Methods, on one sheet.
The same page you can hand to a colleague or a PI: what Methods does, how a session works, what stays yours, and how to reach us.
Science
AI transformation for research, starting with how your work runs today. Methods is the software that maps how the work runs, so a lab can see where AI helps.
Methods is an AI engine that works with researchers as an agentic collaborator. It captures how your work actually runs and turns it into standardized, branded documentation you confirm step by step. Keep your lab's documents and foundational knowledge in your own folders, and Methods uses retrieval-augmented generation (RAG) to ground a private lab agent in them, so every answer cites your lab's own sources. You stay in charge of the science, and nothing leaves until you sign off.
Five things, every one of them yours. Your AI Transformation Assessment: where each step sits on the ladder, your top three priorities and the first win to put to work. Your record: every step, judgment call and value, with anything unstated marked. Your process map drawn by role, and your standardization map ranked by what to do first. Your template library: the documents your team, your PI and your funder need, filled from your sessions in your lab's own layout. Your agent: it answers from your lab's own folders and cites its sources, learns your lab from your team's sessions, and every rule it keeps is visible and confirmed by the PI.
One conversation, at your pace, that you can stop and pick up later. Bring the files you already keep. An annual plan sized to your lab, with the PI plus two logins as standard, so the postdoc, the technician and the rotation student all build the same record. A fraction of the cost of the computational hire it stands in for.
Your raw data stays on your computer, at every tier. Your workspace holds what we create together, versioned, exportable in full and deletable in full. No training on your protocols; zero data retention under commercial terms. You are the author; your name goes on the record because you approved every line.
Four questions to start. One question at a time after that.
How would you like to start? Then the whole process, or one step?
Your agent can review your documentation first and ask only about what it leaves out, or you can talk through your process. Most labs then start with the map of the whole workflow.
What part of your research do you want to work on today?
You pick the area. The session is built through your lab's lens: your instruments, software, team roles, funder mandates and documentation standard.
Suggestions in the chat, or all in the documentation at the end?
Your choice, every session. Either way, every suggestion is tied to a step you described and lands in the record.
What do you want to talk about?
Let's talk through what we can do to make it more efficient and productive. Your answers become the opportunities on your standardization map.
What the agent does while you talk
Inventories your workflow
Every step, input, output, tool and handoff, grouped into sections that could be standardized and, as your lab grows, owned by a role, so you can see your process as an organization chart and project-manage it if it scales.
Asks about the holes
"You said this and then that, but it seems like there should be a step before that in order to allow the next thing. Is there?" It never adds a step itself; it makes sure the picture is complete.
Names what technology could carry
The step you do by eye that already has a tool. The spreadsheet routine a script could run identically for every technician. The figure that could be regenerated from the table. Nobody pays us to be on that list.
The three tiers
Tier 1 · Establish
The session, the record, the inventory, the standardization map, branded templates and a lab documentation standard, your workspace, sign-off and export to your notebook, repository or funder deposition. Annual, sized to your lab.
Tier 2 · Build
Scripts drafted for the steps worth automating, with their assumptions written out and tested on synthetic data first. Your raw data stays on your computer; we test the scripts and give you the output to make sure they work, but we never hold, store, or have any of your own raw data.
Tier 3 · Connect
Run approved workflows on your institution's cloud or ours, one approval at a time; data services that run where the data lives; connections to your institution's systems and to a funder's or organization's program standard; opt-in, fee-free introductions to partners that expand the work.
Bring one part of your research. Leave with a map of it.
Scientists and researchers with an open-science funder first, and NGOs that need their data standardized: if your funder requires a complete, deposited protocol, the first session produces the thing you already owe. Request a session and a founder will reply within two working days.