Biotechnology AI agent · Lab automation

Autonomous-Lab Experimentation Agent (Plan to Run Record)

Plan experiment campaigns, schedule them against instrument and reagent availability, run them inside an envelope your lab head approved, watch them and stop them — the run recorded, no result released as reportable.

Typical delivery: 4–6 weeks
Deployment: Your stack
Run approval: Lab head
After launch: Agent Care

What this agent does

Runs the campaign inside an approved envelope

01
Take the campaign objective, the envelope it may run in and what the last round returned.
02
Read instrument state, calibration status, reagent lots and the consumables on the deck.

Reason

03
Propose the next round of conditions from what came back, inside the ranges the envelope allows.
04
Schedule runs against instrument availability, reagent stability and what may not share a deck.
05
Build the run as executable steps and test each precondition before anything is asked to move.

Decide

06
Hold anything outside the envelope, and work no safety or biosafety owner has authorised.
07
Stop a run on an alarm, a failed check or a deviation, and park the instrument safely.

Out

08
Write the run record — what ran, on what, with which materials, under which plan version.
09
Return the output as run data for a named scientist, never as a reportable value.

Product statement

The agent plans, schedules and runs inside the approval boundaries agreed during implementation. The envelope, authorisation for hazardous, controlled or biological work, and the release of a reportable value stay with the lab head, the named scientist and your biosafety and safety owners.

Example workflow

One campaign round, end to end

Agent

Human

1Round requestedA campaign objective, the envelope it may run in and what the last round returned
2Preconditions readInstrument state, calibration status, reagent lots and expiry, tips, plates and the deck as it stands
3Conditions proposedThe next set of conditions, each inside the ranges the envelope allows, with what the round is meant to settle
4Run built and scheduledExecutable steps, instrument and reagent bookings, and the rules that keep two things off one deck

No human action required

Stages 1 to 4 run without a person in the loop — nobody is asked to look until the preconditions have been read and the round is built. A condition the envelope does not cover stops the round there, before an instrument is booked.

5DecisionSplits on the envelope check and the confidence gate

Inside the envelope

Enters the queue as an approved run.

Outside it, or unauthorised

Held with the offending condition marked.

Lab head, named scientist and safety owners

Read the proposed conditions, the deck, the hazards and whatever falls outside the envelope.

Approve · Amend · Send back

Approved — handed back

6Run executed and watchedStarted only where the envelope, the authorisation and the instrument allow it; stopped on an alarm or a failed check
7Outcome evaluatedAborted runs, preconditions that were wrong, conditions the scientist amended and what did not reproduce

Amendments

Conditions a scientist changes before a run are counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required

8 items

Running anything outside the approved envelope.
- Authorising work with a hazardous, controlled or biological agent.
- Changing an instrument's safety configuration or a calibration.
- Overriding an interlock, an enclosure or an alarm.
Automation boundary
Agent acts unaided
- ✓Propose the next round from what the last one returned.
- ✓Schedule runs against instruments, reagents and the deck.
- ✓Test the preconditions, start an authorised run, and stop it on an alarm or a failed check.
- ✓Write the run record — what ran, on what, with which materials, under which plan version.
Write actions run only inside the approval boundaries agreed during implementation. Widening one is not one of them.
- Releasing a result as a reportable value.
- Restarting a run after a safety stop.
- Widening the envelope or the condition ranges.
Starting an unattended run nobody has agreed to.

Example output

One proposed round, annotated

Everything the agent proposes is attached to the envelope and the preconditions it was read against.

Run proposal · single campaign round

Illustrative example

Campaign: Buffer-condition screen
Round: 3 of an agreed 5
Instruments: Handler, reader, incubator
Proposed: Next condition set and run order
Confidence: 86%
Output status: Run data, not reportable

As received

The campaign, the round it is on and the rig booked for it — nothing on this side is proposed by the agent.

