VisionQ

Work around the products

Four areas of engagement, each built on a product in the portfolio. Each is described the way the products are: what it starts from, what it covers, what it ends with, and where it stops.

Vision system engineering

Inspection programs built on VisionAI. The work starts from the quality question and ends with a program the line runs.

Starts fromA quality question, and a job that takes its image from a camera or an uploaded file.
CoversThe vision tasks the job runs (find circle, find line, find angle, find distance, code and character reading, anomaly, classification), the region of the image each task reads, and the pass-or-fail logic over the measurements they return.
Ends withA program the operator triggers. A run shows the verdict, the per-task results and the overlay that marks where each measurement was taken, and the program exports and imports as a unit, so what was tuned in the editor is what runs.
Where it stopsVisionAI's deep-learning tools are deterministic stubs today, so an engagement that needs a trained model is scoped together with the model lifecycle work below.

Model lifecycle

Training, evaluation and ONNX export on VisionML, ending in a manifest that records what was made.

Starts fromA dataset whose layout is validated before a run, with duplicate images across train and test flagged.
CoversTraining, evaluation and export, and the manifest fields a consumer depends on: the artifact's sha256, the preprocessing recipe, the decision thresholds, the provenance (dataset hash, seeds, framework versions), parity evidence between the training framework and the ONNX runtime, and the pinned runtime contract.
Ends withA registered model, or a refusal. Registration compares the configured acceptance criteria with the measured metrics, and every registration is appended to an audit log.
Where it stopsA criterion that was not measured fails closed, and a model registers only with passing parity evidence unless a waiver is recorded in its manifest.

Edge and fleet deployment

Putting inspection software on plant hardware, and knowing what each device is running.

Starts fromA hardware profile. VisionEdgeOS is a product-image family on a supported upstream Linux rather than a distribution of its own, with versioned profiles that carry an explicit lifecycle (experimental, supported, qualified, retired).
CoversImage and profile work on VisionEdgeOS, and on the operations side VisionFleet: where each commissioned device is assigned, its health and open incidents, and the exact operating-system, application, runtime, model, manifest, firmware and driver versions and digests it reports.
Ends withA fleet whose drift is visible: what was intended against what is observed, as a rollout progresses.
Where it stopsA profile counts as qualified only after tests on its physical hardware, and virtual-machine or CI results count as development evidence only. Both repositories state their own status, design and scaffolding for one and a development-only increment for the other, and the status ledger on this site quotes them. Work here is profile, image and verification-harness work scoped against that status, not a production rollout.

Laboratory evidence software and validation support

Bench capture and assisted counting with Digital Labs, with human review as the boundary.

Starts fromA capture that records the task, the sample, the model package that would run and where it would run, and every outcome, including an abstain, a capture-gate failure and the case where no approved model exists.
CoversAssisted counting: a run proposes editable per-object detections and refuses to give a number outside the method's countable window, and a person accepts, corrects or rejects each result before a session can pass completeness review. The accepted or corrected value is what the step records.
Ends withA versioned evidence package handed to the system that owns the record, with a receipt from it. The product is designed to leave the laboratory's own systems in charge.
Where it stopsThe software is not a validated record system and makes no compliance claim. Where a deployment is regulated, the engagement extends to what the product's own architecture says a validated profile needs beyond the software (intended use, risk assessment, validation plan and evidence, configuration control, procedures and training), prepared with the people who own the process.

No engagement described here implies a customer, a price, an availability date, or a compliance status. What a specific deployment would need is decided with the people who own the process.

If one of these is close to what you need, describe the problem and we will say what it would take.

claudio@dantonoli.com

No form, no tracker. Mail goes straight to the person who built these products.

Write to VisionQ