Trust before autonomy
Grounding, audit, human-in-the-loop and graduated control. Every pilot starts in shadow mode and earns each write.
About
Glass is the transparent backbone of the modern world. It should not be run on memory.
Glasent is building the autonomous operations layer for glass manufacturing: melting, forming, annealing, inspection and handling run by agents inside limits a person sets, and validated on a twin before they touch the plant.
Why
Why we are building this
Glass is the transparent backbone of the modern world, and most of it is still made largely by feel.
Walk a glass plant and you will find furnaces that have run for years, forming lines moving glass at speed, and a handful of veteran technologists whose judgement keeps quality on grade. Those people are retiring, and the setpoints they leave behind are fixed while the process never is.
The gap is not another dashboard. Plants have plenty of screens. The gap is action: seeing a seed, a stone or a stress signal in time to change the furnace, the gob or the lehr, not hours later in the cullet pile. Glasent was built as a system of action from day one.
Three failures that keep showing up
- Fixed furnace and forming setpoints that cap melt quality, rate and consistency.
- Tiny, fast defects and hidden residual stress that turn into cullet, rejects, breakage and safety escapes.
- A melting process so energy- and carbon-hungry that every point of yield and every kilowatt-hour matters.
Each is continuous, tolerance-bound and rate-constrained. Exactly the work autonomy is built for, and exactly the work most plants still run by hand.
Principles
How we build
The guiding principles from the roadmap, and what each one means on a glass line.
Compounding data moat
Every supervised correction trains the system. The craft of the technologist becomes the model's, with the technologist's name on the approval.
Land narrow, expand relentlessly
One line, one KPI, one baseline. Then the adjacent agent, then the plant, then the group.
Run timeline · scenario
What we are actually building
Every Glasent run is an ordered, inspectable sequence. This is scenario_fl2_01 on FL-2 · float line · clear soda-lime: Thickness change FL-2 · 6 mm to 4 mm clear float, residual stress inside spec, zero escaped seeds. It is a worked scenario that shows the shape of a run, not a measured customer result.
scenario_fl2_01
FL-2 · float line · clear soda-lime
scenario
SUCCEEDED
-
01
ingest.order
SUCCEEDED
0.9 s
Plant Orchestrator · Pulled the 4 mm clear float spec, optical-grade tolerances and the standing energy window from plant MES; locked the target envelope for the run.
-
02
twin.simulate
SUCCEEDED
41 s
Glastwin · Simulated 36 candidate transition recipes across furnace pull, tin-bath ribbon speed and lehr curve; ranked them on seed risk, residual stress and energy per tonne.
-
03
melt.pull
SUCCEEDED
6 m 20 s
Meltrix · Stepped furnace pull toward the new ribbon mass flow while holding melt temperature and fining; chemistry stayed inside the composition window.
-
04
form.ribbon
SUCCEEDED
4 m 05 s
Formeon · Raised ribbon speed and re-angled the top rollers to thin the ribbon toward 4 mm; thickness converged inside the design tolerance.
-
05
anneal.curve
SUCCEEDED
3 m 12 s
Anneon · Re-shaped the lehr cooling curve for the thinner, faster ribbon so residual stress stays inside spec at the higher speed.
-
06
inspect.ribbon
SUCCEEDED
continuous
Seedscan · 8 camera, optical and stress stations streaming; a seed cluster flagged at the ribbon edge and attributed to the pull transient, routed to cullet.
-
07
yield.balance
SUCCEEDED
2.4 s
Plant Orchestrator · Re-sequenced cut sizes so transition ribbon routes to cullet recovery and good ribbon to the highest-value open order.
-
08
approve.human
APPROVAL
48 s
Plant Orchestrator · The second pull step exceeded the site autonomy threshold. Held for the glass technologist on shift; approved and written to the audit log.
-
09
handle.stack
SUCCEEDED
1 m 10 s
Panebot · Re-planned pick and stack paths for the thinner panes; plates flagged by Seedscan diverted to cullet, good plates stacked to rack A3.
-
10
ware.qualify
SUCCEEDED
1 m 02 s
Plant Orchestrator · Lot released with full genealogy: batch, melt, forming, lehr curve, defect map, stress map and the technologist's approval.
Focus
What kind of company this is
An independent, pre-launch startup building original physical-AI technology for glass manufacturing.
- Not a consulting shop, an outsourced-development agency, a reseller, a distributor or an internal division of an equipment vendor
- The product is software and plant-edge AI that senses, reasons, simulates and acts inside approved control envelopes
- Services are limited to onboarding, integration, safety validation and customer success around that product
- Incorporation, team, headquarters and funding are being completed and are published here when confirmed, not before
The market, as we size it
- TAM
- $17B · glass automation, furnace and forming control, annealing and tempering control, inspection, glass MES, twins
- SAM
- $4.3B · autonomous melt, forming and annealing control, defect and stress sensing, glass twins
- SOM
- $260M · obtainable within three years
- Growth
- about 11% a year
Company analysis; re-verified before external use.
Accelerated computing
Physical AI, at the furnace
A float ribbon never stops and an IS machine forms thousands of pieces an hour. Perception has to be local, deterministic and fast, so Glasent runs GPU inference at the plant edge and keeps training, simulation and optimisation on DGX, HGX and OVX.
Edge perception
4 to 24 synchronised camera, optical, thermal and stress stations per line. Sub-100 ms defect alerts on container lines and sub-500 ms fused stress and flatness decisions on flat glass are the design targets.
