EXPERIMENTAL SCIENCE FOR AI
Teach AI how science is done.
Run real experiments to teach AI scientific practice. Connect the experimental process to measurement data, metadata and the decisions researchers make.
Programmes scoped with your team. Methods and availability confirmed before execution.
TEACHING THE SCIENTIFIC PROCESS
From experimental work to scientific learning.
We run experiments and connect the work to its measurements, metadata and researcher decisions. Your team can use that evidence to teach AI how to carry out and reason about scientific work.
Run the experiment
Capture the procedure as performed: preparation, actions, parameter changes and deviations.
Measure the result
Retain the original signals and results, including controls, repeats and useful negative outcomes.
Preserve the context
Link samples, materials, instruments, settings, units and timestamps to each experiment.
Train and evaluate AI
Teach procedure following, result interpretation and experiment planning using reviewed scientific records.
EXPERIMENT FAMILIES
Scientific work your AI can learn from.
Explore programmes in materials, chemistry and biology. Each starts with a scientific question, a defined set of measurements and an agreed capture plan.
Batteries and electrochemistry
Connect the way a material is prepared and a cell is assembled to its measured performance.
- Experiments to scope
- Formulation and electrode coating; coin-cell assembly; formation, cycling and electrochemical characterization.
- Data we can deliver
- Preparation and cell IDs; native tester files and exports; reference cells, performance endpoints and failure records.
Study preparation-to-performance relationships and evaluate how models interpret variation, controls and failure.
Thin films and 2D materials
Connect how films are fabricated and 2D materials are transferred to measured quality and the next process decision.
- Experiments to scope
- Spin coating, lithography, deposition, etching, lift-off and graphene transfer; individual steps or a linked metal-patterning workflow on silicon oxide.
- Data we can deliver
- Process recipes and tool logs; microscopy and AFM files; thickness, coverage and defect measurements; researcher decisions to proceed, rework or stop.
Assess pattern fidelity, film coverage and damage, including the expert judgement needed before the next step.
SUPPLIED RESEARCH EXAMPLES
Examples of process failures
These microscopy and AFM figures show reported quality problems in fabrication. A new campaign can connect such observations to process settings, original measurements and the researcher’s next decision.
Open full imageLaser lithography
- Reported issue
- Wavy or scalloped pattern edges and varying linewidth after laser lithography for a microwave resonator.
- Data to capture in a new programme
- Exposure recipe and settings, calibrated pattern images and linewidth measurements, with the researcher’s decision to accept or rework.
- AI learning task
- Assess pattern fidelity before the next fabrication step.
Open full imageGraphene transfer
- Reported issue
- The supplied slide reports openings left uncovered after graphene transfer, based on AFM.
- Data to capture in a new programme
- Transfer and drying conditions, native AFM scans and height profiles, substrate and scan coordinates, and the next-step decision.
- AI learning task
- Check film coverage and choose the next measurement or process change.
Open full imageMultilayer deposition
- Reported issue
- Wrinkling and broken structures after CVD deposition of a Si/SiO₂/SiNₓ stack.
- Data to capture in a new programme
- Layer sequence and deposition settings, original microscopy, thickness and defect measurements, and the researcher’s interpretation.
- AI learning task
- Recognize film damage and evaluate which step to investigate next.
Figures shared by Hadi Arjmandi Tash. Native files, sample links and capture terms are agreed for each new programme.
Materials synthesis and characterization
Keep a material’s preparation history connected to its structure, composition and properties.
- Experiments to scope
- Solid-state synthesis, weighed powder mixtures with XRD, formulation screening, microscopy and physical characterization.
- Data we can deliver
- Actual preparation records; native patterns, images and spectra; reference measurements, repeats and reviewed phase or defect assignments.
Build datasets for structure–property prediction, phase analysis and interpretation of measured evidence.
Chemical synthesis and analytical testing
Capture what went into a reaction, what came out and the checks used to establish the answer.
- Experiments to scope
- Reaction screening, molecular characterization, NMR and LC-MS, analytical validation, QC and scoped route development.
- Data we can deliver
- Structures, amounts and conditions; native spectra and chromatograms; calibrated identity or yield, controls and investigations.
Train reaction models and evaluate structure assignment, analytical reasoning and diagnosis of measurement problems.
Enzyme engineering and biocatalysis
Follow a sequence change through protein production to calibrated activity and substrate response.
- Experiments to scope
- Sequence-verified variants, independent protein preparations, protein quality and activity assays. Kinetics and stability can be scoped separately.
- Data we can deliver
- Verified sequences; production and quality records; original assay files, protein-normalized activity, parent controls and interpretation.
Model sequence–expression–function relationships while distinguishing protein recovery from catalytic performance.
Cell biology and immune assays
Connect controlled perturbations to cellular responses and molecular measurements across assays.
- Experiments to scope
- Viability and cytotoxicity, flow cytometry, Western blot, qPCR, ELISA and co-culture studies.
- Data we can deliver
- Sample-linked FCS files, protein images and plate signals; gating and analysis versions; controls, response tables and interpretation.
Learn cellular-response patterns and evaluate interpretation of multiple assays, controls and conflicting evidence.
We confirm the method, laboratory, availability and data rights for each programme before you approve the work.
ONE EXPERIMENT, IN DETAIL
A battery experiment, from preparation to testing.
A new programme can vary preparation and assembly conditions, measure the response and preserve the decisions made along the way. This recorded workflow shows the work involved.
Recorded stages from the coin-cell experiment.
For a new battery programme
- Experimental process
- Formulation, mixing, coating settings and assembly sequence.
- Measurement data
- Native cycling files and performance measurements linked to each cell.
- Metadata and quality checks
- Material and cell IDs, test settings, controls and researcher interpretations.
Teach AI to relate process choices to performance, assess uncertainty and decide what to test next.
WHAT YOUR TEAM RECEIVES
Process, data, metadata and decisions.
Each programme defines the scientific tasks to learn and the evidence to retain. The delivery connects what happened, what was measured and why the researcher chose the next step.
Experimental process
Actual procedures, recipe versions, preparation history and recorded handling. Video can make the process observable where useful.
Measurement data
Native instrument files and open exports, with settings, units and sample IDs.
Metadata and quality checks
Sample and run IDs, instrument settings, units, timestamps, controls, independent repeats and QC flags.
Researcher decisions
Recorded interpretations, corrections and reasons to continue, repeat or stop.
Linked, documented delivery
An agreed schema, sample-to-file map, data dictionary, workflow guide and checksums. Training and evaluation rights are defined with the programme.
RESEARCH EXAMPLES
Examples of biological data formats.
The biological examples we have received combine cytometry, protein images, gene-expression and plate-assay tables. A new programme is scoped to retain the originals, controls and sample links each task needs.
Received research formats; a complete, licensed dataset is agreed separately.
TEACHING THE SCIENTIFIC PROCESS
Scientific practice in the laboratory
This narrated film explains how laboratory procedures, equipment and observed actions can be connected to structured experimental records for scientific AI.
ALSO AVAILABLE TO SCOPE
Need existing research records?
We can explore historical laboratory records when they fit your task: original measurements, notebooks and documented investigations. Availability, missing context and licensing are checked for each source.
DESIGN YOUR DATASET
What scientific work should your AI learn?
Tell us the experiment, skill or decision you want to teach. We will scope the work, measurements, metadata, independent runs and usage rights with your team.
Start with a non-confidential brief. We confirm feasibility and a scoped proposal before work begins.
EXPERIMENTAL DATA CAMPAIGN