Start with neil. Run on Seal.
Start with a question across existing records or a procedure to configure. neil assembles the evidence, answers with sources and proposes the next piece of work. You can begin without replacing the systems you rely on.
When you run the process in Seal, its instructions, measurements, exceptions and approvals become connected records. That is what makes the next investigation different: it starts with the history of the operation, including what changed and why.
One platform for the whole batch
Manufacturing execution, LIMS, electronic lab notebooks, quality, training and inventory share one configurable platform. 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. The specifications and verification evidence stay with the configuration as it changes.
The manufacturing blueprint is a starting configuration on this foundation. Extend it into lab or quality work without creating a separate record of the same batch. Where an existing MES, LIMS, QMS or ERP remains in place, connect the records needed for the job and agree which system owns them.
Already 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.
At Skye Biologics, the same platform covers batch records, document control, training, inventory and instrument integration. Its story shows the manufacturing foundation in use today: the process, its source data and its review on one platform.
Read the Skye Biologics story.
What neil does for manufacturing
Configure 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.
Answer 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 and answers with sources the team can inspect—including records in connected systems.
Investigate 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. Records and approved decisions retained in Seal become working context for the next job; customer data is not used to train AI models. See neil at work or review AI and data controls.
What 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 a prerequisite 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.
The example records the measured value, device identity and source timestamp together. Where a value is entered manually, configure the required verification and retain that entry’s provenance too.
Check the material before it enters the batch
Scan the lot, check its status and record the quantity against the configured tolerance. In this example, the dispense record connects the physical material, its release status and the measured amount to the operation that used it.
The accepted dispense links the material lot and actual quantity to the operation, providing the source for inventory reconciliation and batch genealogy.
Put lab results and deviations in the same context
An in-process test belongs to a specific batch and operation. Seal links the sample, method, specification and result so manufacturing and the lab can work from connected records.
Configure the dependency between the result and the next operation. Here, pH 7.10 meets the example range, but the result still needs review. Step 13 stays blocked until that review is recorded. An acceptable number and an authorised decision are distinct records.
If a check raises a deviation, the affected batch, equipment and procedure version remain available in the investigation. Manufacturing, the laboratory and quality can follow the same chain of evidence.
Explore laboratory workflows or quality management.
Review exceptions without losing the full record
Review by exception helps reviewers find 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 brings the original timestamps and applicable requirement into review. The authorised reviewer assesses the departure, records the disposition and retains the supporting evidence. The full execution history stays available alongside the exception. These are sample records and limits; the approved process defines the real requirements.
Trace materials through the work
Link raw-material lots, intermediates and finished units to the operations that use or produce them. Equipment, operators and associated test results provide the context around those relationships.
That supports both directions of a trace: 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.
See the available system connections. Capture from supported equipment is described on the instruments page; direct instrument control and data capture are separate scopes.
See what is running, waiting and ready
Follow batch progress alongside equipment use, cleaning and quality holds. A status has a record behind it: the current operation, the pending test, the deviation under review or the clearance needed for the next run.
Change the process without losing its history
An investigation becomes useful when its conclusion can change how work runs. neil can propose a revised configuration from the procedure and supporting evidence. The team reviews the differences against the current version.
Continuous validation is built into the platform. User requirements (URS), functional and design specifications (FS and DS), the configuration specification (CS) and automated verification/UAT evidence stay linked to the process version. They are maintained with the configured work, not as a disconnected handover pack.
For the receiving-readiness gate, the requirement, configuration change and tests belong together. Test the blocked path when acknowledgement is missing and the permitted path when it is recorded. Retain results, exceptions and approval with the new version. 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 evidence to assess its effectiveness. That connects investigation, controlled change and the next run.
Read how continuous validation works in Seal.
Work on the questions that matter
Connected execution is the foundation for deeper process understanding. Our ambition is to put increasingly capable AI to work on yield, scale-up and patient-specific production. Start with the evidence available today, identify what is missing and turn promising hypotheses into experiments the team can evaluate.
Why did yield change?
A lower yield might coincide with a different material lot, an extended hold, an equipment change or a revised method. Compare those records alongside the process version and laboratory results. Establish which runs are actually comparable, identify missing measurements and separate observations from possible explanations.
The useful output is an investigation the process team can act on: 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.
What changed when we scaled up?
Carry development experiments and their rationale into the manufacturing record. Compare equipment, working volumes, mixing conditions, sampling methods and hold times across the transfer. Preserve the context behind a parameter instead of leaving the receiving team with a number and no explanation.
The ambition is a transfer that starts from accumulated knowledge. Process scientists still determine what can be carried across, what needs a new model or experiment, and what must be demonstrated on the receiving equipment. Seal provides a place to keep that reasoning, the resulting procedure and its verification connected.
Why are we investigating the same exception again?
A closed deviation should leave more than a completed form. Keep the original finding, competing explanations, corrective action and effectiveness evidence with the affected process. On a later investigation, neil can use the accessible history to establish what was tried and what remains unresolved.
The objective is to turn a recurring investigation into a durable improvement. A proposed change can move into a versioned workflow in Seal, with its requirements, verification and approval attached. Subsequent runs provide evidence for the team to assess whether the change addressed the problem.
What does manufacturing for one person require?
Patient-specific production makes the relationship between identity, material, process and disposition central to each run. The design must account for chain of identity and custody, time-sensitive handoffs, the procedure version used and the evidence required before release.
Our long-term ambition is to make that complexity manageable without rebuilding the operational system for every therapy. A shared platform gives teams a place to configure those relationships and controls. Therapy-specific workflows, interfaces and identity checks still need to be scoped, verified and approved for their intended use.
A medicine made for every person
That is our mission. Discovering a medicine is only part of the challenge. It must also be made reliably, tested and delivered. For a therapy made from one person’s cells, the operational system must carry the identity, process and proof of that individual run.
Our long-term ambition is biomanufacturing that accumulates knowledge as it operates. Scientific intelligence needs access to the experiment behind a parameter, the conditions behind a result and the reasoning behind a change. It also needs somewhere to test an idea in the physical world and retain what that test established.
Seal provides the shared operational foundation; neil puts the available context to work. The aim is to carry knowledge forward from development to manufacturing, between sites and from one dose to the next. Teams can spend more of their effort improving the process because the history is already there to work from.
That is the future we are building toward: a shorter path from promising science to medicine people can receive.
Start with one job. Expand on the same platform.
Choose 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 would look like. Use sample material or arrange an NDA before sharing confidential records.
Inspect the result
For an investigation, examine neil’s findings against the cited sources. For an agreed process evaluation, see a working configuration and validation pack in 48 hours. Run the workflow, try its exception paths and inspect the requirements, test results and configuration history.
Decide 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.
