Platform

Architecture & Security

Local-first by construction. The product runs entirely on the engineer's machine, and its services are reachable only from the machine itself — nothing is exposed to your network beyond what you configure. Specs, programs, boards and STDF stay local; the only network egress is the prompts the engineer chooses to send to their own LLM provider, on their own keys — and the payload is inspectable before it goes.

01

Everything on the host

ATE·IQ is a desktop product that happens to be built from web technology, not a cloud product with a desktop wrapper. One install serves both the standalone IDE window and the Excel task pane, from the same local server.

ENGINEER'S MACHINE — EVERYTHING RUNS LOCALLY DESKTOP IDE standalone window · system tray EXCEL task pane · live bridge PROJECT DATA specs · programs · boards · STDF one install same projects, same data LLM PROVIDER customer's choice prompts the only egress — on the customer's keys code, specs, boards and STDF stay on the machine — the only egress is the prompts the engineer chooses to send
Fig. 1 — The whole platform on one machine. The IDE and the Excel task pane are one install working the same project data; one labelled arrow crosses the boundary.

The desktop shell sits in the system tray and registers the Office add-in. Closing the main window hides to the tray rather than shutting the product down, so the Excel task pane keeps working. The task pane and the IDE are the same install and the same database — a workbook ingested from Excel is immediately part of the project the IDE sees.

02

Background work, visible faults

Long-running work — test-program generation, code-map indexing, document and board ingest — runs in the background without blocking the app. The scheduling underneath is deliberately conservative: a failure is retried, and work that still fails is surfaced with its error rather than dropped silently; work interrupted by a crash is recovered on restart, not lost. The in-app status bar watches the platform's health continuously, so a stalled pipeline is a visible fault, not a mystery.

03

Bring your own LLM

ATE·IQ ships no model and holds no keys of its own. The customer configures a provider, supplies their own credentials, and every AI feature routes through that choice — which means the customer's existing egress policy and data agreement with their provider apply unchanged.

ProviderConfiguration
Anthropic Direct API with the customer's key.
OpenAI-compatible Any endpoint speaking the OpenAI API — hosted, or a self-hosted gateway inside the customer's network, via a configurable base URL.
Azure OpenAI Endpoint, deployment and API version — for organisations whose model access is already contracted through Azure.

The provider is switchable at runtime from Settings — no reinstall. And what goes to the provider is not a mystery: the Context Curator shows the exact assembled payload — every artefact, every score — before a query is sent. AI is also optional per feature: the validators, analyzers, DIB checker, STDF tools and traceability reconciles are deterministic and run with no provider configured at all.

04

Security posture

ControlImplementation
Network exposure Local-only by design — services are reachable only from the machine itself, and nothing is exposed to your network beyond what you configure. There is no cloud component and no telemetry.
Credentials at rest LLM API keys and Git personal-access tokens are encrypted at rest — never stored in plain text.
Excel bridge The live-workbook bridge requires a shared secret on every request, generated locally on first run — a request without it is refused.
Workbook file reads Workbook access is constrained to the user profile and OneDrive roots and to .xlsm/.xlam extensions — it cannot be used to read arbitrary files.
API authentication Every page and every API surface authenticates the caller in its own right, and the product's internal calls are authenticated as well — there is no unauthenticated back door between components.
05

Proven end to end

Every screenshot in this guide was produced on a single Windows workstation: the demonstration spec, the 34-test program, the five-sheet board, the routed copper and the eight STDF lots all live in the local database, and the analyzers, validators, DRC and traceability reconciles that judged them ran without a network connection. The only traffic that left the machine during the build was the generation and chat prompts sent to the configured provider — the same payloads the curator preview displays.

Honest boundary Today's install is developer-grade — it expects Docker and Node.js on the machine, with the database in a local container. The delivery direction is a packaged single Windows executable with an embedded data store, removing those prerequisites. That is the direction of travel, not a dated commitment.