Evidence used

Envelope as approved
Last round's readouts
Calibration and lot status

Why these conditions

The last round pushed at the top of an allowed range, so the next set steps back inside it.

What the score decides

Below the configured threshold the round waits for the scientist, not the run queue.

Action

ApproveAmendSend back

Value

Where AI adds value

The same four claims, placed at the point in the workflow where each one applies.

Where the value lands

Value 01 – 04

Every round in a campaign

From your scheduler and instruments

03Planning & scheduling

Test every run against its envelope

Use the approved envelope, the instrument and calibration state, the reagent lots and the rules the deck has to respect.

01Approved path

Turn a returned round into the next one

The last round's readouts, the envelope and the deck are read together, so a scientist opens a proposed round rather than an empty plan.

02Human review

Stop the run before the deck does

A failed precondition or an alarm stops the run, parks the instrument and calls the person named on it; a run that degrades with neither is not caught here.

Build an evidence trail

Retain the envelope version, the preconditions read, the conditions proposed, the instruments and lots used, the stop and each scientist amendment — on both paths.

Integrations

Typical integrations

Five system groups connect to the same agent. Which of them are in scope is decided in discovery.

Instruments & robotics
- Liquid handlers
- plate readers
- Incubators
- chromatography
Scheduling & control
- Scheduler software
- device drivers
- SiLA 2 and OPC UA
- run queues
Laboratory records
- Electronic notebooks
- lot records
- Calibration
- maintenance logs

Agent

Autonomous-lab experimentation

Reads instrument state
Schedules and runs
Stops and records

Safety & containment
- Interlock and enclosure status
- alarms
- Hood monitoring
- biosafety registers
Observability & evaluation
- OpenTelemetry
- Langfuse
- Supported monitoring/evaluation sources

Integration availability depends on the client's existing systems and API access.

Agent controls

Six layers between the model and the deck

Each control wraps the one inside it. A proposed round clears every layer before an instrument is asked to move.

L6 · Outermost — last line of defence

Inward → L1 · closest to the model

L6Trail and safe modeProvenance is written with the run, and automation narrows if evaluations or production signals degrade.Record

L5Watch and stopRuns are watched against expected behaviour and stopped on an alarm or a failing check; a failure that raises neither is not seen here.Stop

L4Human authorisationDefine what may start unattended and what waits for the lab head, the named scientist or a safety owner.Gate

L3Deck separationMaterials and samples your rules keep apart are held off one deck and one window; a conflict is raised here, not resolved.Separate

L2Precondition gateInstrument state, calibration status, reagent lots and the loaded deck are read before a step runs; a failed read stops the build.Verify

L1Envelope checkConditions are tested against the ranges the envelope names; one it does not describe is held, and an uncovered range is measured here.Test

Model coreRound proposed — conditions, run order, instrument and reagent bookings, and confidence

L1 – L2: Decide whether a run may be built
L3: Keeps two things off one deck
L4 – L5: Gate the start; stop on an alarm or a failing check
L6: Keeps the provenance, narrows automation

How Nestack evaluates it

Evaluate the whole campaign — not only the run that finished.

Coverage runs the whole depth of the workflow, and every layer is cut by slice.

Surface — the round a scientist is asked to approve

E1Proposal evaluationWere the conditions inside the envelope and tied to the last round?
E2Precondition evaluationWere instrument, calibration and lot state read as they actually were?
E3Schedule evaluationDid the deck and the window keep incompatible work apart?
E4Stop evaluationDid the run stop when it should have, and park where it should?
E5Slice evaluationHow does run quality change across specific run cohorts?
E6Business outcomeHow many runs were aborted, repeated or thrown away?

Floor — the run record the lab works from

Failure modes

Where each failure originates in the agent

Seven failure modes plotted against the five stages of the agent lifecycle.

