Tell Squint the cycle time you need to hit or the number of stations you have, and it builds a balanced line from the time studies you’ve already run.
You get work elements assigned to each station and a Yamazumi chart showing every station against your target.
Hours of line video. Zero hours spent rewatching it.
Upload a full shift and get back a time-and-motion study with every second categorized. Every recommended fix is timestamped, so you can jump straight to what needs improving.
Every operator now has their own run history in Squint.
Open any team member's profile and see every procedure they've completed. Operators can see their own history too.
See it in action: squint.ai/demo
Finding the right documents shouldn't be a scavenger hunt.
Squint now syncs your SharePoint docs with their tags and permissions. Add custom properties, filter fast, and share across every facility.
One source of truth for every plant.
What else is new: squint.ai/blog/whats-new-lea…
"Our customers can't afford a quality error because we're training a new operator." — Rakuya Artis, DESTACO
DESTACO rebuilt standard work with Squint. Within months, customer-reported defects fell 53%.
Get the story: squint.ai/blog/how-destaco-c…
New in Squint:
Input: work instructions, specs, floor photos
Output: time studies in your team's language, tuned to your facility
Also new: cycle comparison on long recordings, doc sharing across facilities in Enterprise Console & more.
Read the blog → squint.ai/blog/whats-new-lea…
Spent this week at Lean Leadership for Lasting Change in Green Bay.
Same idea: you have to get on the floor. Gemba walks still win.
Feed the Lean Manufacturing agent video of your line. It watches, frame by frame. Lean leaders drive the work, we just help it move faster.
Variance analysis is live in the Lean Manufacturing Agent
Upload one long video, a full shift if you have it. Squint finds every cycle, breaks each into work elements, and shows which elements swing most from cycle to cycle.
Pick your best cycle and standardize around it.
Ditch the stopwatch.
The Lean Manufacturing Agent balances your line without one.
This is continuous improvement that's actually continuous.
Most teams still run time studies like they did in 1911: stopwatch, clipboard, a full shift at the line.
Today, the Lean Manufacturing agent does it all for you.
See what it can do, plus everything else we shipped last month! 👇
👉 squint.ai/blog/the-lean-manu…
Link in the blog to join us TOMORROW (9/3) for a live demo of the agent at work. Comes with free access to the tool through 9/30.
Making 100 years of manufacturing expertise work at scale: The Lean Manufacturing Agent automates time studies, generates Yamazumi charts & recommends fixes.
Balance a line in weeks, not months.
Continuous Improvement Loops are here.
Industrial AI is here.
Today, we’re launching Squint’s Industrial Agent Platform to reduce downtime, improve quality, and accelerate impact for industrial teams.
Squint has always helped capture and share hard-won expertise. Now, our agents can put that knowledge to work.
Thanks to the team at @Inc for capturing the full story.
inc.com/georgia-fearn/factor…
No audio?
Operator too quiet?
Facility too loud?
No problem.
Squint sees it all.
Squint actually watches your videos and generates precise steps based on what it sees, not just what it reads from a transcript.
See what else is new in Squint this month 👇
Read the full update: squint.ai/blog/organize-your…
Squint retweeted
This is exactly why the next 18 months of vertical AI are going to be bananas.
The promise of vertical AI, as opposed to vertical SaaS, is to build software that understands a job well enough to actually do the work — not just give a person better tools to do it.
There are 3 trends that have created a perfect storm for vertical AI:
1. AI software is capable of getting jobs done in more magical ways than ever before.
2. The first place that magic has landed is in AI software development itself, so there's a mad rush to build for the builders.
3. This makes for a frenzied loop: build AI tools to solve problems in the current AI tooling → uncover new problems with AI tooling → build different tools to solve the new problems...
Every day a new (and better, and faster) way of building emerges. But it also introduces a new set of problems that require a new set of products. Infra and tooling right now are on a runaway treadmill that just keeps going up in speed. The side effect is an insane tailwind of constant stack upgrades for building vertical AI.
It's a generational opportunity to literally invent solutions for problems that haven't been solved in 100+ years. A factory floor today has the same tribal-knowledge problem it had in 1926: the person who knows why the line really runs is about to retire, and nobody wrote it down. We are now finally getting to the point where we can take on massive real world problems and build solutions that get those jobs done in a magical way.
Give us a P
Give us a P
Give us a T
Give us an X
What’s that spell?
Upload Word, Excel, and PowerPoint files directly into Squint!
Error during a daily inspection?
First changeover for a new hire?
Unexpected troubleshooting?
No matter the situation, a single Squint procedure guides you down a single, reliable path.
Learn more about building procedures with conditional logic through the link below
Check out the full guide here 👉 squint.ai/blog/a-guide-to-bu…
