Inspectial

Pre-launch. Onboarding drainage pilot teams.

From site visit to agent-ready inspection data, done by AI.

Inspectial's AI turns field photos, video, voice and GPS into structured, evidence-linked inspection data. A qualified reviewer approves every finding, and the result is data your GIS, asset systems and AI agents can use directly, not a PDF.

Capture in the field. AI structures the evidence. A human approves. Your systems and agents take it from there.

See how it works

Capture in the field. Review from any desk.

Field app preview: a map of today's route with culvert markers by inspection status, working offline, with culvert C-1046 selected and ready to inspect.

Field app preview. In development, for iOS and Android.

Product preview: a web map of the Route 12 drainage project, with stacks of geotagged field photos pinned at each culvert site and a sidebar listing each site's review status.

The site visit is the quick part. The paperwork is not.

A single culvert visit comes back as a pile of loose evidence. Someone in the office then sorts it, matches it to the asset, codes each defect by hand, writes the report, and updates the GIS.

Field work and office work stay disconnected, and the condition data your asset system needs is the last thing to get done. What finally comes out is usually a PDF or a spreadsheet: something a person can read, but that your GIS, your asset system and any AI agent can't use without someone re-keying it.

  • Photosabout 35
  • Video clipsinlet, barrel, outlet
  • Voice and text notesunstructured
  • GPS and the previous inspectionin separate places
Then, by handcoding, report writing, GIS updates

Every photo becomes a record that people can read and agents can use.

An inspector in a hi-vis vest and hard hat crouches beside a concrete culvert and photographs its circular barrel opening with a phone. Water runs out over the invert onto a gravel apron.
Culvert C-104249.1231, 16.4561 · drainage pack
  • Headwall · surfaceweatheringAI suggested
  • Barrel · surfacestainingAI suggested
  • Barrel · vegetationmoss at wall baseAI suggested
  • Outlet · flowclearHuman verified
  • Channel · sedimentloose stones (possible)AI suggested
  • Wing wall · surfaceno defects visibleHuman verified
Evidence IMG_4821 (photo), IMG_4822 · Confidence 0.91
{
  "asset": "C-1042",
  "location": [49.1231, 16.4561],
  "headwall": {
    "surface": "weathering",
    "status": "ai_suggested"
  },
  "barrel": {
    "surface": "staining",
    "vegetation": "moss at wall base",
    "status": "ai_suggested"
  },
  "outlet": {
    "flow": "clear",
    "status": "human_verified"
  },
  "channel": {
    "sediment": "loose stones (possible)",
    "status": "ai_suggested"
  },
  "wing_wall": {
    "surface": "no defects visible",
    "status": "human_verified"
  },
  "evidence": ["IMG_4821", "IMG_4822"],
  "confidence": 0.91
}
The numbered boxes on the photo map to the observations in the record, and every value links back to the evidence it came from.

How it works

One workflow from the site visit to the asset system. AI does the coding; people make the call.

  1. Capture offline, with location

    The field app guides the inspector through the required evidence: photos, video, voice and notes. Each item is stamped with time, GPS and asset ID. No signal needed; it syncs later.

  2. AI structures the evidence

    Evidence is grouped by asset and component, and turned into structured observations: defect type, severity, confidence, and the evidence each one came from.

  3. A reviewer approves

    An engineer checks each finding next to its photos, then approves, edits or rejects it. The record always shows what the AI suggested and what a person verified.

  4. Hand off to your systems and agents

    Approved data goes out as GeoJSON, CSV, a PDF report or through the API, into the GIS and asset tools you already use, and into AI agents and automations that need reliable, structured inputs.

AI creates the inspection record, not just the report

Keep your ArcGIS or asset system. We automate the inspection-coding layer in front of it, under rules you can trust.

Agent-ready data, not documents
The structured dataset is the source of truth, so your GIS, scripts and AI agents read it directly. Reports are generated from approved observations, never written straight from the media.
Evidence first
Every observation references the photos, clips or notes behind it. A finding never exists only as an AI sentence.
A human approves
AI proposes; a qualified person decides. Inspectial is not an autonomous inspector, and only approved inspections become official records. Every value is tagged with who stands behind it, so agents know what to trust.
Location is first-class
Evidence, observations and assets carry coordinates, so the output drops onto a map without cleanup.
Offline-first
The full capture flow works in a ditch with no signal. Data syncs when the connection returns.
Configurable, not custom-built
A new inspection type is a template: evidence checklist, observation schema, AI rules and report format. Not a new app.

Who it's for

Anyone who captures photo or video evidence in the field and has to write it up afterwards. We're starting with drainage.

Drainage and culvert inspection contractorsYou already have crews, cameras and reporting workflows. Inspectial is designed to cut the time spent coding footage and writing reports.
Municipalities and counties with small GIS teamsGet condition data that lands in your GIS without someone re-keying it.
Road maintenance contractorsInspect long runs of structures along a route, with status and priority per asset.

Inspection packs

  1. Culverts and drainagePilot
  2. BridgesComing
  3. Utility polesComing
  4. RoofsComing
  5. Construction QAComing

Outputs and integrations

Inspectial feeds the tools you already run. It doesn't ask you to move your asset data anywhere. And because the output is structured, evidence-linked data rather than a document, it also works as input for AI agents and automations.

Works with

  • ArcGIS
  • QGIS
  • PostGIS
  • MapLibre

Formats

  • GeoJSON
  • CSV
  • PDF
  • REST API
  • Excelplanned
  • Shapefileplanned
  • GeoPackageplanned

Join the pilot

We're onboarding a small number of drainage inspection teams for a pilot. Tell us what you inspect, roughly how many structures a year, and which GIS or asset system you report into.

  • Bring real inspections: photos, video and the reports you wrote from them.
  • We set up a drainage template that matches your existing condition codes.
  • You review the AI's structured output against your own findings.
  • Exports arrive as GeoJSON, CSV or PDF, or through the API, in the format you need.