Summary
- The problem
- Answering a batch question or investigating an exception means gathering records from separate manufacturing, laboratory and quality systems. When the investigation concludes, carrying the change into the next run is another manual project.
- Seal’s approach
- Manufacturing execution, laboratory, quality, training and inventory share one platform instead of separate MES, LIMS and QMS systems, so a result, deviation or material lot links to the step it concerns. neil answers with sources and proposes configuration changes; your team verifies and approves them.
- Evidence
- MiAlgae: 75% less documentation time. Skye Biologics: 40% fewer non-conformances and 35% higher production throughput.
- Where to start
- One job: a recurring exception, a batch question or a representative procedure. Book a demo.
1One platform for the whole batch.
Manufacturing execution, LIMS, electronic lab notebooks, quality, training and inventory share one configurable platform in Seal. A lab result belongs to the batch step it governs. A deviation opens with the affected material, equipment and procedure in view. The operator’s qualification is available where the work requires it.
Forms, calculations, dependencies and review gates define how the work runs. Permissions, signatures, audit history and process versions are shared controls, and the specifications and verification evidence stay with the configuration as it changes. When a process runs in Seal, its instructions, measurements, exceptions and approvals become connected records, so the next investigation starts with the history of the operation, including what changed and why.
You can begin without replacing the systems you rely on. Where an existing MES, LIMS, QMS or ERP remains in place, connect the records needed for the job and agree which system owns them. Explore the Seal platform.
1.1Why teams choose Seal for manufacturing execution
Build the manufacturing system around your process. Material eligibility, equipment readiness, operator instructions, QC and review belong to the same workflow, so the batch record grows as the work happens.
When the process needs to change, give neil the procedure and the evidence behind the change. It builds a proposed configuration for your team to test and approve. An investigation can lead to a new check at the affected step; a transferred process can become the starting point for another site. Earlier batches retain the versions they ran. The platform supports both today’s production and the operation you are building next.
2Already running in production.
MiAlgae brought its electronic lab notebooks, quality management and batch records into Seal as it scaled from lab to commercial production. Its customer story reports a 75% reduction in documentation time. Operators follow guided workflows; measurements and quality events stay linked to the batch. Read the MiAlgae story.
At Skye Biologics, the same platform covers batch records, document control, training, inventory and instrument integration: the process, its source data and its review in one place. Read the Skye Biologics story.
3What neil does for manufacturing.
3.1Configure the process
Give neil a procedure or master batch record. It proposes the steps, fields, calculations, material and equipment requirements, and review gates in Seal. Process experts check the source mapping and resolve assumptions before testing and approval. Operators run the approved version.
3.2Answer with the source records
Ask “Which batches used material lot RM-208?” or “Which procedure version governed this run?” neil follows accessible manufacturing, lab and quality records, including records in connected systems, and answers with sources the team can inspect.
3.3Investigate and prepare the next change
Ask what changed between runs. neil compares timestamps, procedure versions, results and linked deviations, then proposes an investigation or process change. The finding, its sources and the proposed action stay connected for review.
In this example, the next question is whether the receiving team was ready when each hold began. The proposed gate becomes a change to assess and test. The 45-minute limit stays in place; the source records do not establish a cause.
neil follows the requester’s access permissions, and customer data is not used to train AI models. See neil at work or review AI and data controls.
4What happens during a run.
The approved workflow defines the prerequisites: procedure version, operator qualifications, material and equipment status, and line clearance. It also defines what happens when one fails: block the step, require verification or follow an exception path.
Operators follow the current instruction, scan material lots and record measurements from supported instruments. Calculations use the configured expressions and units. These are controls in the workflow: execution does not depend on neil interpreting the instruction afresh at every step.
A captured reading keeps its value, device identity and source timestamp together. Where a value is entered manually, configure the required verification and retain that entry’s provenance too.
Material is checked before it enters the batch. The operator scans the lot, the workflow checks its status and the quantity is recorded against the configured tolerance. The accepted dispense links the lot and actual quantity to the operation, which is the source for inventory reconciliation and batch genealogy.
5Review results and exceptions in context.
An in-process test belongs to a specific batch and operation. Seal links the sample, method, specification and result, and the workflow can make the next operation depend on that result. Here, pH 7.10 meets the example range, but step 13 stays blocked until the review is recorded. An acceptable number and an authorised decision are distinct records.
Review by exception brings forward the entries that need attention: a failed check, an out-of-range result, a missing approval or a documented departure from the procedure. DEV-018 carries the original timestamps and the applicable requirement into review. The authorised reviewer assesses the departure, records the disposition and retains the evidence, while the full execution history stays available alongside the exception.
These are sample records and limits; the approved process defines the real requirements. Explore laboratory workflows or quality management.
6Trace materials and see what is ready.