Agent lifecycle

Direction of processing →

01 · Planning
2 modes
- AL-01
  Condition proposed outside the envelope
  A range the envelope never covered is treated as allowed.
- AL-02
  Optimiser chases an artefact
  The readout climbs for a reason that is not the effect.
Stage proposes
The next round's conditions, inside the envelope
02 · Preconditions
2 modes
- AL-03
  Run started on a lapsed calibration
  Qualification expired between the check and the run.
- AL-04
  Deck does not match the plate map
  Tips, plates or a lot were changed after the plan was built.
Stage checks
Instrument state, calibration, lots and the deck
03 · Scheduling
1 mode
- AL-05
  Incompatible work booked together
  Two reagents or samples share a deck or a window they must not.
Stage books
Instruments, windows and what may share a deck
04 · Execution
1 mode
- AL-06
  Overnight failure raises nothing
  A run degrades with no alarm and no failing check until morning.
Stage runs
Only where the envelope and the authorisation allow
05 · Record / Version
1 mode
- AL-07
  Manual intervention never recorded
  Someone opens the enclosure and the record does not show it.
Stage records
Plan version, materials, instruments and the stop

Sev-1 · a run puts material or a rig at risk
Sev-2 · the data cannot be traced back
Sev-3 · the round is wasted and repeated

See the complete Biotechnology failure-mode catalogue

Affected slices

A run nobody is standing next to costs the most

Aborted, repeated and discarded runs, counted where a precondition, a deck or a stop was wrong and never where the science simply did not work. An overnight round has nobody in the building when the deck turns out wrong.

Slice performance — reported separately, not only in aggregate

Illustrative example

Slice	Failure rate	Lift	Status
Unattended overnight runs	4.3%	2.8×	Review
Newly integrated instruments	3.6%	2.3×	Review
Runs after a lot change	2.5%	1.6×	Watch
Repeats of a known condition	1.4%	0.9×	Normal

Bar: lost-run lift vs. known-condition baseline · scale 0–4.0× · tick at the 2.0× threshold

2 of 4 slices over threshold

Evidence-linked improvement

An aborted run says something about the plan

What stopped a run at night is worth more than the round it cost. The precondition, the deck rule or the range behind it is what has to move.

Improvement cycle · five stages

Switchback — the path turns at Improve and returns at Learn

01
Detect
Aborts, repeats and failed preconditions rise in one run cohort.
02
Diagnose
The night's logs and the deck as found are set beside what the plan assumed.
03
Improve
The rule that failed is rewritten, and the lab head signs it before a run uses it.
04
Verify
The failing conditions are run again on a rig nothing else is relying on.
05
Learn
What the night left behind is written into the checks the next run starts from.
Learn → Detect
The return edge. The envelope itself moves only with the lab head and the safety owners who set it — a limit the agent runs against is not a limit the agent may widen.

Typical build scope

Twelve workstreams across six weeks

The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, envelope and instruments, planning and scheduling, evaluation, integration, then production validation and handover.

Workstream

Week 1Week 2Week 3Week 4Week 5Week 6

01Workflow discovery and boundary definition.Week 1
02Envelope definition with the lab head and safety owners.Week 1, Week 2
03Instrument, driver and scheduler assessment.Week 1, Week 2
04Precondition reads — calibration, lots, deck.Week 2
05Campaign planning and condition proposal.Week 2, Week 3
06Scheduling and deck-separation rules.Week 3
07Watch, stop and safe-state routing.Week 3, Week 4
08Lab-head, scientist and safety-owner review workflow.Week 3, Week 4
09Run record, provenance and version capture.Week 4
10Evaluation suite and regression runs.Week 4, Week 5
11Instrument integration and rehearsed runs.Week 5
12Observability, deployment and Agent Care handover.Week 6

12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallel

Final scope and sequence confirmed in discovery

Engagement tiers

What each tier includes

Rows are the capabilities named in each tier's scope. Higher tiers include everything below them.

