Co-Founder @ Addepto, technology expert, marketing and social science enthusiast more: https://nitter.cf/t.co/A2JpSaOLGo & https://nitter.cf/t.co/C9z0wLc3in
Joined May 2018
- Tweets32
- Following159
- Followers34
- Likes57
AI in manufacturing is done with PoCs.
It’s time for production.
25 real-life AI & Big Data use cases based on Addepto's 10+ years of hands-on experience.
📅 Feb 12, 4 PM CET: webinar.getresponse.com/JhfL…
Few patterns I see for 2026:
❌ AI stops being exciting
⚡️And starts being useful
It moves from chat interfaces into infrastructure, supports decisions (not replaces them), and prioritizes reliability, cost, and accountability.
1
9
When it works, nobody notices.
When it fails, everyone does.
That’s AI becoming infrastructure.
More context in my latest Medium article: medium.com/p/b8b9699e929b
8
We talk a lot about growth & tech, but the best lessons come from people. 3 books that made me pause:
💡 One truth: success starts with people.
medium.com/@elisowski/3-book…
19
“AI will fix everything” might be the most overused phrase in tech right now.
But as Katarzyna Czupik writes in her latest article, enterprise AI isn’t a super brain. It’s math with rules.
addepto.com/blog/lets-get-re…
10
Dusted off my Substack 💡
I’ll be sharing more casual posts there — updates, insights, and random thoughts on tech and AI.
If you feel like chatting, stop by and say hi 👋
Would love to hear from you.
open.substack.com/pub/edwinl…
11
At @addepto , we love turning complex problems into impactful solutions.
Our latest case study shows how an AI-driven system helps airports optimize stand allocation, boosting efficiency, revenue, passenger experience & sustainability: addepto.com/case-studies/opt…
21
One of the biggest misconceptions in AI adoption:
“Start with the most technical team. They’re the most ready.
Not always. Some of the biggest wins I’ve seen came from non-technical teams… while technical ones stalled or resisted.
1
13
The teams most ready for AI:
✅ Feel the pain (manual, repetitive work)
✅ Open to experimentation
✅ Have clear but flexible use cases
✅ Willing to change workflows
Tech skills help, but mindset matters more.
1
9
For years, the “standard” way to make documents usable has been the same:
1️⃣ Split text into snippets
2️⃣ Embed them
3️⃣ Pray your assistant can stitch it all back together
We tried that too. And we kept hitting the same wall: snippets don’t understand relationships.
1
7
That’s why last week we open-sourced Graph Builder — the part of ContextClue that transforms messy documents into structured, queryable knowledge graphs: github.com/Addepto/graph_bui…
1
11
AI moves fast. The only constant is change.
We built ContextClue at @addepto as a knowledge management tool. Then the LLM boom hit. Overnight, semantic search was everywhere - for free. Our product felt obsolete. We had 2 options: push forward or pivot fast.
1
15
We chose to pivot.
From general-purpose KM → semantic search for engineering: digital twins, system structures, virtual commissioning.
That meant a new roadmap, new domain, and rebuilding sales from scratch. Painful, but it kept us alive.
1
8
Tried the top coding assistants. No one-size-fits-all. It depends on your workflow.
Claude: smart, multi-file
Cursor: VS Code native
Aider: terminal, open-source
Cline: agents in VS Code
Copilot: classic plug-and-play
Full breakdown:medium.com/@elisowski/claude…
61
Most company knowledge is stuck in PDFs, reports & tables. Valuable, but locked away. We’ve open-sourced (for free) part of ContextClue: Graph Builder 🚀 A toolkit to turn semi-structured docs into knowledge graphs. github.com/Addepto/graph_bui…
Feedback & contributions welcome!