Open Platform · 28+ Standards

The European standard for visual inspection AI

An open, schema-driven platform for building inspection and grading software. 28+ industry standards built in — and a framework for any standard you need.

Schema-drivenStandards-basedOpen API
The Problem

Why inspection AI hasn't scaled

The industry keeps rebuilding the same foundation. We built it once, properly.

Inspection is fragmented

Every industry builds custom tools from scratch. No shared infrastructure.

Standards exist on paper

PSA, NEN 2767, FHWA NBI — real grading standards locked in PDFs, not APIs.

AI without trust

Black-box scoring that auditors can't verify and professionals won't adopt.

Platform

One platform, any inspection vertical

Six composable primitives form the foundation. Build any inspection workflow from the same set of building blocks.

01

Verticals

Define the industry domain — retail, infrastructure, collectibles, and more.

02

Grading Schemas

Encode real standards into structured, version-controlled scoring rules.

03

Catalog

Register the objects you inspect — products, assets, specimens.

04

Observations

Capture structured field data — photos, measurements, annotations.

05

CV Jobs

Run computer vision pipelines — detection, segmentation, grading.

06

Inspections

Produce auditable inspection reports with full provenance.

Schema-drivenStandards-basedTransparent
For Developers

SDK-first. Always.

Every feature we ship lands in the SDK before it reaches our own products. If we can build on it, so can you.

inspection.ts
1import { KliqAI } from '@kliq-ai/sdk';
2
3const kliq = new KliqAI({ apiKey: process.env.KLIQ_API_KEY });
4
5// Define a vertical
6const vertical = await kliq.verticals.create({
7 name: 'bridge-inspection',
8 standard: 'FHWA_NBI',
9});
10
11// Create a grading schema
12const schema = await kliq.schemas.create({
13 verticalId: vertical.id,
14 grades: ['Good', 'Fair', 'Poor', 'Severe'],
15 formula: 'weighted_average',
16});
17
18// Run an inspection
19const inspection = await kliq.inspections.run({
20 schemaId: schema.id,
21 images: ['s3://bucket/bridge-deck-01.jpg'],
22});
23
24console.log(inspection.grade); // "Fair"
25console.log(inspection.auditUrl); // Full provenance

TypeScript & Python SDKs

First-class client libraries with full type safety.

OpenAPI spec

Auto-generated docs. Import into Postman, generate clients.

Webhook events

Real-time notifications for inspection lifecycle events.

Full audit trail

Every decision logged with timestamps and provenance.

Read the docs
Trust

Trust through transparency

Inspection professionals need to trust AI before they adopt it. We earn that trust by making everything visible.

Human-in-the-loop by default

AI proposes grades. Humans approve, override, or escalate. Every decision is recorded with who made it and why.

Open grading schemas

No hidden scoring. Every grading schema is inspectable, versioned, and exportable. What you see is what gets applied.

Deterministic formulas

Given the same inputs, you get the same grade. Every time. No stochastic surprises in production.

Full audit trail

From photo capture to final grade — every step is logged with timestamps, model versions, and human decisions.

Build the next standard

Start with our SDK, define your grading schemas, and ship production inspection software.