Raw-material lots, intermediates and finished units link to the operations that use or produce them, with equipment, operators and test results as context. A trace can run in both directions: from a finished batch back to its inputs, or from a material lot forward to the batches that used it. Agree the identifiers, units and source of record when configuring the process, particularly where inventory is also maintained in an ERP.
The same records drive facility status. Every status has a record behind it: the current operation, the pending test, the deviation under review or the clearance needed for the next run.
See the available system connections and supported instruments; direct instrument control and data capture are separate scopes.
7Change the process without losing its history.
An investigation becomes useful when its conclusion changes how the work runs. neil can propose a revised configuration from the procedure and supporting evidence, and the team reviews the differences against the current version.
Continuous validation is integrated into the platform. User requirements (URS), functional and design specifications (FS and DS), the configuration specification (CS) and automated verification and UAT evidence stay linked to the process version, rather than living in a separate handover pack.¹ For the receiving-readiness gate, that means testing the blocked path when acknowledgement is missing and the permitted path when it is recorded, then retaining the results, exceptions and approval with the new version.² Open runs keep the approved version they started on.
Intended use and risk determine the testing scope, including affected interfaces, calculations, permissions and exception paths. Approval authorises the new process; subsequent runs provide the evidence to assess whether it worked. Read how continuous validation works in Seal.
8Work on the questions that matter.
Connected execution is the foundation for deeper process understanding. Our long-term ambition is to put increasingly capable AI to work on yield, scale-up and patient-specific production. Today the work starts with the evidence available, identifies what is missing and turns promising hypotheses into experiments the team can evaluate.
8.1Explaining a change in yield
A lower yield might coincide with a different material lot, an extended hold, an equipment change or a revised method. Establish which runs are comparable, identify missing measurements and separate observations from possible explanations. The useful output is the runs to examine, the evidence for each hypothesis and the next experiment that could distinguish between them. Finding a pattern is the beginning of that work, not proof of its cause.
8.2Carrying context through scale-up
Carry development experiments and their rationale into the manufacturing record, so the receiving team inherits the context behind a parameter rather than a number alone. Process scientists still decide what carries across, what needs a new model or experiment, and what must be demonstrated on the receiving equipment.
8.3Recognising a recurring exception
A closed deviation should leave more than a completed form. Keep the finding, competing explanations, corrective action and effectiveness evidence with the affected process, so a later investigation can establish what was tried and what remains unresolved.
8.4Manufacturing for one person
Patient-specific production makes identity, material, process and disposition central to each run: chain of identity and custody, time-sensitive handoffs and the evidence required before release. A shared platform gives teams a place to configure those relationships, though therapy-specific workflows, interfaces and identity checks still need to be scoped, verified and approved for their intended use.
8.5A medicine made for every person
That is our mission. A medicine must be made reliably, tested and delivered, and for a therapy made from one person’s cells the operational system must carry the identity, process and proof of that individual run. Seal provides the shared operational foundation and neil puts the available context to work, carrying knowledge forward from development to manufacturing, between sites and from one dose to the next.
9Start with one job. Expand on the same platform.
9.1Choose the work
Bring a recurring exception, a batch question or a representative procedure. Together we agree the question to answer or workflow to run, the records needed and what a useful result looks like. Use sample material or arrange an NDA before sharing confidential records.
9.2Inspect the result
For an investigation, examine neil’s findings against the cited sources. Once we agree the process evaluation scope and receive the required inputs, see the first working configuration and supporting validation pack within 48 hours. Run the workflow, try its exception paths and inspect the requirements, test results and configuration history.
9.3Decide what goes into production
Manufacturing, quality and IT review the process, interfaces, migration, device use, training and support needed for release. The evaluation is a way to make that decision with evidence, not automatic production approval. Expand into linked operations as the scope is approved, keeping the systems you still need.
References
- 1ISPE, GAMP 5: A Risk-Based Approach to Compliant GxP Computerized Systems, second edition (2022).
