taggl (@tagglai) header
taggl (@tagglai) profile picture

Operators talk. AI captures their tacit knowledge. Voice-to-knowledge for the shop floor.

Netherlands
Joined June 2025
Photo by taggl (@tagglai)
Outdated knowledge is more dangerous than missing knowledge. A missing instruction creates a gap you notice. An outdated one looks reliable — and leads you wrong. Machines get overhauled. Specs change. Workarounds become obsolete. Docs rarely keep up. taggl.ai/knowledge/knowledge…
1
1
7
taggl retweeted
This is effectively the #1 problem for AI agents in the enterprise. As we go from agentic coding (where a large amount of context is in the code base, and users are technical enough to get the rest to the agent easily) to a world of knowledge work agents, the context problem becomes much more acute. We see this every day with customers at Box. For existing digital knowledge, it’s often fragmented across legacy systems or environments that don’t play nice with agents, and have access controls that don’t map to the real work that needs to be done, which become a huge hurdle for getting agents the context they need. This has to all get moved to modern, secure cloud environments. But also, companies often haven’t captured and digitized some of the critical context that agents need to work with. Decisions, processes, and workflows often live in people’s heads and tribal knowledge that need to get turned into unstructured data for agents. This is actually one of the biggest points of leverage for applied AI companies, because they can work to specialize in getting agents exactly the information and domain expertise they need. But it’s also one of the reasons why FDEs and new system integrator plays will also work so well right now. The companies that figure this out will be able to get the most out of AI going forward.
Imagine replacing 90% of your employees with a team of geniuses who have no idea how your company operates. Total chaos. Nothing works. That’s what AI feels like today. The missing piece is extracting all the domain knowledge from people’s heads and providing that as structured context to the models.
122
97
25
753
187,662
2 August 2026. That's when high-risk AI obligations under the EU AI Act become enforceable. Most manufacturers think the law only applies to AI builders. It doesn't. If you deploy AI on the shop floor, you're in scope. What it means in practice ↓ taggl.ai/knowledge/eu-ai-act…
1
13
Tribal knowledge: the process expertise that lives nowhere but in people's heads. Why one machine behaves differently above 20°C. Why a customer gets looser tolerances than the drawing says. Why Friday afternoon isn't Monday morning. Not in any SOP. Not in any wiki.
1
1
11
Operators already share know-how all day — just not in a format that survives retirement. Here’s a sharper take on knowledge transfer in manufacturing. taggl.ai/knowledge/knowledge…
1
1
14
Your best operator knows things that aren't in any manual. Which machine behaves odd at 20°C. What to do when X happens. That knowledge lives in one head. Until it doesn't. Taggl captures tacit knowledge the moment it happens. No typing. No extra work. Just talk.
9
Solving knowledge leaks with AI 🧠 3 steps: → Capture during work → AI structures automatically → Intuitive access for everyone Result: 60% faster onboarding, 40% faster problem-solving. @djschoone explains
1
1
16