Establish first. Build when you are ready. Connect when you want compute, and partners, behind it.
Each tier adds a capability and a named point where you, not the software, make the call. Plans are annual and per lab, with unlimited seats, so a year of protocols builds into a lineage rather than a stack of one-offs.
Your processes, established, and a map of what could be standardized
- Guided talk-through: brainstorm and establish the process or protocol, about 45 minutes each
- Structured protocol: materials with identifiers, quantities with units, timing, controls, acceptance criteria
- Variance points: every step where two runs could differ, and why
- Computational candidates: the by-hand or by-eye steps a workflow could standardize
- A standardization map: where your lab's value chain can be optimized, and what can be automated first
- Export ready for funder deposition (protocols.io-compatible)
Scripts the agent writes and you run on your own computer
- For each computational candidate, a script with its assumptions written out in plain language
- You run it on your own machine; your data never leaves the lab
- A test run on synthetic data so you can see what it does before it sees yours
- Which existing tools already do this step, so you are not paying for a script you did not need
- The paths that open once the step is automated: what else the same data supports
Compute, and the connections beyond the lab
- Execute the workflow you approved on your institution's cloud account or ours
- Results land back in the protocol's version history, so the analysis and the method stay together
- Introductions to third-party partners that expand the work toward commercialization, when you ask for them
- Every run is approved by you and logged
A protocol is not a one-off document. It is a lineage.
Protocols change, and the changes are the point
The version you ran in March and the version you run in October differ in ways nobody wrote down. An annual plan keeps every version, every variance point and every correction in one history, so a reproduction attempt can see exactly what changed.
The whole lab, not a seat
The person who knows the protocol best is often not the PI. Unlimited seats mean the postdoc, the technician and the rotation student all interview against the same protocol and the record gets better each time.
Budgetable
An annual, per-lab plan fits a modular grant budget as a single line under other expenses, which is how labs already buy notebook and repository software. It is a fraction of the cost of the computational hire it stands in for.
No fees from anyone else
Nobody pays us to appear in a recommendation. When the agent says an existing tool already does a step, that is because it does.