Follow a sample from receipt to result — custody, location, storage excursions, aliquot parentage, timepoints and turnaround — and hold what will not confirm, for your analyst, QC supervisor and QA to act on.
Take the sample as it arrives — the request, the labels, the custody record and the conditions it travelled in.
02
Read the LIMS as the system of record — logins, locations, aliquots, storage, timepoints and test assignments.
Reason
03
Check the login against the request: identity, containers, condition on receipt and the tests asked for.
04
Follow custody, location, aliquot parentage and consumed volume, and mark where the chain does not join up.
05
Set storage readings, timepoints and turnaround against the protocol and the specification in force.
Decide
06
Route a reading outside its limits into the investigation procedure your SOP defines, to a named person.
07
Hold anything whose identity, custody or record will not confirm, and say what is missing.
Out
08
Present the sample's history, the gaps found and the record standing behind each result.
09
Put an excursion in front of a person with the chamber log and the product's own stability data beside it.
→Product statement
The agent tracks, compares and routes inside the approval boundaries agreed during implementation, and writes carry a trail that is attributable and reviewed. Releasing a result, calling one invalid, authorising a retest or a resample and disposing of a sample stay with QC and QA.
Example workflow
One sample, end to end
AgentHuman
1Sample received and loggedThe request, the container labels, the condition on receipt and the custody record that came with it
2Identity and custody checkedLogin set against the request: identity, container count, aliquot parentage and every move in the chain
3Conditions and timepoints readStorage readings against the protocol limits, stability and retention timepoints, expiry and consumed volume
4Tests and record assembledTest assignment against the specification in force, turnaround against the plan, and the record behind each result
No human action required
Stages 1 to 4 run without a person in the loop — nobody is asked to read a sample file until custody, conditions and the record behind the tests have been checked. A reading outside its limits leaves for a named person the moment it is seen.
5DecisionSplits on the identity check and the confidence gate
Identity and record confirm
Goes to the analyst as a checked sample file.
Custody or record will not confirm
Held with the unconfirmed link marked.
Analyst, QC supervisor and QA
Read the history, the excursion and what would not confirm, then run the investigation your procedure defines — a result is invalidated on a cause that investigation finds, not on a retest that came back cleaner.
Accept · Correct · Investigate
Accepted — handed back▼
6LIMS updatedWritten only where access and policy allow, with an attributable trail; no result is approved and none released
7Outcome evaluatedExcursions missed, flags a supervisor dropped, records still short at review and corrections by cohort
Corrections
Flags a supervisor drops or rewrites are counted in the evaluation.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Approving or releasing a result.
Deciding an out-of-specification result is invalid.
Authorising a retest or a resample.
Disposing of, consuming or reassigning a sample.
Automation boundaryAgent acts unaided
✓Check the login against the request and the labels.
✓Follow custody, location, aliquot parentage and consumed volume.
✓Compare storage readings, timepoints and turnaround with the protocol.
✓Flag the gaps and hold what will not confirm.
Write actions run only inside the approval boundaries agreed during implementation. Releasing a result is not among them.
Changing a specification, method or stability protocol.
Accepting a storage excursion as having no impact.
Closing an investigation or naming its cause.
Changing the tracking rules, limits or thresholds.
Example output
One stability pull, annotated
Everything the agent flags is attached to the sample and the record it came from.
Sample file · single stability timepointIllustrative example
Sample
Storage
Custody
Proposed
Confidence
Result status
Stability pull, mid-point
Excursion during a transfer
Unbroken
Assess against stability data
92%
Left for QC and QA
As receivedThe pull, its timepoint and the conditions it was held in, as the LIMS and the chamber log hold them.
Evidence usedChamber log for the periodCustody and aliquot chainStability protocol timepoint
Why it is flaggedThe reading left its limits in transfer, so this product's own stability data decides.
ActionAcceptCorrectInvestigate
What the score decidesConfidence decides how much a supervisor re-checks, not whether a result may stand.
Value
Where AI adds value
The same four claims, placed at the point in the workflow where each one applies.
Where the value landsValue 01 – 04
Every sample in the laboratoryFrom receipt to disposition
03Tracking & checks
Keep identity and custody joined up
Use the request, the labels, the custody chain and the specification in force — identity is what every result above it rests on.
