Journey · Master's student · 5 full days · Level 1 to Level 3
What you get out of the week
On Monday you pick one prepared lab case. On Friday you show a result that works, that a fellow student has rerun, and that you can explain in five lines. In between you use AI where it helps and check it every time it answers. On the last afternoon you plan how to do the same in your thesis.
The case stays the same all week. Each day asks a bit more of it:
- Level 1: it works for you.
- Level 2: a fellow student can use it.
- Level 3: someone else could rely on it without you.
Who this is for
You study a life science at master's level. You have used a chatbot. You have never opened a terminal. If your Thursday build needs one, its book walks you through every click. You don't need your own data: everything you work on comes with the case. Scientists who want to bring a task from their own lab have their own journey: Life-Science Scientist.
Pick one case on Monday and keep it all week:
- Cells: microscopy images, with hand counts, including clumped and blurry ones.
- Protocols: lab protocols, with facts about them that were checked by hand.
- qPCR: plates of Ct values (the cycle at which each sample's signal appears), with the known result for each sample.
- Protein: published protein sequences whose structures are already solved.
Every case comes as two sets of files, each with at least ten known answers. You work on the first set. On Thursday your partner reruns your work on the second set, so you can always tell whether a tool got it right.
Download your case: Cells · Protocols · qPCR · Protein. Each download has a README that explains the files, where the answers are, and how to cite the sources. All files are public and openly licensed, so they count as green.
The method behind every day
Monday to Thursday, each day is one trip round the four quadrants from T01-L01 · From Idea to Working Result: The Four-Quadrant Method. The quadrants form a grid of four boxes: two about the problem, two about the solution. Friday checks the result and takes it to your thesis.
| The problem | The solution | |
|---|---|---|
| Define | Structure it | Choose tools |
| Explore and test | Understand it | Build it |
- Structure it: say in one sentence what goes in, what comes out, and how you'll know it worked.
- Understand it: find out how the task is done today and what you can reuse. When that changes the problem, go back to Structure it. This back-and-forth is where most of the value is.
- Choose tools: start with the simplest option and only move up when it fails. First, something that already does the job. Then a small change to it, then a template or spreadsheet formula. Last, AI for one part only.
- Build it: make it, try it on cases where you know the answer, and fix what breaks.
How Monday to Thursday run
| Time | Quadrant | What happens |
|---|---|---|
| 09:00–10:30 | Structure it | A 20-minute demo, then you write today's problem sentence. |
| 10:45–12:15 | Understand it | You look at what already exists: the case files, the papers, other people's tools. |
| 13:15–15:15 | Choose tools | You try options on known answers and pick one. Then you start building. |
| 15:30–17:00 | Build it | You finish today's result. Your partner checks it, and you write the exit check. |
Breaks: 15 minutes mid-morning, an hour for lunch and 15 minutes mid-afternoon. There's no homework. All reading happens in the room: the trainer points you to the parts of each book you need that day. The whole books are for later.
You work in pairs, each on your own case. Your partner is your first checker, and you check their work, too. The course runs with up to 12 people per trainer.
The five-line exit check closes every day, Friday included. It's the only paperwork:
- Problem: today's final Structure it sentence.
- What exploring changed: what you learned in Understand it, and how it changed the problem.
- Choice: the tool or method you picked, and why it's the simplest that works.
- Result: what you built, and whether it worked when your partner tried it.
- Next step: the one thing you'd improve on the next trip round.
From Monday you also keep an AI use log, one line per AI step: date, tool, what you asked, what you kept. On Friday it becomes the AI statement for your thesis.
The week at a glance
| Day | Question of the day | Level | You leave with |
|---|---|---|---|
| Monday | What exactly is the problem, and what may I paste? | 1 | A problem sentence, the case files sorted by colour, a prompt you can reuse |
| Tuesday | What is already known? | 1 | A checked list of sources |
| Wednesday | Which tool gets the lab data right? | 1 → 2 | A tool tested on known answers, and a first result on the case |
| Thursday | Can someone else rerun it? | 2 → 3 | A script, pipeline or small tool your partner reran with the same numbers |
| Friday | Would it hold up, and how do I use this in my thesis? | 3 | A checked result shown live, an AI statement and a plan for your thesis |
Monday: the problem, safely
Before any tool, you decide what the problem really is, and which data may go into which AI tool. The case data is safe to practise on. Your thesis data won't be, so you learn the rules now.
