Meet Neo
Neo is the first autonomous AI engineering agent that plans, researches and executes multi-step work for tasks such as building AI agents, AI model fine-tuning and evals, and ML pipelines; using your codebase, data, and experiments to ship faster with inspectable artifacts.
It can reason over your repository, wire tools and retrieval, debug training runs, and help you develop production-ready AI workflows; all without leaving your editor.
Neo can be used in VS Code, Cursor and Antigravity IDEs via extensions.
What Neo Does
Neo functions as an AI engineering agent that can understand goals, plan multi-step execution, run code locally, and adapt based on results while keeping you fully in control.
Agentic AI workflows
Neo breaks down high-level objectives into executable steps across data preparation, ML training, LLM workflows, evaluation, and iteration. It analyzes tasks before acting and adjusts strategies based on outcomes.
Inspectable and reproducible outputs
Every action produces concrete artifacts including code, prompts, configurations, metrics, reports, and models that live in your repository and can be edited, versioned, or rerun.
Context aware reasoning
Neo reads your project structure, schemas, experiment history, prompts, model checkpoints, and prior runs to make informed decisions rather than starting from scratch each time.
How Engineers Use Neo
Neo supports real AI engineering work beyond single-shot code generation.
- Build and debug end-to-end ML pipelines with data validation and leakage detection
- Develop and evaluate LLM-based systems such as RAG pipelines and fine-tuned models
- Design agentic workflows that use tools, code execution, and external APIs
- Analyze and fix failing experiments, training runs, or prompt strategies
- Refactor notebooks, scripts, and prototypes into maintainable production pipelines
- Generate reproducible reports, evaluations, and deployment-ready artifacts
Platform vs VS Code Extension
Neo works in both the web platform and VS Code. Engineers typically use the VS Code extension for deeper control over execution, data, and version control.
| Platform Mode | VS Code Extension | |
|---|---|---|
| Setup | Instant, no local setup required | Install once inside VS Code |
| Execution | Managed cloud environment | Local-first execution with optional cloud access |
| Data Access | File uploads (50MB limit) or cloud storage | Local files (no size limits) plus cloud integrations |
| Code Control | Download generated artifacts | Edit, run, debug, and commit directly in IDE |
| Best For | Quick experiments and sharing results | Production-grade AI and ML development |
End-to-End AI and ML Lifecycle Support
Neo assists across the full lifecycle of modern AI systems while keeping all decisions transparent and reversible.
Data and Knowledge Sources → Feature or Context Engineering → Model or LLM Execution → Evaluation → Iteration and Refinement
This applies to traditional ML pipelines, generative AI systems, and agent-based workflows.
Get Started in VS Code
Install the VS Code Extension and run your first AI task →