Skip to Content

FAQ

Quick answers to common questions about NEO. Contact support: support@heyneo.so.


Quick Navigation


Getting Started

NEO supports multiple ML domains:

What is NEO and how does it work?

NEO is an autonomous ML agent automating the full pipeline from data to deployment.

Workflow:

  1. Describe your ML task in natural language
  2. Provide data (upload, URL, or cloud)
  3. NEO analyzes data and selects models
  4. Receive production-ready artifacts with documentation

Example Task:

Build a customer churn prediction model using customer_data.csv. Optimize for recall since missing churners is costly.

NEO handles preprocessing, feature engineering, training, evaluation, and artifact generation automatically.

Do I need ML expertise?

No. NEO is designed for all skill levels.

BeginnersML Practitioners
Use task templatesSpecify models/constraints
Step-by-step explanationsAccess detailed reports
Start simple, progressCustomize deployments & evaluation
Describe your business goalModify generated code in VS Code

The key is clear goal description, not prior ML knowledge.

How long does a typical project take?

Task TypeDuration
Simple tabular models15-30 min
Image classification30-60 min
Large datasets (>1GB)1-3 hrs
NLP fine-tuning2-6 hrs
Custom deep learning4-12 hrs

Tip: Start with a small sample, then scale.


Data & File Handling

Supported Formats

FormatUse CasePlatformVS Code
CSVTabular/time series
ParquetLarge datasets
JSONStructured/log data
ImagesCV tasks✅ (50MB)
AudioSpeech/music✅ (50MB)

How do I handle large datasets?

Approach:

  1. Platform – Use cloud storage (S3/GCS/Azure)
  2. Convert to Parquet – Faster processing
  3. Test first – Use 10% sample

File limits:

  • Platform upload: 50MB/file
  • Platform cloud storage: unlimited
  • VS Code: unlimited local files

Does NEO handle missing data?

Yes. Automatic detection and imputation:

Data TypeStrategy
NumericalMean, median, predictive
CategoricalMode, “Unknown”
Time SeriesForward fill, interpolation
AdvancedML-based imputation

Platform Mode vs VS Code Extension

FeaturePlatformVS Code Extension
AccessBrowserVS Code editor
SetupQuick, no installInstall once
DataUpload ≤50MB or cloudLocal + cloud
ArtifactsDownloadableGenerated in workspace
Code EditingView onlyFull IDE + Git
Best ForPrototyping, collaborationCustomization, local dev, large datasets

Which mode should I use?

Platform Mode: Quick results, no setup, collaborative testing

VS Code Extension: Edit code, work with large local files, full IDE features, version control


Task Submission

GoodPoor
Predict customer churn using customer_data.csv (50k rows). Optimize for precision-recall balance.Do some ML with my data

How do I write an effective task?

Include:

  1. Goal – What to predict/classify
  2. Data – Files, size, key columns
  3. Metrics – How to measure success
  4. Context – Business relevance

What metrics should I use?

TaskMetric
RegressionRMSE, MAE, R²
ClassificationAccuracy, F1, AUC-ROC
Time SeriesMAPE, SMAPE, directional
RankingNDCG, MAP, precision@k

Map metrics to business goals:

  • Minimize false positives → precision
  • Catch all fraud → recall
  • Balance speed & accuracy → F1-score

Technical & Security

FeatureDescription
Data EncryptionAt rest & in transit
No SharingNever shared with third parties
Complete ControlDelete or export anytime

Is my data secure?

Platform: Cloud encrypted, deletion on request, no sharing

VS Code: Local files never leave machine, secure cloud access via credentials, full control

Can I see generated code?

Yes, NEO provides:

  • Preprocessing & modeling code
  • Step-by-step notebooks
  • Deployment scripts
  • Documentation & methodology

What if model performance is low?

Improvement:

  1. Improve data quality/features
  2. Adjust metrics/constraints
  3. Provide domain knowledge
  4. Request specific approaches (ensembles, deep learning)

Focus on practical business impact, not perfect accuracy.


Need More Help?