| Quadrant | What you do | Read |
|---|---|---|
| Structure it | Write the case task as one sentence. Then sort the case files by colour (see below), and only then compare with the case notes. | T12-L01 · Decide What You May Paste Into AI at Work |
| Understand it | Read the case notes: how is this done by hand today, and what comes with the case that you can reuse? Meet the four facts about AI assistants (see below). Rewrite your sentence. | T01-L01 · From Idea to Working Result: The Four-Quadrant Method |
| Choose tools | Go from the simplest option upwards. Only one part of the task goes to AI, and only if nothing simpler works. | T01-L01 · From Idea to Working Result: The Four-Quadrant Method |
| Build it | Write one prompt for that part: your material, who the answer is for, one example, what to leave out. Run it, check every claim and save the prompt. | T02-L01 · Get Answers You Can Use from a Chatbot, T03-L01 · Write a Prompt You Can Reuse |
The three colours:
- Green: already public, like published papers or protocols from a journal. Any tool.
- Yellow: internal but not sensitive, like a lab how-to with no names in it. Only tools your university has approved.
- Red: unpublished results, anything about a person, and anything confidential. No online AI tool, unless someone who may decide has cleared this exact use in writing.
The case notes say which colour each file is, so you can check your sorting. In your thesis, most lab data will be red until it's published. The week practises the way around this. You show the AI the shape of the data, such as the column names and a few made-up numbers, and let it build a tool. Then you run that tool on the real data on your own computer.
The four facts about AI assistants:
- It writes what sounds right.
- It starts every chat from zero.
- It sounds just as sure when it's wrong.
- What you type goes to the provider.
What goes wrong today: the assistant gives you a confident answer that turns out wrong: a reference that doesn't exist, or a number it made up.
Tools: the chat assistant your university has approved, for example ChatGPT, Claude or Microsoft 365 Copilot.
Tuesday: what is already known
Every case task has been done before, by hand or by a tool. Today you find out how, and you check every source an AI hands you.
| Quadrant | What you do | Read |
|---|---|---|
| Structure it | Turn the case problem into three questions for the literature. For each one, write what a good answer would let you do. | T17-L02 · Frame a Problem Your Team Agrees On, T15-L01 · Use AI in Your Research and Say Exactly How |
| Understand it | Search with an AI research tool, then check every hit in PubMed. Does the paper exist, and does it say what the summary claims? | T17-L03 · Explore What Already Exists Before You Build |
| Choose tools | Decide where your papers go. Published papers are green, so any notebook tool will do: a tool that answers only from the papers you upload. | T04-L01 · Ask Your Own Documents and Check Every Citation |
| Build it | Load the case's starter papers and ask your three questions. Mark each claim in the answers as supported, unsupported or not found. | T04-L01 · Ask Your Own Documents and Check Every Citation |
What goes wrong today: a summary cites a real paper, but the paper says the opposite. You only catch it because you opened the paper.
Tools: Perplexity to map the field, PubMed to check it, and Gemini notebooks for the papers. DeepL handles papers in other languages.
Example: Chat over documents.
Wednesday: the lab data
Today a tool works on the case data. The rule of the day: before you trust a tool, test it on cases where you already know the answer. Your case comes with those answers.
| Quadrant | What you do | Read |
|---|---|---|
| Structure it | List the known answers you'll test against: at least ten, from the case notes. | T16-L03 · Test a Tool on Your Own Work Before Your Team Depends on It |
| Understand it | Look at the data the way the tool will see it: file types, empty wells, clumped cells, blurry images. Make sure the awkward cases are in your list. | Your case's book |
| Choose tools | Try two options on the same cases, and keep the one that gets them right with the least effort. | T16-L01 · Pick the Right Tool for One Task by Trying It |
| Build it | Run the chosen tool on the whole case, and compare ten results with the known answers. | Your case's book |
Your case's book and tools:
- Cells: T18-L01 · Count Cells With a Ready-Made Model and Check It by Hand, with Cellpose and Fiji. Example: Segment cells with Cellpose.
- Protein: T18-L02 · Predict a Protein Structure and Read Its Confidence Honestly, with AlphaFold Server. Example: Explore molecular structures.
- qPCR: T10-L01 · Ask a Spreadsheet a Question and Check Which Rows It Used, then T10-L02 · Clean a Messy Export Once, So Your Team Can Refresh It.
- Protocols: T04-L01 · Ask Your Own Documents and Check Every Citation. An AI turns the protocols into a comparison table, and you check it against the ten hand-checked facts.
What goes wrong today: the tool gets the easy cases right and fails on the awkward ones, such as clumped cells, a failed well or a floppy loop in the protein. This is why the known answers come first.