01Approved path
Stop rebuilding the sample's history
Custody, location, aliquots, storage and timepoints arrive assembled, so an analyst starts from the sample file rather than from five screens.
02Human review
Raise what a result cannot rest on
Storage excursions, broken custody links, missed timepoints and records short of what a result needs reach a named supervisor as a list.
04Build an evidence trail
Retain the readings taken, the rule behind each flag, the custody links checked, the confidence and every supervisor and QA edit — on both paths.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
Integration availability depends on the client's existing systems and API access.
Agent controls
Six layers between the model and the sample record
Each control wraps the one inside it. A check clears every layer before it reaches the sample file, and the trail it leaves is written to be reviewed, not only kept.
L6 · Outermost — last line of defenceInward → L1 · closest to the model
L6Rollback / safe modeRestrict automation if evaluations or production signals degrade.Roll back
L5Attributable trailReads, flags, edits and model, prompt and rule changes are recorded for a defined review.Record
L4Analyst and QA gateDefine what may be written as a draft; release, retest, resample and disposal wait for a person.Gate
L3Investigation routingReadings are tested against their limits and routed to the procedure your SOP defines; one that reaches a queue instead is the failure measured here.Escalate
L2Protocol limit testsReadings and timepoints are tested against the protocol and the specification version in force.Test
L1Identity bindingEach check names the login, container and aliquot it came from; unbound checks are held.Verify
Model coreCheck proposed — the custody link, the reading, the timepoint, the record gap and confidence
L1 – L2Decide whether a check may stand
L3Routes a reading to the procedure, and is measured on it
L4 – L5Leave release to QA, keep the trail reviewable
L6Pulls automation back when signals degrade
How Nestack evaluates it
Evaluate the whole sample file — not only the flag at the end.
Coverage runs the whole depth of the workflow, and every layer is cut by slice.
Surface — the sample file the analyst opens
Depth of coverage ▼
E1Final-output evaluationWas the flag real, and the rule it names the one in force?
E2Custody evaluationDid identity, aliquot parentage and every move join up?
E3Condition evaluationWere readings and timepoints read against the right protocol?
E4Routing evaluationDid a reading outside its limits enter the procedure, and how fast?
E5Slice evaluationHow does performance change across specific sample cohorts?
E6Business outcomeHow much was re-checked, and what was still missing at review?
Floor — the result a supervisor and QA stand behind
Failure modes
Where each failure originates in the agent
Seven failure modes plotted against the five stages of the agent lifecycle. The most cited of them is a result treated as invalid because a repeat came back cleaner, rather than because an investigation found a cause.
Agent lifecycleDirection of processing →
01 · Intake / login2 modes
LS-01
Custody gap reads as a clean chain
A move with no record reads as continuous, so identity stops being provable.
LS-02
Aliquot inherits the wrong parent
A child tube is linked to the wrong parent and carries its history.
Stage gathersThe request, the labels, the custody record and the LIMS
02 · Tracking1 mode
LS-03
Excursion smoothed into a period mean
A spike is averaged away instead of assessed against the stability data.
Stage comparesCustody, conditions and timepoints against the plan
03 · Assessment2 modes
LS-04
Reading outside limits raised as a query
It reaches a data queue rather than the investigation procedure.
LS-05
Cleaner repeat shown as the answer
A later passing result sits above the original as though it settled it.
Stage flagsReadings, gaps and records short of what a result needs
04 · File / handoff1 mode
LS-06
Record reads complete when it is not
Raw data missing behind a result does not show in the file.
Stage returnsThe sample file an analyst and a supervisor read
05 · Change / Version1 mode
LS-07
Limit changed outside change control
A threshold moves without the approval the system requires.
Stage tracksSpecification, limit, model, prompt and rule changes
Sev-1 · a result loses the procedure behind itSev-2 · the sample file misstates the sampleSev-3 · flags degrade, the laboratory re-checks
A tube that changed hands is not a tube that never left
Supervisors drop or rewrite flags before the file is worked, and that is what this number counts. Paper custody has to be transcribed before it can be checked, and a frozen shipment arrives with somebody else's history.
