The operating system for labs to plan, run, and prove any experiment.
Protocol design, real-time scheduling, ELN/LIMS, data analysis, an AI assistant, and edge-agents for every instrument, manual to fully robotic, in one system with a complete audit trail and role-based access.
No install required for scientists: edge agents handle the instrument side.
Shown here: FluenticOS customized for a precision oncology drug-screening lab, one example of how the general-purpose platform adapts to a workflow.
Who profits most
The same system of record, read differently depending on who's asking.
Scientists
Design a multi-day experiment as a flowchart, then let the scheduler and analysis pipelines run it.
Lab technicians & operators
Every step run carries a plain-language briefing, task by task, whether it's claimed at the bench through the edge control UI or run automatically by a driver.
Project leads & PIs
One live view of every experiment's progress across every instrument, with a priority-aware scheduler that reprioritizes on its own the moment something slips, instead of a status meeting.
QA & compliance teams
Every result traces back to its originating sample in one click, and role-based access keeps each person to only what they're cleared to see.
A lab data platform, in three sentences
Why
Multi-day, multi-instrument experiments still run on whiteboards and tribal knowledge. By the time a result reaches a report, tracing it back to its source sample is a support ticket, not a click.
What
One system of record that plans a protocol as a flowchart, schedules and runs it across real instruments, and keeps every sample and result traceable end to end.
How
A priority-aware scheduler recomputes the whole plan continuously. Edge agents at the bench claim and report work over an authenticated line, so the plan and the physical lab never drift apart.
One system plans the protocol, runs it on the bench, and proves what happened, end to end, instead of stitching together a scheduler, a spreadsheet, and a shared drive.
Explore the technical detail
Every claim above has a real screen and a real mechanism behind it. Jump straight to any of them.
Visual protocol editor
Drag step templates onto a canvas, wire connections, configure each step inline.
Real-time scheduling
A priority-ordered, resource-aware scheduler that recomputes the global plan continuously.
Samples & consumables
Full chain of custody from source tube to individual well, plates and kits included.
Data explorer
Table, plate map, scatter, and dose-response views over every well, filterable and exportable.
Logistics
Know where every consumable is right now, and move it with a scan.
Audit trail & notebook
Every state change and note merged into one append-only experiment timeline.
Every layer of the lab, in one system of record
FluenticOS is built around the real shape of a research workflow, from how a protocol is drawn to how a sample physically moves between instruments.
Design protocols like flowcharts, configure each step inline
Drag step templates onto a canvas and wire them with typed connections. Click any node and an inspector opens beside it, its schedule, parameters, and simulate toggle, right there on the canvas: no separate settings screen, DAG validity checked at design time.
Query every well like a spreadsheet, plot it like a scientist
Filter by drug, concentration, indication, sample type, or QC status, then switch between table, plate map, scatter, and dose-response views without losing the filter state. Export to CSV whenever it's time to leave the platform.
Protocols & pipelines
Every screen and analysis DAG ever designed, versioned from draft to released, catalogued by accession ID.
Lab Space
Every instrument mapped to your real bench layout, with live device state.
Real-time scheduling
A priority-ordered, resource-aware scheduler that recomputes the global plan continuously, driving the Gantt, the edge-agent timeline, and claim enforcement alike.
Systems registry
Instruments, compute, services, and people, in one heartbeat-monitored table.
Sample lineage
Full chain of custody from source tube to individual well, traced through every derivation step.
Reagents & drugs
Working preparations traced back to their source stock lot, concentration, and expiry.
Consumables & kits
Plates, tubes, bottles, and slot-validated kits, tracked from registered to processed.
Logistics
Know where every consumable is right now, and move it with a scan.
Audit trail & notebook
Every state change and note, central or filed at the bench, merged into one append-only timeline.
A few more things worth knowing
Automated analysis, configured not hardcoded
Curve fitting, segmentation, and other pipeline steps are configured per protocol, not a one-size-fits-all script.
Role-based access & display
Navigation and data both adapt per role, with an admin impersonation view for support.
