FLUXLINESchedule board

Manufacturing production planning

Plan production around costly changeovers.

Fluxline helps small manufacturers sequence production orders to cut cleaning, tooling and setup time between jobs. Machine learning estimates changeover durations from production records; an optimisation engine recommends schedules that respect deadlines and machine availability — for planners to approve.

In the order received

Sequenced by Fluxline

478 min → 242 min of changeover2 → 0 late jobs3.9 h of press time backTen fictional jobs on one flexo press. Hatched = changeover. Shade = ink darkness.

The problem

Some job changes take ten minutes. Others take an hour.

Going from a dark ink to a light one means a full wash-up. A new substrate means re-threading; a different width or plate set means re-tooling. The order you run jobs in decides how much of the shift goes on making product — and in most small plants it is decided on a whiteboard.

  • Wash-up per shade lighter+5.7 min
  • Per shade darker+2.0 min
  • Material change+15.1 min
  • Per 100 mm width change+3.1 min
  • Plate change+11.8 min

What drives changeover time on this fictional line, learned from 200 past changeovers. Typical error on 40 held-out changeovers: ±1.9 min.

Estimated changeover minutes, from row job to column job
404401405402403409
404 Bread bag, white—1028494748
401 Bread bag, wholemeal14—26474546
405 Detergent refill3529—414748
402 Rice sack 25 kg605545—4950
403 Snack pouch, chilli62565453—21
409 Coffee pouch6357555421—

Production sequencing

An order for the day that respects every due time.

Fluxline searches thousands of possible job orders, scoring each by total changeover time and any lateness — with lateness weighted twenty times heavier. The planner sees the recommendation, the reasoning and the alternative, then approves.

  1. from yesterday +37′J-401Bread bag, wholemealLight · PE film · 640 mm
  2. +14′J-404Bread bag, whitePastel · PE film · 640 mm
  3. +22′J-408Ice bagPastel · PE film · 700 mm
  4. +26′J-410Detergent 5 kgMid · PE film · 760 mm
  5. +8′J-405Detergent refillMid · PE film · 760 mm
  6. +45′J-407Flour sack 10 kgLight · Kraft paper · 900 mm
  7. +12′J-402Rice sack 25 kgDark · Kraft paper · 900 mm
  8. +47′J-406Snack pouch, plantainDark · BOPP film · 520 mm
  9. +10′J-403Snack pouch, chilliBlack/process · BOPP film · 520 mm
  10. +21′J-409Coffee pouchBlack/process · BOPP film · 480 mm

Light to dark, same substrate and plates together, urgent jobs early. Fictional jobs.

Scenario comparison

See what an urgent order or a breakdown really costs.

Add an order or block out the press, and Fluxline re-plans in seconds — showing changeover time, late jobs and when the shift finishes, before anyone commits.

Tomorrow as planned478 min changeover · 2 late242 min changeover · 0 late
Urgent order arrives (due 12:00)529 min changeover · 3 late307 min changeover · 0 late
Press down 10:00–12:00478 min changeover · 5 late299 min changeover · 0 late
Both at once529 min changeover · 6 late325 min changeover · 2 late

When something has to give, Fluxline says which job will be late and by how much — the planner decides.

Performance tracking

Planned against actual, every shift.

Each shift’s actual run and changeover times are recorded against the plan. The gaps show where estimates are off — and every new record makes the next estimate better.

How it works

From a spreadsheet to tomorrow’s run sheet.

  1. C

    Import

    Upload your job list, changeover log and shift reports as spreadsheets.

  2. M

    Learn

    Fluxline fits a changeover model to your own records and shows its error.

  3. Y

    Sequence

    It recommends an order for the next day that respects due times and downtime.

  4. K

    Approve

    The planner adjusts if needed and approves; actuals flow back after the shift.

Ground rules

Planners approve

Nothing runs on Fluxline’s say-so. A planner approves each daily schedule and can move any job.

Estimates show their error

Every changeover estimate is shown with the model’s typical error on records it never saw.

Deadlines first

The sequencer would rather spend changeover minutes than miss a due time — and says so when it can’t avoid it.

Your records, your model

Estimates learn from your own line, not an industry average.

Why it matters

Most plants are small, and changeover time can change.

Who it’s for

Small plants where changeovers eat the shift.

Packaging manufacturers

Films, bags and cartons with frequent size and print changes.

Printing businesses

Ink, plate and substrate changes between short runs.

Plastics processors

Colour and material purges on extrusion and moulding lines.

Contract manufacturers

Many customers, many recipes, cleaning between each.

Pricing

Priced by production line.

Illustrative pricing for a proposed product, to be agreed with pilot plants.

