The AI for real science.

Turn a research question into literature, protocol, and computation steps in one workspace.

  • Turn a research question into literature, protocol, and computation steps in one workspace.
  • Build protocol drafts from papers, then audit assumptions, hazards, gaps, and yield limits.
  • Call chemistry tools for molecular weights, GHS hazards, spectra, reaction checks, and quantum calculations.
  • Run Python, Jupyter, RDKit, PySCF, and data analysis without leaving the research thread.
  • Save protocols, audits, plots, PDFs, and notes into workspace files that survive the conversation.
  • Keep evidence, assumptions, and tool outputs visible so results can be reviewed later.
Used by researchers at
MIT ·Stanford ·Harvard ·Oxford ·Cambridge ·Caltech · & 1000+ institutes
Search PubMed, arXiv, and Google Scholar in plain language.
Literature Search

Search PubMed, arXiv, and Google Scholar in plain language.

Build evidence-grounded protocol drafts with assumptions and sanity checks.
Protocol Builder

Build evidence-grounded protocol drafts with assumptions and sanity checks.

Resolve compounds, calculate properties, check hazards, and reason over reactions.
Chemistry Tools

Resolve compounds, calculate properties, check hazards, and reason over reactions.

Proof-check procedures against yield limits, boiling points, hazards, and gaps.
Protocol Audit

Proof-check procedures against yield limits, boiling points, hazards, and gaps.

Install packages, run quick commands, and execute inline calculations.
Compute Shell

Install packages, run quick commands, and execute inline calculations.

Save protocols, audits, PDFs, images, plots, and notes as durable files.
Workspace Files

Save protocols, audits, PDFs, images, plots, and notes as durable files.

Run quantum chemistry calculations with PySCF and ASE.
Quantum Simulation

Run quantum chemistry calculations with PySCF and ASE.

00 // AI RESEARCH AGENT

Autonomous AI research agent.

Ask a research question. An AI agent reasons about your intent, selects the right tools, executes them, and evaluates the results. It repeats until it has a verified, cited answer.

Autonomous reasoning
Up to 10 reasoning cycles per question, with a scratchpad that tracks goals, findings, and next steps
Dynamic tool selection
The agent picks the right tool for each step: literature search, patent lookup, chemical analysis, or simulation
Physics and chemistry aware
Every answer is grounded in real constraints: thermodynamics, kinetics, solubility, and molecular structure
AGENTgoal met?MessageGoalPlanExecuteResultsEvaluateAnswerLiteraturePatentsChemistrySimulationWeb
01 // WHAT IS NEW

New in Vicena 3.0: research that continues.

Version 3.0 turns Vicena from a single chat into a working research environment. The focus is simple: keep the record, continue the computation, and make tool results inspectable.

Keep the record
Workspace Files give protocols, audits, uploads, plots, and notes a durable place to live.
Continue the computation
Jupyter work is targetable, state-aware, and organized around the notebook you are actually using.
Inspect the evidence
Research and science tools return assumptions, provenance, gaps, and outputs the agent can reason over.
01

Workspace Files

Save protocols, audits, PDFs, plots, data files, and notes as normal files with stable paths.

Open Workspace Files
02

Scientific simulations

Work in real notebooks with explicit targets, compact transcripts, visible UI state, and support files beside the notebook.

Open Scientific Simulations
03

Long-running chat

Queue follow-up prompts, jump to the latest result, and keep Files, Computer, and Tools open in side tabs.

Try the workspace
04

Evidence tools

Research, protocol, and chemistry tools expose assumptions, provenance, gaps, and structured evidence.

Browse tool catalog
Release notes Read the full Version 3.0 changelog
02 // LITERATURE REVIEW & PRIOR ART

Automated literature review & prior art research.

Search PubMed, arXiv, Google Scholar, and Google Patents in plain language. The AI agent iterates with refined queries across scientific and patent databases until it has comprehensive, cited results.

Multi-source search
PubMed, arXiv, Google Scholar, Google Patents, and the open web searched in parallel
Adaptive query refinement
The agent evaluates results and reformulates queries until coverage is comprehensive
Full citation chains
Every finding linked to its original source with DOIs, authors, publication dates, and patent numbers
AGENTcoverage complete?QueryGoalPlanSearchResultsEvaluateReviewPubMedarXivNatureIEEEPatentsScholarly
03 // SCIENTIFIC SIMULATIONS

Scientific simulations.

