser: in Claude.ai or ChatGPT, add a custom connector and paste the URL; for coding agents, run fai mcp install https://openx.fathym.com/ox-api/mcp --name openx and sign in when the browser opens. Setup for each client is in Bring Any AI.

Then ask:

"Which areas have the highest energy intensity, and what's driving it?"

The AI reads your saved queries with call_api. If it wants to build something new, it proposes it with manage_proposals, and a person accepts.

What you built

Component	Count
Connections	5 or more
Surfaces	6 or more
Warm queries	5
Team access	Set
MCP clients	1 or more

Before and after

Before	After
Spreadsheet emissions reports	Saved queries anyone on the team can read
"Trust me" allocations	One allocation query, the same for everyone
Scattered meter data	One workspace, organized by surface

Next steps

If you want to...	Go to...
Try the hybrid track	Hybrid track
See query patterns	Query Patterns
Connect more AI clients	Bring Any AI
Explore manufacturing	Manufacturing