Floorstack

Memory for the plant floor

The institutionalmemory ofmanufacturing.

Floorstack captures expert interventions directly on the line. Speech, video, context and asset data become structured precedent for the next similar stoppage.

Foundation models can now extract reliable procedures from speech and video. At the same time, the expertise of the best operators is leaving the plant.

From event to solutionFS-RCA · v1.0
WERKINGOLSTADT

01 / 06 · Plant alert

Stoppage reported.

01 / 07 · Manifest

Every fault you fix today is a precedent you’ll wish you had next week.

Industry runs on tacit knowledge. The kind of judgment a reliability engineer earns over twenty eight years and that vanishes the day they retire. The day the last good diagnostician on a line walks out, the line forgets.

Floorstack treats that knowledge as infrastructure. We capture the intervention, not the documentation. We index it against the asset, not against an audit. And we put it back into the operator's hands the next time the same symptom returns, on a different shift, in a different plant, in a different country.

02 / 07 · The Problem

Stops have a price tag. Forgetting has a bigger one.

$1.4T

lost annually to unplanned downtime across the world’s 500 largest manufacturers. Eleven percent of their combined revenue.

Source: Siemens, True Cost of Downtime 2024

63%

of employers cite skills gaps as the number one barrier to transformation. Manufacturing leads in reskilling need through 2030.

Source: World Economic Forum, Future of Jobs Report 2025

The same pattern surfaced in every conversation we had.

01

An unusual problem arises.

A symptom no junior has seen before. A senior intervenes.

02

It gets documented too late, if at all.

By the time someone writes it up, the language is sanitized for audit and the diagnostic reasoning is gone.

03

The next person starts from scratch.

On the next shift, in the next plant, in the next quarter. The same hypothesis tree is rebuilt by hand.

03 / 07 · Approach

Sporadic capture. Structured replay.

Four steps. Each one runs in the background until an expert begins work on a defined event.

01

Capture

First person video and ambient audio, time synced with asset and process context. Triggered, not continuous: capture starts when work begins on a fault, deviation, or non standard intervention. Ends when the event ends.

02

Structure

We convert the captured episode into structured data: symptom seen, hypothesis stated, action taken, equipment referenced, outcome observed. Vision and audio extraction, validated by the operator.

03

Index

Every record is indexed against your asset hierarchy, so the next operator can retrieve a precedent by symptom, by equipment, by alarm code, on the line they’re standing on.

04

Surface

When a similar event recurs, the relevant precedent is surfaced in seconds. The same corpus later grounds audio prompted guidance for the operator and any AI agent acting inside the plant.

05 / 07 · Why now

Three forces converged this year.

01

Foundation models grew up.

Multimodal models can now extract structured procedures from video and audio at industrial fidelity. What needed a forty person annotation team in 2023 is now a prompt and a pipeline.

02

Industrial wearables crossed the line.

RealWear and Vuzix now ship intrinsically safe IECEx Zone 1 head mounted devices in production. Hands free capture on the line moved from pilot to deployment this year.

03

The generational turnover is here.

An entire generation of senior operators is retiring at once across industries. The window to capture their judgment without asking them to write it down is years, not decades.

06 / 07 · Company

Built by AI researchers who grew up around machines.

A founding team out of TUM, with research at Stanford, Cambridge, MIT, IBM and Fraunhofer behind us. Advised by operators who’ve built and scaled industrial software before.

Sophie Tollmann, Co founder
01 / 03
FloorstackCo founder

Sophie Tollmann

Co founder

Management and CS at TUM. Research on industrial energy flexibility at Stanford. AI implementation work at Langdock (Trumpf, Würth).

Felix Hadasch, Co founder
02 / 03
FloorstackCo founder

Felix Hadasch

Co founder

Management and CS at TUM. Research at IFM Cambridge and MIT on AI in manufacturing. Built an enterprise grade AI system inside the TDK incubator.

Julian Sikora, Co founder
03 / 03
FloorstackCo founder

Julian Sikora

Co founder

Informatics and Physics at TUM. ICML published machine learning work. Currently VP at TUM.ai. Quantum ML research at Fraunhofer and IBM.

Advisors

  • Thomas Kirchner

    Co founder and former CEO, ProGlove

  • Prof. Thomas Bohné

    Founder, Cyber Human Lab, University of Cambridge

  • Dr. Slavomir Tadeja

    Postdoc, MIT LEAP Group, workforce development

Research and training environments

  • TUM
  • CDTM
  • UnternehmerTUM
  • Stanford
  • Cambridge
  • MIT
  • IBM
  • Fraunhofer
  • TDK
  • Langdock
  • TUM.ai
  • Studienstiftung

07 / 07 · Engage

Pilot on one line. Prove it on one shift. Scale on your terms.

We start with a two to three day on site engagement. Shadowing five to eight expert operators during live maintenance and fault resolution. Full NDA. Safety induction. Zero operational disruption.

What you get

  • 01Direct input into product design, built around your asset hierarchy.
  • 02Clear insight into knowledge loss patterns and AI potential on your floor.
  • 03A first mover position in your industry’s reference corpus.

What you commit

  • 01Site access and coordination of the on site visit.