Dustin Pulver

In case you're wondering, this is the stage of the market we're at.

imo, the most important and interesting problem to work on today is organizing a 'company environment' for your agents to operate in. Concretely - this means creating a filesystem/repo that models your entire company...cc/codex/cursor will live and operate in this repo.

@NoahKahan do you think Mythos has ever stared directly at the sun ?

Fonts that instantly feel like a logo → Part 03 Steal these for your next brand identity. Which one hits different?

From due diligence to feature planning, good decisions start with good inputs. Tavily helps teams move from question → credible sources → clear answers in one streamlined search workflow.

“When you feel the AGI, you feel your soul” — Dylan Patel

99.9% of people don't understand 2026 yet we had our first fully Righthand-triaged customer support ticket last night - all AI employees, no human involved at all ↓

me after reading the anthropic blog post

Best pyramid theory we have right now

We need a AI State of the Union @lexfridman

Tavily has been named to The Agentic List 2026, recognizing the agentic AI companies most admired by industry execs. We power AI agents with real-time, high-quality search and retrieval, helping enterprises move from experimentation to reliable, production-ready systems grounded in live data. See the full The Agentic List 2026 → agentconference.com/agenticlist/20… #TheAgenticList2026 AI Agent Conference

This is a ridiculous stat in a ridiculous story: "The marginal cost of running an agent, had collapsed to, essentially, the cost of electricity." The marginal cost of a coding agent is not even remotely close to "the cost of electricity." These agents are absurdly expensive to use and run. Why do you think AI labs are banning people from having multiple $200 subscriptions? Because those subscriptions are heavily, heavily discounted to drive demand. Why did labs stop folks from using their subscription costs in OpenClaw? The OpenClaw guy had five max subs and was losing 20k a month building and running his amazing project (because he was retired and had the money to set in fire) before AI labs banned this practice of having multiple subs. In case you just missed it: Because these agents are expensive as hell to run. The cost of running coding agents daily on eight hour shifts is thousands of dollars a month at API pricing and that is subsidized too. My team regularly burns anywhere from 4K-8K a month across three people using the latest and greatest for an AI driven building workflow. That's not even agents running 24x7 "making money while you sleep" which is utter and total nonsense. This is one of the most spectacularly unprofitable businesses in history so far. People talking about the end of all work because this stuff runs for "pennies" cannot do even the most basic math. New NVIDIA chips don't even break even for data centers for like 24-36 months and they are basically obsolete by then. That doesn't count power and cooling and people to run it all. Imagine if your car was basically worth zero after three years? I'm so sick of these idiotic Population Bomb level stories about the end of all work and running agents for pennies. It's a mass delusion for people who can't be bothered to bust out a calculator on their phone for five seconds.

Sunday. I did a brain reset, 7 hours of silence. What it did to my brain: No phone. No music. No books. No screens. Just water and silence. This was week 8 of my 53 Skills project. The first few hours were easy. Then around hour 3, my brain switched from boredom to processing mode. Old emotions, unresolved thoughts, things I’d been outrunning for years. All surfacing on their own. By the end, my mind felt completely clear. Not tired. Not numb. Actually calm. It lasted for hours after. Why this matters: I think we never give our brains offline time anymore. Every quiet moment gets filled with a podcast, a scroll, a notification. Your brain is running on 100% input and 0% processing all day. Neuroscience backs this up. Unstructured mental downtime improves memory consolidation, creative problem-solving, and emotional regulation. It’s the same mechanism as sleep, except we can access it while awake. We just choose not to. You don’t need 7 hours. One hour of zero input per week would put you ahead of most people in terms of mental clarity. Try it: one hour, no phone in the room, no background noise. First 20 minutes will be uncomfortable. Last 10 will surprise you.

unpopular (maybe?) opinion: MCP is dead in the water @openclaw has shown me that api & cli will win. every MCP server you connect loads its tool definitions into your context window. name, description, parameter schema, all of it. connect 10 servers with 5 tools each and you've burned 50 tool definitions worth of tokens before your conversation even starts. context bloat will never be a good thing - performance-wise or economically. i assume this is why @steipete left it out of @openclaw. the "exec" tool paired with on-demand skills is all you need. it can run any command invented since the beginning of computers. a resurgence of glory for ancient, but powerful tools like curl, sed, awk, grep. command line tools once mastered by the greats, but long forgotten and buried underneath abstractions developed for us lesser mortals. now available to us all, piloted by the smartest models on earth. every founder gets their own mass army of greybeards. the inertia required for MCP adoption, imo, is too great to overcome the momentum @openclaw has breathed into api + cli + skills. the common defenses people bring up: • "MCP gives you typed schemas and validation" — so does a well-documented CLI • "MCP gives you explicit permissions" — so does a sandbox with an allowlist • "MCP is a standard" — a standard that scales poorly is still a standard that scales poorly lastly, i've heard many MCP servers are just wrapping existing APIs - that kind of redundancy and unnecessary indirection should be a red flag. so, let's drop it and redirect our efforts into cli tools & apis with accompanying skills.

@gdb Token anxiety

feels like such a wasted opportunity every moment your agents aren't running

one thing i’ve observed is that the companies that add tremendous value today excel at applying AI while simultaneously developing infrastructure that’s loathsome to build. AI web search is a great example. Building great infra takes up 98% of developer time, yet the AI aspect drives 98% of the value. Same with agents for enterprise. AI reasoning and tool use drive the visible value, yet 90% of the work is permissions, sandboxing, safeguards, integration with legacy systems etc.

Thank you for having us. I had a great time speaking at the event. For a deep dive on how the @tavilyai team built the deep research and achieved the SOTA performance, take a look at tavily.com/blog/research-…

@dishantwt_ @ramxcodes Semantics 📉 when you master lexical you realize the true potential

cursor uses turbopuffer as their vector DB, they are good at indexing because they do semantic search on the code base and not barely use grep cursor has its own embedding model to which they keep on improving ig based on the data we share they keep the track of the file changes through merkle trees this is some of the knowledge that I had about how they work

Yapping out RAG, obsidian, Cursor How i solved a problem and the solution that will create a problem later

We’re now live on the GitHub MCP registry. Plug Tavily into your GitHub agents to give them real-time web access via one MCP tool. Grounded agents. Fresh context. No custom scraping. github.com/mcp

NYC AI Builders! 🛠️ 🗽 Want to see how @TavilyAI hit the top of the DeepResearch Benchmark? 📈 Join us with @datadoghq & @daytonaio as one of our engineers breaks down their new SOTA Research Endpoint. See you Thursday! 👇 luma.com/gultpezn