- 2EudraLex Volume 4, Annex 11, Computerised Systems (2011), sections 4 (validation) and 10 (change and configuration management). European Commission
ACapabilities
| Capability | What it covers |
|---|---|
| Digital batch records | Run the approved workflow with required fields, configured checks, timestamps and signatures retained with the batch. |
| Weigh and dispense | Identify material lots by barcode and record weights from supported balances. Check identity, status and quantity against the configured requirements. |
| Batch release | Bring exceptions and supporting records into review. Batch disposition remains with the authorised team. |
| Equipment integration | Capture data from supported instrument interfaces and link it to the batch and step. Verify mapping, timestamps and recovery for the connection. |
| Electronic logbooks | Keep cleaning, usage and maintenance records linked to the equipment and batches involved. |
| Resource scheduling | Configure a schedule around rooms, equipment and teams. Read linked booking records, identify overlapping allocations and open the source record to adjust the plan. |
| Genealogy and traceability | Follow the recorded relationships from material lots to intermediate and finished batches, and back to their inputs. |
| neil for manufacturing | Ask batch questions, investigate exceptions and propose process configurations from source procedures. neil follows accessible records; process experts review the evidence and changes. |
| Material inventory | Track raw materials, intermediates and finished goods. Apply configured status, expiry and quantity checks at the point of use. |
| Operator qualification | Require the qualifications configured for a controlled step and record who performed the work. |
| Cleaning and line clearance | Link cleaning records and clearance checks to the equipment and batch. Apply the approved prerequisites before execution. |
| In-process controls | Link sampling and testing to the batch step. Configure result dependencies, hold limits and exception handling. |
| Electronic signatures | Record who signed, the signature meaning and its time against the reviewed record and version. |
| Connected quality management | Run deviations and investigations on the same platform, linked to the batch, equipment and source results under review. Connect an existing QMS where it remains the system of record. |
| ERP and inventory connections | Keep material use and stock records connected. Where inventory remains in an ERP, agree record ownership and transaction handling for the connection. |
BConnected records
CQuestions and answers
What does manufacturing that learns mean in practice?
It means retaining the context of the operation: executed runs, source measurements, investigations, approved decisions and process versions. neil can use accessible history on the next job, while Seal connects proposed changes to configuration, verification and review. It does not mean a model silently rewrites an approved process or that every run automatically improves yield.
Can neil optimise our process autonomously?
Today, neil helps answer questions, investigate results and propose process configurations or changes from accessible records. A pattern is not proof of causation. Process scientists decide which hypotheses merit experiments, assess the results and approve changes through the required controls. Deeper AI-assisted process understanding is the ambition. Changes to operating parameters and any direct equipment control need explicit scope, verification and approval.
Is this an MES or an electronic batch record system?
Both are part of Seal’s unified platform. Manufacturing execution defines the operations, instructions, checks and review gates; the electronic batch record retains what happened. Laboratory, quality, documents, training and inventory processes use the same configurable platform and connected record model. You can start with the manufacturing scope you need and extend it without treating each area as a separate software project.
What is shared across MES, LIMS, QMS and the rest of Seal?
The platform provides connected records, configurable forms and workflows, calculations, permissions, signatures, audit history, process versions and validation evidence. The domain-specific work is configured on that foundation. A batch can link to its lab sample and deviation; the underlying source records and review requirements remain available to the people who have permission to see them.
Is neil only for configuring batch records?
No. neil also answers questions and investigates results across accessible records in Seal and connected systems. It can trace a material lot into batches, compare process versions or assemble the evidence around a recurring exception. It can then propose a process configuration or improvement for review. The same agent works with the context accumulated as your team runs and reviews the work.
Can we use neil before moving manufacturing into Seal?
Yes. Start with a defined question or investigation and connect the records it needs. Agree permissions, the source of record and any write-back separately. If you later choose to execute a process in Seal, scope its configuration, interfaces and release with the process owner. An initial agent job does not require a whole-system replacement.
Does learning from our operations mean training AI on our data?
No. Customer data is not used to train AI models. Executed records, source links and approved decisions provide working context that neil can use on later jobs, subject to access permissions. More context does not give neil authority to change approved procedures or release batches on its own.
Can we start with one operation?
Yes. Agree a representative operation or batch record for evaluation. Define the boundaries with the remaining paper or electronic process, including handoffs and which system owns each record. Expand after your team has reviewed the evidence and approved the next scope.
What can neil configure from our existing records?
neil can propose operations, fields, calculations, material and equipment requirements, and review gates from the supplied procedures and batch records. Your process experts check the mapping, resolve assumptions and verify behaviour before release. No confidential upload is required to start the conversation.
What happens if a result or prerequisite fails?
The configured process determines whether a failed check blocks the next step, requires verification or follows an approved exception path. Keep the original result and any justification with the batch. Configure and test those paths explicitly; do not treat every warning as permission to continue.
Can operators use tablets or work offline?
Seal is browser-based. Evaluate the proposed devices, scanners, gloves and network conditions with the operators who will use them. Where offline operation or local capture is needed, agree the supported scope and verify interruptions, synchronisation and recovery before release.
How does Seal connect to our ERP and equipment?
Scope each connection around the job, interface and source of record. ERP connections can exchange material, order and inventory information; supported instrument connections can capture measurements and available metadata. Reading data, writing transactions and controlling equipment are separate decisions that need verification.
How are changes and validation handled?
Specifications, configuration and verification evidence are maintained in Seal. Assess each proposed change for intended use and risk, run the required checks and review exceptions before approval. Executed batch records retain the version used. The detailed assurance page explains the continuous-
Does the 48-hour evaluation mean production goes live in two days?
No. The agreed evaluation provides a working process and a validation pack to inspect. Production timing depends on the process scope, interfaces, migration, operational readiness and your team’s quality and release requirements.