Line

$290per line / month

  • One production line
  • Spreadsheet imports
  • Changeover model
  • Daily sequencing and approval
Request a pilot

Plant

$690per month

  • Up to 4 lines
  • Everything in Line
  • Scenarios and downtime planning
  • Planned vs actual reporting
Request a pilot

Group

Custom

  • Several plants
  • ERP or MES integration on request
  • Single sign-on
  • Agreed data-handling terms
Contact us

Technology

How we use Amazon Web Services.

Fluxline’s work is a cycle: production records come in every shift, changeover models are retrained as more records arrive, and sequencing is a compute-heavy search that runs whenever an order or a machine changes. Designing on AWS lets storage, model training and on-demand optimisation run as managed services, and keeps each manufacturer’s data isolated as they grow from one line to a whole plant.

  1. Stage 1

    Import

    Amazon S3AWS Lambda

    Spreadsheet exports of jobs, changeover logs and shift reports land in per-customer storage; Lambda validates and normalises them.

  2. Stage 2

    Learn changeovers

    Amazon SageMaker AI

    A duration model is trained on past changeovers — shade, material, width and tooling either side — and reports its error on held-out records.

  3. Stage 3

    Jobs & constraints

    Amazon DynamoDB

    Open orders, due dates, machine calendars, material availability and approved schedules are stored per line.

  4. Stage 4

    Optimise

    Amazon ECSAWS Fargate

    Containerised optimisation runs on demand to search job sequences that cut changeover time without missing due dates.

  5. Stage 5

    Planner workspace

    Amazon API GatewayAmazon Cognito

    Authenticated schedule, scenario and approval APIs serve the schedule board, with planner and supervisor roles.

Across every stage

  • AWS Lambda runs validation and scenario triggers
  • Amazon CloudWatch monitors imports, training jobs and solver runs
  • AWS KMS encrypts each manufacturer’s production data
  • Amazon SES sends approved schedules to shift supervisors

Services and their role in Fluxline

ServiceRole
Amazon S3Stores imported job lists, changeover logs, shift reports and exported schedules, separated by customer.
AWS LambdaValidates imports, triggers re-planning when an order or machine changes, and records planned-vs-actual results.
Amazon SageMaker AITrains and hosts the changeover-duration model for each line, and tracks its accuracy as new records arrive.
Amazon DynamoDBHolds jobs, due dates, machine calendars, constraints, approved schedules and the decision log.
Amazon ECSRuns the sequencing optimiser as a containerised service, isolated from the rest of the platform.
AWS FargateSupplies compute for each optimisation run on demand, so a long search never slows the workspace.
Amazon API GatewayExposes the schedule, scenario and approval endpoints, plus the website’s pilot-request intake.
Amazon CognitoSigns users in and separates planner, plant-manager and supervisor roles.
Amazon SESSends approved schedules and pilot-request notifications.
Amazon CloudWatchCollects logs and metrics for imports, model training, solver run time and API errors.
AWS KMSEncrypts production data at rest with customer-specific keys.

Proposed, not deployed. This website and the schedule board run in your browser on fictional data.

Team

The founder behind Fluxline.

Augustina Oyetade

Founder

Augustina founded Fluxline after watching small plants lose hours a day to changeovers that a better job order would have avoided — planned on a whiteboard because scheduling software was built for factories ten times their size. Augustina leads product, customers and every pilot.

  • Product
  • Plant pilots
  • Production planning

Progress & pilot programme

Bring one line and its spreadsheets.

Fluxline is in its building stage and opening its first pilots. A pilot covers one production line: we import your job lists and changeover records, fit the model, and your planner approves a recommended schedule each day while we compare plan and actual.

Where Fluxline is today

2026Company foundedBy Augustina Oyetade, to give small plants the scheduling tools large ones take for granted.
DonePlanning method definedChangeover model from your own records, a sequencer that respects due dates and downtime, planner approval.
DoneSchedule board prototypeSequencing, scenarios, approval and planned-vs-actual shown on a fictional flexo line.
DoneAWS reference architectureData intake, model training, optimisation and planner workspace designed.
NextFirst pilotsOne production line per pilot, from your spreadsheet exports, with schedules your planner approves daily.

We use these details only to respond to your request. See the privacy notice.

FAQ

Frequently asked questions.

What data do we need?

A list of upcoming jobs with due dates, and a log of past changeovers — even a rough spreadsheet. The more history, the better the estimates.

Does Fluxline control our machines?

No. It recommends a sequence and a planner approves it. It does not connect to or control equipment.

What if a job has to go first?

The planner can move any job; Fluxline re-calculates changeover time and lateness straight away.

Is Fluxline live?

Not yet. It is a proposed product; the schedule board is a prototype running in your browser on fictional jobs.

Contact

Talk to the Fluxline team.

Questions about the product, the pilot programme, spreadsheet imports or how production data is handled. Messages go directly to the founder.

Emailaugustina@fluxline.space