Use this resource hub to explore MLdeck's public guides, example workflows, documentation, video channel, and company channels. The focus is practical CSV-based machine learning: browser-local AutoML, Data Quality review, validation evidence, ONNX-oriented export packages, and no raw CSV upload during normal browser-local workflows.
MLdeck suits browser-local CSV exploration, review, and teaching. Each situation below is about exploration and review — not a guarantee of a production-ready or compliant outcome. Using MLdeck does not establish regulatory compliance and is not a substitute for external validation before high-stakes decisions.
When a CSV should be reviewed carefully before it leaves your environment, browser-local training keeps raw CSV rows in the browser during normal training flows. This supports early internal review; it is not a compliance claim, and your own data-governance obligations still apply. See Privacy-first AutoML and AutoML without uploading data.
Go from a CSV to a compared set of candidate models in the browser without provisioning infrastructure or a Python environment — useful for quick, early evaluation. See Train ML models in your browser and Browser-based AutoML.
Profile a CSV, pick a target, compare models, and review warnings through a visual workflow — no pip, virtual environments, or notebooks required to start. See Local AutoML for CSV files and CSV Data Quality Checker.
Point learners to MLdeck: they open it, sign in where required, load their own approved dataset, and then train or review it in the browser — with no lab setup. Sharing an MLdeck link does not share or open a dataset; each learner loads their own. A low-friction way to teach CSV modeling and data-quality concepts. See the training workflow and data quality checks.
Explore internal KPIs, sales, or operational CSVs and export supported artifacts for internal review and runtime testing. Treat results as exploratory evidence to validate, not as finished decisions. See AutoML export artifacts and Data Quality.
Sanity-check features and model families quickly before committing to a heavier stack. MLdeck surfaces baselines, warnings, and validation evidence, but final validation remains your responsibility. See AutoML validation evidence and Export ONNX models from the browser.
Learn how MLdeck keeps the normal CSV modeling loop in the browser while making validation and export responsibilities visible.
Compare the browser-based user experience with the browser-local training boundary for practical CSV workflows.
See the training workflow from CSV review to model comparison, validation evidence, and export artifact context.
Review the normal browser-local workflow scope and the user-side responsibilities that still apply.
Check missing values, schema signals, risky columns, and CSV readiness before reporting, sharing, cleanup, or AutoML.
Understand why missing values, leakage risk, identifiers, high cardinality, imbalance, and sample limits matter before training.
Read a practical example of Data Quality review before interpreting AutoML metrics or export readiness.
Learn how to interpret exploratory metrics, holdouts, baselines, leakage review, reports, and user-side verification.
Compare local-first exploration with managed cloud workflows, including privacy, setup, validation, and export responsibilities.
Review reports, manifest-driven package concepts, ONNX-oriented artifacts, and external verification responsibilities.
Understand how browser-local training can lead to ONNX-oriented export packages for external testing and verification.
Follow an example workflow from CSV training to schema review, parity checks, and export artifact testing.
See how numeric target selection, feature review, mean baseline comparison, and export context fit a regression workflow.
Review a tabular classification example using audio-feature CSV data, leakage checks, baselines, and validation context.
Explore a practical churn workflow with browser-local AutoML, feature review, Data Quality warnings, and exportable artifacts.
Use the public repository for MLdeck documentation, examples, privacy notes, validation notes, and public link maps.
Read the public documentation page that explains the browser-local AutoML positioning and boundaries.
Review public documentation for CSV Data Quality concepts and how they connect to MLdeck website guidance.
Connect website export artifact guidance with the public documentation repo's export-artifact notes.
Use the channel for planned demos covering browser-local AutoML, Data Quality review, validation evidence, and export artifacts.
This guide is the matching website page for a planned video showing how to train a machine learning model in the browser.
Follow product updates and educational posts about privacy-first CSV workflows, validation evidence, and export readiness.
Use the public documentation repo as the safe public source for docs, examples, and link maps.
Watch for public walkthroughs and demos that match the website's educational resource cluster.