Portfolio — Applied AI

Yarneon

Every roll right first time, before it leaves the mill.

Seed 2026 · $1.5M Applied AI London, United Kingdom

Yarneon runs the mill from fibre to finished roll: spinning and yarn-quality control, weaving and knitting control, dyeing and finishing chemistry and colour control, AI fabric-defect and shade inspection at line speed, yield, water and energy recovery, robotic roll handling, and an as-produced fabric twin that checks a recipe or a sequence before a machine moves.

Fabric is one of the largest manufacturing sectors on earth and one of the least instrumented, and the colourists and weaving masters who hold the tacit knowledge are retiring faster than mills can replace them. A yarn drift becomes a barré in weaving becomes a shade reject in dyeing, and each stage is usually fixed in isolation. Ethan and Ryan are closing the loop across the whole mill instead of reporting on it afterwards.

Yarneon

  • Seed · 2026Stage
  • $1.5MRound
  • Applied AISector
  • London, United KingdomHeadquarters
The founders

Ethan Mitchell

Co-founder & CEO

Ethan runs the company and the commercial side: which dyehouse or weaving shed goes first, what number it is judged on, and who at the mill signs off on the baseline. He started Yarneon because mills still find a shade miss or a barré at the end of the line, long after the lot that caused it.

Ryan Parker

Co-founder & CTO

Ryan leads engineering: the mill-edge runtime, the fabric vision and control models, the OT connectors, the as-produced fabric twin, and the bounded, audited write-back into machine controls. He is why every agent earns its authority in shadow mode first, with an evidence trail behind each action.

How it's gone
  • 2026

    We came in

    $1.5M seed to take the first mills from shadow mode to bounded control.

  • 2026

    Where it starts

    Re-dyes and shade misses first: baselines run against live lots before any agent is given write authority.

  • 2026

    Building the team

    Hiring controls engineers, vision researchers and people who have run a dyehouse.

An illustrative 99SA Ventures profile — founder, team and figures stand in until the company shares its own.

Building AI that has to be right, not just impressive?

If your model gets graded against something real, we're the easy meeting to get.