Other similar profiles
Explore more posts
-
Dan Porder
I went down a bit of a rabbit hole on AI spreadsheet ingestion this month, as I continue improving our data pipelines at Valae. There’s a lot of research and products in this space that don’t match what we see inside companies every day. Papers like Microsoft Research’s SpreadsheetLLM achieve high metrics for table extraction, but there’s always a catch. The success is measured on spreadsheets where the data is already pretty clear. Real company spreadsheets aren’t so easy. Sometimes they have three tables crammed into one tab, column headers that are someone's initials, and cell B7 containing "check with Marco re: pricing (NOT final)". In my research, I also dug into the survey "Toward Real-World Table Agents" (Tian et al., 2025) which confirms what I found after reading dozens of these papers: almost all LLM table research uses clean academic datasets. The messy reality of business data is barely ever addressed. That gap is where my team at Valae lives. We're perfecting proprietary processes for turning the messiest possible spreadsheets into clean, machine-readable knowledge, automatically. Despite SpreadsheetLLM, despite LlamaIndex launching LlamaSheets, despite years of research… nothing on the market truly handles the gap between what a spreadsheet contains and what it means. Encoding is a solved-ish problem. Interpretation isn't. And that's the one that matters. https://lnkd.in/er7PdDBP
1 Comment -
Saurabh Bhise
Great evening at ClawCon NYC last night. Really enjoyed seeing the different approaches teams are taking to build real-world AI agent systems. Highlights for me: • Cathryn Lavery sharing lessons from building AI-driven products and documenting the journey publicly • Kilo Code and Scott Breitenother demoing the Kilo / KiloClaw stack for agentic engineering • Passive Claw exploring autonomous trading agents • Zo Computer with Ben Guo and Rob Cheung showing what a personal AI cloud computer could look like • Memory Router tackling the challenge of memory routing and context management for agent systems What stood out is how quickly the ecosystem around AI agents is evolving. Each team is solving a different piece of the stack — infrastructure, execution, memory, and real-world automation. Appreciate everyone sharing demos and ideas tonight. Looking forward to experimenting with some of these tools and incorporating some of these concepts into my own projects. Exciting times ahead for agent systems.
1 Comment
Explore top content on LinkedIn
Find curated posts and insights for relevant topics all in one place.
View top content