Pre-launch · design-partner pilots open for 2027Synthetic defects · edge inspection · NVIDIA stackApply for the pilot

Pilora · QA copilot

From a flagged frame to a likely cause

Pilora reads defect events from Veridex and writes them up in plain language, routes borderline calls, and looks across shift, batch and process data for what changed upstream.

Specification

Inputs
Veridex defect events and frames; MES and historian telemetry
Models
Vision-language and language models customized with NVIDIA NeMo
Serving
NIM and Triton with TensorRT-LLM; on-premises option on IGX (planned)
Guardrails
NeMo Guardrails; answers cite the events they use
Capabilities

What Pilora does

  1. 01

    Plain-language defect reports

    Type, severity, location and probable cause for each flagged frame or cluster.

    Core
  2. 02

    Borderline calls routed

    Auto-pass, auto-reject or human review, with every routing decision logged.

    Core
  3. 03

    Looks upstream

    Correlates defect clusters with SKU, shift, batch, lighting and process telemetry.

    Core
  4. 04

    Corrective suggestions

    Recommends what to check and alerts on trends before they become escapes.

    Core
  5. 05

    Questions in plain words

    Ask about defect trends across lines and plants and get answers grounded in your data.

    Core
  6. 06

    Drift triggers retraining

    Detects drift and proposes a Coreon retrain for approval (planned).

    Planned
Example output

What Pilora produces

Pilora reportExample

Scratch cluster on AX-204, Line A

Window
Shift B, 14:00–16:00
Rejects
23 scratches
Location
Top face, near slot
Correlates with
Fixture 4 change at 13:40
Confidence
Medium

Suggested action. Inspect fixture 4 clamp pads for debris. Scratch position matches the clamp contact area.

Needs engineer reviewReview
Example report. Events, times and the suggested cause are illustrative.
How it works

Inside Pilora

  1. ST-01

    Collect

    Defect events and frames arrive from Veridex.

  2. ST-02

    Ground

    Process data and past reports are retrieved.

  3. ST-03

    Reason

    A vision-language model drafts the report.

  4. ST-04

    Review

    An engineer confirms or corrects it.

Specification

Specification

Items marked planned are in design with pilot partners.

ItemDetail
InputsVeridex defect events and frames; MES and historian telemetry
ModelsVision-language and language models customized with NVIDIA NeMo
ServingNIM and Triton with TensorRT-LLM; on-premises option on IGX (planned)
GuardrailsNeMo Guardrails; answers cite the events they use
OutputsDefect reports, triage decisions, root-cause suggestions, alerts
StatusAgentic root-cause analysis is in design with pilot partners (planned)
Questions

About Pilora

Does Pilora make decisions on its own?

Only the ones you allow. Triage rules are set by your engineers, and root-cause suggestions always need a person to act.

Will it make things up?

Answers are grounded in your inspection and process data and cite the events they rely on. If the data does not support an answer, Pilora says so.

Which process data can it use?

Anything you connect: MES, historian tags, maintenance logs. Pilots usually start with shift and batch data.

Next step

Try Pilora on one SKU

Pilots start with one part, one defect list and accuracy measured on real frames.