Scientists work in notebooks. They run simulations, plot results, and iterate. So we brought JupyterLab into Vicena. You and the AI agent work together in the same notebook, building on each other's work across sessions.

Agentic JupyterLab
The agent builds notebooks cell by cell: writes code, checks output, fixes errors, and refines. You see every step live.
30+ scientific packages
NumPy, SciPy, matplotlib, RDKit, PySCF, ASE, and more pre-installed. Need something else? Ask the agent to install it. It persists for next time.
Persistent cloud environment
Your notebooks, data, and installed packages persist across chats. Pick up where you left off.
Scientific Simulations
04 // VIRTUAL LAB SIMULATION

Virtual lab simulation.

Simulate your protocol in a virtual lab before going to the bench. The AI validates each step against thermodynamic, kinetic, and chemical constraints.

Thermodynamic validation
Energy balances, equilibrium constants, and Gibbs free energy checked at every reaction step
Kinetic feasibility
Reaction rates, activation energies, and time-to-completion estimated from literature data
Solubility and compatibility
Solvent compatibility, miscibility, and precipitation risks flagged before you start
AGENTall steps validated?ProtocolGoalPlanSimulateValidateEvaluateReportLiteratureChemistryThermoSimulationTech. Webloading protocol: 6 steps to validate... step 1: mixing reagents -- checking solubility... simulating: 95C heating -- thermodynamics valid no simulation available -- inferring from literature... step 4 flagged: precipitation risk at pH 3.2 5/6 steps pass, 1 warning issued
05 // PROTOCOL WORKFLOWS

Extract experimental protocols.

Describe the experiment you want to reproduce. The AI agent extracts every variable from the literature and delivers a complete protocol where nothing is hallucinated.

Variable-by-variable extraction
Temperatures, concentrations, durations, reagents: each parameter found and cross-referenced independently
Confidence scoring
Every value scored by how many independent sources agree, so you know what to trust
Chemistry-aware validation
PubChem and RDKit integration catches impossible reactions and validates molecular structures
AGENTall variables found?RequestGoalPlanExtractScoreEvaluateProtocolScholarProtocol DBChemistryPatentsTech. Webidentify target variables: temp, pH, concentration... plan: extract each variable from 3+ independent sources found: 95C denaturation temp (4 sources agree) scoring: 7/8 variables confirmed, high confidence missing: annealing temp -- refining search... all 8 variables confirmed and cross-referenced
06 // CHEMISTRY LAB
NEW Explore the chemistry lab

AI for real chemistry.

Audit synthesis protocols before the bench. Predict reactions. Run quantum chemistry. Every finding cites its source, and when a tool has no data it says so — instead of faking safety.

Protocol Audit
Validates yield, atom balance, reagent-vessel compatibility, boiling points, and GHS hazards. Catches impossibilities before you run them.
Computational chemistry
20+ tools for reactions, properties, descriptors, spectra, solubility, and retrosynthesis. ReactionT5v2 neural predictor for patent-style coupling reactions.
Quantum chemistry
DFT, Hartree-Fock, and MP2 calculations with PySCF. The AI picks the method and basis set, writes the code, runs it, returns the results.
AGENTanalysis complete?MoleculeIdentifyPlanAnalyzeResultsEvaluateReportConvertersPropertiesReactionsKineticsSafetySpectraresolving: caffeine -> C8H10N4O2... plan: properties, safety, solubility, spectra MW=194.19, LogP=-0.07, passes Lipinski GHS: H302, H312 -- harmful if swallowed predicting IR/NMR spectral signatures... complete: full molecular profile assembled

Try it free.

Literature review, patent search, computational chemistry, and a persistent JupyterLab computer. Describe your research problem and the agent gets to work.

Literature Review Protocol Builder Lab Simulation Compute Shell Chem Tools Web Research Patent Search
Terms & Privacy · Changelog · YouTube · LinkedIn · © 2026 Scitodate B.V.
Featured on There's an AI for That