Model serving
Defect, stress, time-series drift and process-risk models served across edge and plant servers, with glass-knowledge and reasoning endpoints packaged as NIM services.
Training
Multimodal models fine-tuned on inspection imagery, optical and stress outputs, PLC time series, recipes, gob weight, furnace temperature, pull rate, lehr curves, energy, cullet and final grade. Planned cadence: monthly plant refreshes.
Digital twin
GPU-accelerated furnace CFD, glass-flow and annealing-stress simulation of the as-run line, with 10 to 100 candidate recipes evaluated per grade change.
Synthetic data
50,000 to 250,000 rare seed, stone, cord, inclusion, check and stress scenes per glass family, always validated against real inspection distributions before training use.
Optimisation
Pull-rate constraints, energy windows, cullet routing, forming and annealing sequence and line takt, with RAPIDS for high-volume telemetry ETL.
Team
Who is building it
A deliberately small founding team, led by co-founders Alexander Brooks (CEO) and Nathan Carter (CTO). Backgrounds are published here once confirmed; nothing is listed that cannot be checked.
Alexander Brooks
Alexander owns the design-partner programme, the pilot structure and the commercial model, and spends more time in control rooms than in the office.
Nathan Carter
Nathan owns the plant-edge runtime, the policy engine, the audit architecture and the bounded write-back that keeps it safe.
Perception
Owns the station pipeline, the seed, stone and check models and the stress fusion running on the plant-edge GPU.
Glass technology
A glass technologist by training. Owns the twin's physics, the composition windows and the translation between the plant and the platform.
Writing
From the notes
Three of the working notes, for the argument behind the product.
Why a fixed furnace setpoint is a decision you made years ago
The furnace runs for a decade. The batch, the cullet ratio and the pull change every week. A setpoint that was right at campaign start is a guess by month six.
A seed is a melt problem that arrived at the inspection station
Attribution is the whole point of fusing inspection with control. A defect you cannot trace to a process cause is a reject; one you can trace is a setpoint.
Residual stress is the defect you only see in the field
Polariscope spot checks tell you about one piece. Birefringence at the lehr exit, on every piece, tells you about the curve.
From the plant floor
The problems we hear
No customer quotes yet; we are pre-launch. These are the three buyer personas the product is built for and the pain each one describes, in their own terms.
"The furnace has run for years on the same setpoints. The process never has. We find out a melt drifted when the cullet pile grows."
Plant / operations director · ICP persona
"I can tell you why a check appeared from the lehr curve and the gob weight. I cannot be at every line, and the people who could are retiring."
Glass technologist · ICP persona
"A missed seed is a reject. A missed stress fault is a pane that shatters in the field. I need genealogy on every piece, not a spot check."
Quality / reliability engineer · ICP persona
Guardrails
An agent that can move a furnace needs a leash
Glasent writes to production equipment. Every capability is scoped, every write is policy-checked, and every action is written to an append-only audit log the plant owns.
- Bounded action space. Each agent can only write to an explicit tag allow-list, inside per-tag rate and magnitude limits.
- Policy engine before every write. Autonomy level, shift, product, interlock state and operator presence are all evaluated before a setpoint moves.
- Human-in-the-loop gates. Anything above the site threshold, pull steps, grade releases, safety-adjacent moves, waits for a named approver.
- Immutable audit log. Append-only, hash-chained, exportable, and retained on the plant's own storage.
- Hard fallback. Loss of the edge node, the network or the model returns control to the furnace, forming and lehr systems' last known-good state.
- Tenant and IP isolation. Compositions, forming recipes and defect libraries never cross a customer boundary. On-prem deployment available.
Compliance posture
| Standard | Scope | Status |
|---|---|---|
| SOC 2 Type I | Cloud control plane | RUNNING Planned in the first six months |
| SOC 2 Type II | Cloud control plane | QUEUED Planned in months six to twelve |
| IEC 62443 | Plant-edge OT security | RUNNING Design-aligned |
| ISO 9001 / IATF 16949 | Quality and genealogy records | SUCCEEDED Record formats supported |
| Container and safety-glass standards | Stress and defect conformance records | SUCCEEDED Record formats supported |
FAQ
Straight answers
The questions plant directors and glass technologists ask in the first meeting.
Yes, but only within an explicit tag allow-list with per-tag rate and magnitude limits, and only at the autonomy level your site has set. Every pilot starts in shadow mode, where Glasent predicts and recommends and a person enters everything. Writes come later, after the recommendations have earned it.
Control returns to your existing furnace, forming and lehr systems at their last known-good state. Glasent is a supervisory layer on top of the control system you already run, never a replacement for it, so an outage degrades the plant to its current way of running, not to a stop.
Shadow mode starts on the first day from existing SCADA, forming, lehr and inspection data. Defect and stress prediction improve as site history and labelled outcomes accumulate; the pilot plan sets a baseline period before any recommendation is scored.
Only if you choose cloud training. Compositions, forming recipes and defect libraries are tenant-isolated and never used to train another customer's models. On-prem training and an air-gapped plant edge are available for IP-sensitive producers.
You are, the same as with any control strategy, which is why every write is policy-checked, bounded, logged and reversible, and why anything above your risk threshold waits for a named approver. The audit log records the request, the reasoning, the limits applied and the human decision.
A 90 to 120 day line pilot in three stages: shadow mode to measure the baseline, assist mode where a technologist approves each recommendation, then bounded write-back on low-risk forming, annealing or inspection loops if the plant is satisfied with the results.
Get started
Come build the glass plant's operating system
Design partners, engineers who want to work next to a furnace, and glass technologists who want to encode what they know.