ABOUT DIAGVANCE

Built to Make HVAC
Diagnosis More Intelligent

Turning scattered fault codes, service data and manufacturer documentation into structured, traceable diagnostic intelligence, so technicians reach the right next test faster.

Diagvance is building an AI-assisted HVAC diagnostic system that combines manufacturer knowledge, field data, sensor measurements and technician verification.

Manufacturer KnowledgeField DataSensor MeasurementsTechnician Verification

The Problem

Why Diagvance Exists

HVAC is not short on technical knowledge. It is short on knowledge that is easy to reach at the moment of diagnosis.

What a technician needs is spread across manuals, fault-code tables, bulletins and service histories. The rest lives in the heads of experienced technicians and rarely transfers across a team.

Diagvance is being built to make that knowledge structured, traceable and usable during diagnosis. We do not claim that all HVAC knowledge is in the system today.

Where diagnostic knowledge lives today

Service manualsInstallation manualsFault-code tablesTechnical bulletinsService historiesMeasurementsTechnician experience
↓
Goal
One structured, source-linked diagnostic record the technician can use on the call.
Lennox gas furnace on a residential service call
“

A fault code tells you where the control gave up. It does not always tell you why, or what to test next.

What technicians face on a call
Incomplete work orders, codes without context, pressure to diagnose fast, scattered manuals, repeat visits, and knowledge that lives in one person's head.

The Founder's Perspective

Built from Real HVAC Experience, Not Just Software

Diagvance started from direct experience with HVAC service, troubleshooting and field workflows, not from a software idea looking for a market.

Founder Masoud Aghighi has hands-on HVAC/R experience and builds from the technician's side of the call. The goal is not to impress with AI. It is to give a technician a clearer starting point and a better next test.

Our Diagnostic Philosophy

Built on Evidence, Not AI Guesswork

Manufacturer facts, field observations and AI reasoning are different kinds of information. The system is designed to keep them apart and traceable.

01

Official Manufacturer Documentation

Source Fact
02

Structured Diagnostic Knowledge

Source Fact
03

Field Data & Observations

Field Data
04

AI Reasoning

Inference
05

Next-Test Guidance

Suggestion
06

Technician Verification

Human Decision

Manufacturer Facts

Stay traceable to their original source.

Traceability

Source document, model, control revision and page are kept.

Fact vs. Inference

Facts, field data and AI reasoning are never mixed.

Uncertainty

Confidence is shown, not hidden.

Technician in the Loop

AI suggests the next test. The technician decides.

Furnace control board and wiring harness

Source Traceability

What a Structured Record Keeps

Each diagnostic record is designed to carry its own provenance, so a technician can see what a statement is based on and which equipment it applies to.

Illustrative structure only. Not an excerpt from the Diagvance database.

fault_code: example code
fact: manufacturer's stated meaning Source Fact
source: official service manual, section / page
applies_to: model family · control board revision
field_checks: technician measurements Field Data
likely_causes: ranked, with confidence Inference
verified_by: technician Human

The Platform

What We Are Building

Not a chatbot and not a fault-code lookup. A connected system that links fault codes, service data, manufacturer knowledge and next-test guidance.

Working System

AI-Assisted Diagnostics

Turns symptoms, fault codes and measurements into a structured brief. Outputs are ranked suggestions for a qualified technician, never a final diagnosis.

Brief layout (illustrative)
Fault code meaningmanufacturer source
Likely fault areasranked, with confidence
Next testfirst check to run on site

Service Request Triage

Customer symptoms turned into useful information before arrival.

Working System

Technician Briefs

Likely fault areas and next checks by text or email.

Working System

Structured Fault Knowledge

Manufacturer fault data in a source-linked structure.

In Development

Field Measurement Layer

Technician readings and service history to confirm the diagnosis.

Research Direction

Methodology

How We Validate Diagnostic Knowledge

Our working method, shown honestly. It is not a formal certification, third-party validation or peer-reviewed process.

STEP 01

Source

Start from official manufacturer documentation.

STEP 02

Structure

Convert it into consistent records, keeping provenance.

STEP 03

Separate

Keep facts, field observations and inference distinct.

STEP 04

Cross-Check

Review model applicability, conflicts and gaps.

STEP 05

Test

Run it against realistic troubleshooting scenarios.

STEP 06

Human Review

Critical logic is reviewed before production use.

Where This Is Heading

Development Roadmap

A structured path, from diagnostic intelligence, to real field data, to a deployable HVAC diagnostic platform. This shows direction, not finished capabilities.

Phase 1

Build the Intelligence

Build a structured HVAC diagnostic knowledge layer using verified OEM information, fault codes, troubleshooting logic, field evidence, and technician knowledge.

OEM informationFault codesTroubleshooting logic
Phase 2

Connect the Field

Introduce technician measurements, equipment data, technician inputs, and guided diagnostic testing to connect the diagnostic intelligence with real HVAC systems.

Technician measurementsEquipment dataGuided testing
Phase 3

Deploy the Platform

Bring the diagnostic intelligence into technician workflows, service operations, integrations, and real HVAC company environments.

Technician workflowsService operationsIntegrations

Long-Term Vision

Where We Are Going

A capable HVAC diagnostic intelligence layer that brings together the evidence a technician already depends on, and tracks where each piece came from.

Manufacturer knowledgeFault codesEquipment identityTechnician observationsSensor dataMeasurementsService historyField validation
From

“What might be wrong?”

Toward

“What evidence do we have, what is most likely, and what should we test next?”

The Person Behind Diagvance

Meet the Founder

Masoud Aghighi, founder of Diagvance, on a furnace service call

Masoud Aghighi

Founder, Diagvance · Vancouver, BC

HVAC/R technician and diagnostic technology builder combining field experience, structured technical knowledge and AI-assisted troubleshooting.

Connect on LinkedIn

See What We’re Building

Explore the diagnostic approach or talk to us about a demo. Feedback from technicians and service teams shapes what gets built next.

© 2026 Diagvance | Data Security | Pilot | Pricing | Contact