Capability✓ in scope · — not at this tier	PilotOne campaign, one rig	ProductionProduction integration	AdvancedSeveral rigs / sites
Introduced at Pilot
Envelope definition and checking	✓	✓	✓
Precondition and calibration-status reads	✓	✓	✓
Deck separation and incompatibility rules	✓	✓	✓
Watch, stop and safe-state routing	✓	✓	✓
Run record and provenance capture	✓	✓	✓
Lab-head and safety-owner authorisation	✓	✓	✓
Baseline evaluation	✓	✓	✓
Introduced at Production
Scheduler and instrument integration	—	✓	✓
Observability and evaluation	—	✓	✓
Introduced at Advanced
Several rigs, sites and instrument families	—	—	✓
Multi-programme and enterprise controls	—	—	✓
Build price	From $5,000	From $8,000	Custom quote

Final build price: Confirmed after discovery based on the instruments and scheduler in scope, campaign types, run volume, authorisation controls, site coverage and deployment requirements.
Separate from build: Build pricing is separate from recurring Agent Care, which covers managed monitoring, evaluations, incidents and verified improvements after launch.

What we need from you

What you bring, and what we build with it

Each input maps to a piece of build scope and a week in the delivery timeline.

You bring

We build with it

01The envelope you are willing to let a run happen inside
→
Envelope definition with the lab head and safety owners
Week 1
02Where your approval boundary sits and who signs
→
Approval-boundary definition and authorisation rules
Week 1
03Driver, scheduler and calibration-record access
→
Instrument, driver and scheduler assessment
Week 2
04A campaign your scientists have already run by hand
→
Campaign planning, condition proposal and precondition reads
Week 2
05Your own rules for what may not share a deck
→
Scheduling and deck-separation rules
Week 3
06Runs that went wrong — an abort, a bad deck, a lost night
→
Evaluation suite, regression runs and failure-mode testing
Week 4
07Named scientists, the lab head and your safety owners
→
Review workflow, then rehearsed runs and production validation
Weeks 5–6

Nothing else is required

Deployment, documentation and Agent Care handover are ours.

Delivery timeline

Four phases across six weeks

Phases are drawn over the weeks they actually occupy. Week 5 is the first week an instrument moves for the agent, and it is rehearsed before it is live.

Phase

DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6

Week focus

W1Envelope and the stop agreed with your safety owners

W2Instruments, drivers, scheduler and precondition reads

W3Condition proposal, scheduling and deck separation

W4Run-record capture, stop tests and cohort slices

W5Instrument links, rehearsed runs and amendments

W6Production validation, live runs and Agent Care handover

Reading the band: Bars sit over named work, and an empty week in a row is empty on purpose. The envelope and the stop are built in week 1; no instrument moves under a rule that was not agreed there.
At the end of W6: Your scientists have watched runs the agent planned, including at least one they stopped. Envelope checks, precondition reads and the version map move to Agent Care.
Duration: Six-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.

Next step · Biotechnology AI agent

Build an experimentation agent around the rigs you already run.

Show us one campaign, the instruments it runs on and what your lab does today when a run fails overnight. The stop matters more than the envelope, and who it wakes matters more than the stop. We design all three in week 1 with your lab head and your safety owners, and rehearse them before an instrument moves.

Typical delivery: 4–6 weeks
Deployment: Your instrument stack
Run approval: Lab head and safety owners
After launch: Agent Care available

Nestack Agents · Autonomous-lab experimentation

AGT-BT-12 · Agent Care available after launch

Autonomous-Lab Experimentation Agent (Plan to Run Record)

Test every run against its envelope

Turn a returned round into the next one

Stop the run before the deck does

Instruments & robotics

Scheduling & control

Laboratory records

Autonomous-lab experimentation

Safety & containment

Observability & evaluation

Condition proposed outside the envelope

Optimiser chases an artefact

Run started on a lapsed calibration

Deck does not match the plate map

Incompatible work booked together

Overnight failure raises nothing

Manual intervention never recorded

Detect

Diagnose

Improve

Verify

Learn

Build an experimentation agent around the rigs you already run.