Switch instantly. Keep everything.
Research
Full-cycle research automation: from framing hypotheses and synthesizing literature to planning experiments, GPU training, running evaluations, and drafting manuscripts.
Biology
Your specialist for both wet-lab and computational biology — covering protein design, genomics, pathway analysis, and biomedical reasoning workflows.
Flywheel
Turn production usage into compounding model gains — automatically design fine-tunes, run evaluations, and continuously ship better versions.
Write
Transform rough notes into publication-ready papers with structured arguments, fact-checked citations, clean LaTeX, and camera-ready layouts.
Mathematics
Solve anything from arithmetic to research-level mathematics — step-by-step working, KaTeX-rendered proofs, formal theorem proving, function graphs, and web-grounded solutions from MathOverflow and arXiv.
A workflow for almost everything.
Literature Synthesis Pipeline
Condense 100+ papers into one organized survey
Protein Structure Analysis
Execute AlphaFold variants on your own sequences
Custom Data SFT Fine-Tuning
Supervised fine-tune DeepSeek on specialized datasets
Paper Drafting
Go from outline to a LaTeX-ready first draft
Research Hypothesis Builder
AI-guided formulation of research questions
Genomics Analysis Pipeline
Perform variant calling, annotation, and pathway mapping
Benchmark Harness Configuration
Automated benchmarks across model checkpoints
Paper Structure Builder
Convert notes into a well-organized paper structure
Experiment Design Tool
Plan ablations and statistical testing strategies
Compound-Target Screening
Screen compound libraries against specific protein targets
Preference Data Generator
Automatically generate preference pairs from production logs
Citation Fact-Checker
Live fact-checking against OpenAlex and PubMed
Step-by-Step Solver
Full working for any integral, ODE, or algebra problem
Proof Assistant
Formal proofs by induction, contradiction, and direct methods
Practice Generator
Unlimited problems across 33 math topics with graded solutions
Linear Algebra Suite
Eigenvalues, SVD, matrix transformations with visualizations
Bring the tools you already trust.
Built to run while you're away.
Stateful Sandboxes
Every agent runs inside an isolated, stateful environment with full checkpointing and reliable resume.
Flexible Compute Scaling
Go from a single analysis node to a full GPU cluster — no need to change prompts, workflows, or context.
Background Job Orchestration
Send long evaluations, training runs, and literature pipelines to a background queue while you're away.
Long-horizon RL environments, built for scientific work.
Build RL environments and process-based training data for LLMs — beginning with agentic coding environments designed for ML research workflows.
Begin buildingI created Veil because I kept jumping between five separate tools just to complete a single research task — reading papers in one tab, running models in another, writing in a third. Every switch shattered my flow and wiped my context.
Researchers and ML engineers deserve a workspace where the AI holds the full context of their work — not just the last message. That's what Veil is. One unified workspace, five specialized modes, thousands of workflows, your own compute — all together, always in sync.
