Skip to content
Planning & productionChemicals & Process IndustryFood & BeveragePharma & Biotech

Check batch records against the recipe

Every deviation in weights, temperature or time is flagged, so the batch is released sooner.

Today

Batch records are reviewed by hand before release, often days after production. Deviations are found late or missed. Meanwhile the goods wait in the warehouse, or they have already shipped.

An example

At Tarvina, batch L26314-1 of sauce SC-250 shows a hot-hold time below the recipe minimum in step 4. The agent flags the value, links the lab result at pH 4.2 and puts the batch on hold until quality decides. All other values of the batch are within tolerance.
Fictional company, typical workflow.

Your data, wherever it lives

Batch records come today from the process control system and the MES, some still as scanned paper sheets with handwritten entries; recipes and specifications sit in the ERP and in spreadsheets, lab results in the LIMS, weighings in the scale logs. demi reads, understands and links them per batch, with your rights. The AI checks every value right after the batch ends instead of days later, and quality decides on release.

Where the data lives today

  • Machines & sensors
  • MES
  • Scans & paper
  • ERP
  • Office files
  • Databases
Data LayerOne view of everything, with your rights

How demi solves it

Three layers in this order: connect the data first, then the rights, then the AI.

  1. 1 · ConnectData Layer

    The case needs data from the MES, LIMS, ERP and spreadsheets. demi replaces nothing and links batch records from the process control system with recipes, specifications, lab results, raw-material batches and weighings. demi only writes back after approval.

  2. 2 · PermitPermission Layer

    Batch release stays with quality. Operators see their own batch, recipes only authorized roles, and every step is recorded.

  3. 3 · ActIntelligence Layer

    The agent checks every recorded value deterministically against the recipe and the stored tolerance and lists deviations with step, target and actual value. It links the lab results and prepares the release summary.

How it runs

  1. 1

    Read in the batch record once the batch is complete

  2. 2

    Check every value against recipe and tolerance

  3. 3

    Assign the batch's lab results

  4. 4

    List deviations with context, hold the batch if needed

  5. 5

    Hand the release summary to quality

What changes

  • Faster batch release

  • Every deviation listed against its limit

  • Audit-ready batch records

What does it bring you?

Check it with your own numbers

Every starting value is an assumption you can change. The calculation sits right below, step by step.

Assumption, editable

Your numbers

Result

+320 hfreed per year

Assumptions and calculation

demi compares weights, temperatures and times with recipe and limits; you release the batch.

20 min → 12 min per case

How does it run today?

What is already digital saves less: the factor lowers the share demi brings.

How we calculate

200 batch records × 20 min × 40% × 1.0 (manual) × 12 months = 19,200 min = 320 h

Value per year, before demi costs

Freed per year+320 h

Assumption: labor cost of $48.62 per hour in US manufacturing in June 2026 (BLS), plus workplace, IT and overhead.

= Value per year, before demi costs

+$20,800

gained per year

320 h ÷ 1,760 h per role = 0.2 full-time roles

An estimate, not a promise. The starting values are assumptions for an industrial company with 150 to 500 people.

Combine with more cases and get the package

Questions about this use case

Where does the batch data come from?

It comes from your process control, MES or weighing systems; how it gets to demi, we clarify in a conversation. The case also needs recipes and specifications from the ERP or recipe management, and lab values from the lab system. None of these systems is replaced.

Does demi check lab results too?

Yes. Lab values are assigned to the batch and checked against the specification just like process values. If a required result is missing, it appears as an open point in the summary.

Who releases the batch?

Quality. The agent checks, holds the batch on a deviation and prepares the decision. A person sets the release or final hold, with the reason in the record; the status goes back after approval.

Who can see our recipes?

Only the roles you allow. For the check, the agent needs targets and tolerances, not the full recipe in every view. Operators see their batch and its deviations.

Does this replace our HACCP or GMP system?

No. demi makes the review faster and fully documented. Which values are critical and how deviations are assessed is decided by your quality experts.

See this case with your data

In the demo we show you the workflow on your own systems.

Your configurator

No use cases yet

Your configurator is still empty

Add a use case from any card or case page and see what it brings per year, with the calculation. Free, no sign-up, no commitment: try it out and change any number.

Browse use cases