QC review
Review well-level measurements against a plate map and record QC decisions before data reaches analysis.
Diagnostics
System health, flow registry, and agent tool status in one place.
Receive-only by design. Every instrument reports in: none get commanded
Edge agents run next to each instrument and talk to the platform over authenticated REST. The platform never opens a connection back to a device: it can only accept or reject what an agent reports.
The StepRun state machine is the spine of the platform
Every unit of work, a robotic move, an imaging pass, an incubation window, is a StepRun with the same lifecycle. A system error auto-suspends its running work instead of losing it, and claims are capacity- and priority-checked, rejected synchronously on conflict.
From a step template to a well of live cells
Step templates
Reusable building blocks: imaging, dispensing, incubation, analysis.
Protocols & pipelines
Templates wired into an ordered, versioned DAG.
Experiments
A protocol instantiated against real samples, consumables, and a project.
Step runs
Scheduled, claimed, and executed by the right instrument, in priority order.
Results
Measurements, images, and outputs flow back in, queryable within seconds.
Manual bench today, robotic bench tomorrow: same protocol either way
Every instrument in Lab Space is linked to the platform by an edge agent, a small process that runs next to the device, claims the step runs scheduled to it, and reports results back. Whether that step happens by robot or by hand is a property of the instrument, not of the protocol.
Fully automated
When an instrument has a driver, a SiLA 2 device, a serial device, a vendor SDK, the edge agent claims the step the moment it's schedulable and runs it end to end. No operator touches it.
Manually operated
No driver configured? The step is scheduled all the same. The edge agent's local control UI turns the step briefing into a checklist: which consumable, which parameters, what to do. An operator claims it, follows it, and uploads the results.
Either way, results reach the platform through the same door: a scoped presigned upload, then an authenticated measurement post. Same validation, same lineage, same Data Explorer on the other end.
An assistant you talk to, and agents that work inside the run
FluenticOS keeps the conversational assistant and the autonomous execution agent as separate services with separate tool surfaces, so "ask a question" and "act on the bench" are never the same permission.
Ask FluenticOS
Surfaced from anywhere in the app to explain a failure or answer "why is this step blocked" in plain language, grounded in live data. It can also draft new steps and protocols and validate a design before it's saved.
Autonomous step-run agents
A separate agent runtime with tool access to create, run, and troubleshoot experiments directly, all reviewable in Diagnostics.
Full lineage, standard ontologies, complete provenance
Every result traces back through a real chain of custody, source sample to derived sample to well. Below is what that looks like on a clinical drug-screening study; the same lineage engine tracks any sample type just as well.
Patient
Pseudonymised record: an accession ID stands in for identity everywhere downstream.
Biopsy
Barcoded tissue sample, timestamped at collection: the root node every derived sample traces back to.
Derived sample
A microtumor, organoid, or cell culture: derived_from and pooled_from recorded automatically.
Plate & well
Placed into a slot-validated consumable under a drug plate design.
Measurement
A well-level result, queryable and traceable back through every hop to the biopsy.
Every sample carries a full timeline (created, lineage, step runs, measurements) so "where did this number come from" is always a click away, not a support ticket.
Patients & biopsies
Pseudonymised patient records with linked, barcoded biopsies: the root node every downstream lineage graph traces back to.
Microtumors, organoids & cell culture
Samples derived or pooled from a biopsy carry that ancestry forward automatically, traceable back to the originating tissue.
Drugs, therapies & indications
A drug catalogue enriched with clinical evidence, and indications coded against standard ontologies (NCIt, SNOMED CT, ICD-10), so results link out to the same vocabularies your EHR already uses.
Drug plate designer
Lay out dose ladders across 96-, 384-, or 1536-well formats with controls and dosing built in, then check the design against screening standards before it's materialized onto a real plate.
See FluenticOS on your bench
This is a preview build: request early access and we'll walk you through a live protocol, a real edge-agent claim, and how your instruments would map onto Lab Space.