Have AI suggest hypotheses and experimental designs

Researchers have hypotheses and experimental designs suggested to them

Future prospectAI Act: no extra obligationsDesigning & simulatingSchools & universities, Chemicals & pharma

Fits: Research & development

Aim: at the start of a project, more ideas and experimental set-ups are on the table than in a team meeting, including unfamiliar ones. To be honest: such suggestions often seem novel at first glance, but lose this edge as a project goes on. They only become robust if you check every suggestion yourself against the literature and against what is feasible for you.

Is this for you?

  • You regularly start new projects or supervise theses and are looking for ideas for the start.
  • You can check every suggestion yourself against the academic literature and your knowledge of methods.
  • You want to try out early how far this goes, without a proposal or publication depending on it.
First step today

Do a retrospective test on one of your own completed projects: using the template below, describe only the starting point and research question, without your results, and compare the suggestions with what you actually did and found at the time.

How to go about it

  1. Set the research question and constraints
  2. Provide your own state of knowledge and the literature
  3. Have hypotheses and experimental designs generated
  4. Check against literature and feasibility, and choose
  5. Test it in a pilot experiment
  6. Feed experience back into the template and checklist

Templates to copy

Try it now
in the training
Analyse
in the training
Plan the rollout
in the training
Included in the training

The complete guide

  • 6 steps explaining exactly what to do
  • 3 proven templates to copy into your own AI
  • Safe use: data, checking, deciding, informing
  • Pitfalls, effort and how to recognise success

With the training you get all 430 guides for as long as your access runs.

See the trainingOne-off per person, no subscription

Same approach, other use cases

15 more use cases follow the pattern “Designing & simulating”.

Develop image ideas and a mood board for a consistent feedCreate furniture designs and cutting lists fasterDesign lighter components with generative designEstimate crash and flow behaviour of early variantsModel price increases and supply failures in advancePre-plan photovoltaics and heat pumps from aerial images and consumptionRun stress scenarios for the portfolioWork through design variants and floor plans fasterHave AI pre-select drug candidates computationallyHave synthesis routes suggestedPilot AI-suggested structural optionsPre-develop recipe variants with AI
‹ PreviousSee all use casesNext ›

SH-11 · Legal status 08.10.2026