Evan Welbourne

Stop building chatbots. Start building agents with MCP. 🤖⛓️ After our Claude Code deep dive, the Claude Builder Club is back, this time with Notion UMD. We are diving into the Model Context Protocol (MCP), the emerging standard for connecting AI to tools, data, and real world workflows. If you want to move beyond simple chatbots and start building real AI agents, you should come.

9

2 Comments

Shardul Shah's post on our Series A captures something important about how we build product at 7AI. He wrote: "Its multi-agent architecture learns each environment's unique context, enabling faster, more accurate, and more consistent investigations than humans or rule-based systems." That's the product vision in one sentence. Not a one-size-fits-all solution. A platform that learns your environment, your context, your tools, and delivers outcomes specific to you. Shardul called 7AI potentially "the defining agentic security company of this new era." That's the standard our team is building toward. Every day.

46

1 Comment

📣 Some good AI news for designers: agentic AI is just UX in disguise! You know when someone says something simple and suddenly the hard thing makes sense? Just had one of those 💡 lightbulb moments in a workshop with Chris Johnson about command line tools for process optimization with agentic AI. I've been watching a lot of videos about building AI workflows lately. About 30 seconds in, the presenter usually dives off into n8n or some other visual coding environment where they have 10000 boxes joined up with spaghetti string. If you just set all of this up, magic will happen! (Anyone who has used a prototyping tool has been there: no judgment!) CJ skipped past the complicated tools, and stuck with the concepts. Turns out that "agents" are just a very thorough and structured JTBD-like persona in a file that the AI uses as context for its work. Let's break it down a bit: ( 💻 AI-speak) -----------------------> (👩‍💻 UX-speak) As long as you have a tool capable of agentic AI (e.g. Claude), you create: * a "knowledge base/context" ------> "folder" of files, including * "skills" ------------------------------> "user expertise & knowledge" * "agents" ----------------------------> "persona" * "processes" -------------------------> "tasks, workflows & journey maps" ...to get things done. Who knew? UX-ers have been AI-ers all along! 🙌 I might just be the last person on the planet to "get" it (wouldn't be the first time...), but I figured maybe others have been as mystified as me. I'm pretty excited about the possibilities that this opens up: using a new technology to play a bigger UX game on our own home turf. Especially when you throw a little OOUX into the mix...😎 More from CJ here: https://lnkd.in/eunxQAXa https://lnkd.in/eFQds6KT https://lnkd.in/emvdvm5Q

2

2 Comments

Why does the second search feel instant when the first one takes 3 seconds? I built a local semantic search engine using EmbeddingGemma. The bottleneck? Generating embeddings—10-100ms per chunk of text. Twenty chunks takes under a second. Two hundred chunks? A few seconds. Two thousand? You're waiting. And every search regenerated every embedding. Wasteful. The fix is simple caching: save embeddings to a JSON file after the first indexing run. On subsequent searches, load from disk instead of regenerating. First run: generate and cache. Every run after: instant. The real insight: caching doesn't just make it faster—it changes how you use the tool. Without caching, you think twice before searching. With it, searching becomes nearly free. That's the difference between a tool you built and a tool you actually use. I teach by building in public and sharing what I learn. Full write-up with code:  https://lnkd.in/gJtgEQ7s  #AI #MachineLearning #BuildInPublic #AILiteracy

4

Without standardization, web3 will remain like a Tower of Babel, where communication between chains is more akin to translation than transaction, argues Temujin Louie. https://lnkd.in/g8tuvUNS

7

Perplexity just announced Perplexity Patents. Ask in plain language, get verified prior art with links you can open. A natural next move from Perplexity and Aravind Srinivas, shaped by Jerry Ma and team. It feels less like a product launch, more like a quiet redefinition of research literacy. India is an intriguing test case. Patent publications grew 60 percent in 2024, but examinations collapsed nearly 80 percent since 2020. R&D spending still sits at 0.64 percent of GDP. Many universities file patents because NIRF rankings reward volume, not validation. The result is a sea of forms, few defensible claims, and a generation that thinks innovation equals paperwork. The government’s 2024 amendments tried to speed things up, yet capacity gaps, procedural opacity, and the occasional rent-seeking habit remain. We made filing easier but not necessarily wiser. That’s why the airtel x Perplexity partnership feels like a smart play by Perplexity and a real opportunity for Indian users. If 390 million people get a year of Perplexity Pro, prior art literacy could expand fast, provided coverage and provenance hold up. In that case, we should ideally see better habits: fewer blind filings, fewer checkbox patents in classrooms, and more startups aiming for real differentiation instead of duplication. Potential ripple effects • Broader access for MSMEs, labs, and first-time filers • Cleaner claims and fewer speculative filings • Better go or no-go calls before lawyers enter the room Caveats • Verify coverage of Indian and non-English filings • Keep provenance logs and multiple reference points • Remember: AI assists judgment, it does not replace it Perplexity Patents could help India pivot from filing races to intellectual integrity. If curiosity becomes the default operating system, the next decade may finally reward original thought over bureaucratic stamina. Can we turn this cultural awakening into high-quality, evidence-backed research before the next wave of filings arrives?

7