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
Samples received from a CMO
5.7%
3.7×
Review
Hand-written and scanned custody
4.4%
2.9×
Review
Cold-chain shipments with an alarm
2.9%
1.9×
Watch
Routine in-house release samples
1.2%
0.8×
Normal
Bar: dropped-flag lift vs. in-house release baseline · scale 0–4.0× · tick at the 2.0× threshold2 of 4 slices over threshold
Evidence-linked improvement
Nothing is fixed at the bench and left there
A flag the supervisor rewrote points at a limit, a custody rule or a protocol map. That is where the fix goes, under change control, before the next run.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
A cohort starts costing more re-checks than it used to.
02Diagnose
The cohort is the clue — samples in it share a route into the lab.
03Improve
The change clears your change control before the agent uses it.
04Verify
Affected samples are read again from login, the failures included.
05Learn
The sample that failed is kept, and later releases run against it.
Learn → DetectThe return edge. A limit or a rule the agent checks against lives in a validated system — it moves with a named approver and a record, not quietly between runs.
Typical build scope
Twelve workstreams across six weeks
The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, access and login, custody and conditions, evaluation, integration, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Workflow discovery and boundary definition.
02LIMS, instrument and chamber access review.
03Specification, limit and protocol mapping.
04Sample login and identity checks.
05Custody, location and aliquot parentage tracking.
06Storage, excursion and stability-timepoint comparison.
07Turnaround and test-assignment checks.
08Record-completeness checks behind a result.
09Investigation routing to a named person.
10Analyst, supervisor and QA review workflow.
11Evaluation suite and regression samples.
12Integration, deployment and Agent Care handover.
12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallelFinal 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 tierPilotOne sample type, one siteProductionProduction LIMS integrationAdvancedSeveral sites / systems
Introduced at Pilot
Login, identity and custody checks✓✓✓
Storage, excursion and timepoint comparison✓✓✓
Investigation routing to a named person✓✓✓
Attributable trail written for review✓✓✓
Release left to a supervisor and QA✓✓✓
Record-completeness checks✓✓✓
Baseline evaluation✓✓✓
Introduced at Production
LIMS, instrument and chamber integration—✓✓
Observability and evaluation—✓✓
Introduced at Advanced
Several sites, product families and systems——✓
Multi-site and enterprise controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on the sites and systems in scope, sample types and volume, storage and stability coverage, review controls and deployment requirements.
Separate from buildBuild 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 bringWe build with it
01Your specifications, limits and stability protocols→Specification, limit and protocol mappingWeek 1
02How a sample is logged, labelled and handed over today→Sample login and identity checksWeek 2
03Read access to the LIMS, chamber logs and instrument data→LIMS, instrument and chamber access reviewWeek 2
04Custody records as they really are, paper included→Custody, location and aliquot parentage trackingWeek 3
05Your out-of-specification procedure, as your SOP writes it→Investigation routing to a named personWeek 4
06Samples that went wrong — a mix-up, a missed excursion→Evaluation suite, regression samples and failure-mode testingWeek 4
07Named analysts, QC supervisors and a QA reviewer→Review workflow, then pilot samples and production validationWeeks 5–6
Nothing else is requiredDeployment, documentation and Agent Care handover are ours.
Delivery timeline
Four phases across six weeks
Phases are drawn over the weeks they actually occupy. Week 3 is where custody and storage meet, and the later checks rest on both.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Specifications, limits, protocols and the automation boundaryW2LIMS, chamber and instrument access, and sample login checksW3Custody, aliquot parentage, storage and timepoint comparisonW4Investigation routing, record checks and sample cohort slicesW5LIMS integration, first supervisor-reviewed sample filesW6Production validation with your analysts, then Agent Care handover
Reading the bandBars cover only the weeks their work is named in. Nothing runs on a live sample before week 4, which is when routing is put against your own out-of-specification procedure.
At the end of W6A supervisor has worked a real sample file and said where it was wrong. Limits and the version map pass to Agent Care after that.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Biotechnology AI agent
Build a sample-tracking agent around the LIMS you already work in.
Show us one sample type, the systems its history sits in and how a result outside specification reaches your QC supervisor today. We write down where the agent stops before we write down what it does. An out-of-specification procedure that software is allowed to shorten has stopped being a procedure.