Thursday: make it rerunnable
A result only you can produce is a result nobody can check. Today you turn Wednesday's work into something your partner can run on their own laptop and get the same numbers.
| Quadrant | What you do | Read |
|---|---|---|
| Structure it | Write what your partner needs to rerun it: which input files, which tool version, which prompt and which settings. | T15-L02 · Record an AI Step So a Co-Author Can Rerun It |
| Understand it | Try the red-data route once, even though the case is safe: run your AI step on a model on your own laptop. This is how you'll work with thesis data. | T11-L01 · Run an AI Model on Your Own Laptop, Offline |
| Choose tools | Pick the build that fits your case (see below). A coding assistant builds it with you, one small change at a time. | Your build book |
| Build it | Build it, then hand it to your partner. From your notes alone, they rerun it on your files and get your numbers. Then they run it on the second set and check it against its known answers. | Your build book |
Pick one build:
- A small tool that runs in your browser, for example a Ct calculator, or a page that shows the prediction's confidence along the protein: T06-L01 · Build a Small Browser Tool You Will Actually Use.
- A script that repeats the analysis on each new file: T08-L02 · Get a Script Your Colleague Can Rerun, Without Being a Developer.
- A counting pipeline for a whole folder of images: T18-L03 · Build a Cell-Counting Pipeline Your Group Can Rerun and Check.
- An analysis that gives the same numbers every time it runs: T10-L03 · Build an Analysis Your Colleague Can Rerun and Get the Same Numbers.
Same numbers, even with AI in it. An AI can answer differently each time you ask. So either the AI only writes the tool and the finished tool contains no AI, or you save the AI's output with your notes and your partner checks that.
What goes wrong today: your partner can't get your numbers, because a tool version, an input file or the exact prompt was missing from your notes. You fix the notes, not the partner.
Tools: opencode as the coding assistant (the Desktop app, where you describe what you want and it writes the code), and LM Studio for a model that runs offline.
Friday: would it hold up, and your thesis
Today you find out whether your result would hold up without you in the room. Then you take the method to your own thesis.
| Time | What happens | Read |
|---|---|---|
| 09:00–10:30 | Swap results with another pair. Check theirs the way a careful supervisor would, and write them a short check note. | T01-L02 · Check AI Output Before Your Team Relies on It |
| 10:45–12:15 | Fix what the check found. Remove whatever nobody needs. Turn your use log into an AI statement: which tool, which step, what you checked. | T01-L03 · Build the Smallest Thing Your Colleagues Can Run Without You, T15-L01 · Use AI in Your Research and Say Exactly How |
| 13:15–15:15 | Show your result, 8 minutes each: run it live, read your five lines, answer two questions. | — |
| 15:30–17:00 | Your thesis: write one task from your thesis as a Structure it sentence, sort its data by colour, and plan the week's steps for it. Then write your fifth exit check, on the whole week. | T12-L01 · Decide What You May Paste Into AI at Work |
Before you use AI in your thesis, check your university's rules and ask your supervisor. Your AI statement is the note you show them.
How you pass
There are no points. You pass when all five of these are true:
- It runs. You show your result live on Friday.
- Someone else reran it. From your notes alone, your partner got your numbers, and correct answers on the second set.
- It was checked against known answers: at least ten, including the awkward ones.
- Your paperwork is complete: five exit checks, the use log and your AI statement.
- Your thesis plan is written: one task, its colours and its steps.
What you take home: your result, your notes for rerunning it, five exit checks, a check note from another pair, your AI statement and a plan for your thesis.
Before Monday
- An account for your university's approved chat assistant. If there isn't one, the course provides one.
- A laptop you may install software on. It should be a Mac with an Apple chip or a recent Windows PC, with 16 GB of memory for the offline model (8 GB works with smaller models) and about 10 GB of free disk space.
- The install list. Your trainer sends it a week ahead: LM Studio, opencode Desktop, and Fiji for the cells case. It takes about 30 minutes.
- Nothing to read in advance.
What this week leaves out
- Your own thesis data (you plan for it on Friday).
- Setting up servers.
- Automations that run on their own.
- AI on clinical or patient data.
Further reading and tools
All the books in this journey are listed below the course, in the order you meet them.
- Used hands-on: Cellpose, Fiji, AlphaFold Server, PubMed, Perplexity, Gemini, LM Studio, opencode.
- Mentioned: DeepL, ChatGPT, Claude, Microsoft 365 Copilot.
Rule to remember: one case, round the quadrants again and again, and nothing counts until someone else has rerun it.