Gavin Basuel

@handotdev @mintlify dubs in the chat

we eliminated seat-based pricing at @mintlify seat-based saas pricing doesn't have a future where agents are the primary users. it's like pricing electricity by the bulbs

@gregisenberg Unlimited agents, unlimited usage works as marketing but will kill you if taken literally

I'm giving away a FULL course on how to build a managed AI agent business solo using Hermes Agent, Orgo, Obsidian, Codex, Claude Code etc. Here's everything (47 minutes): 1. The offer: unlimited agents, unlimited usage, all infrastructure and security included. The customer gets a digital employee. They never think about tokens or models. You handle everything. 2. Don't niche down too fast. Try marketing agencies, law firms, insurance, manufacturing, real estate. See where the market pulls you. Then go vertical. Diverge first, converge later. 3. Every executive has the same problems regardless of industry. Too many emails, too many meetings, too many follow-ups, too many open loops. Solve those first. Then layer in vertical-specific skills. 4. The stack: Hermes Agent for the agent harness. Codex or Claude Code desktop to build and configure. Orgo for cloud computers so every agent lives in its own sandbox. Composio for one-click authentication across thousands of apps. Agent Mail to give every agent its own email. Obsidian for the knowledge base. 5. Use agents to build agents. Don't stress about setup. Use Claude Code or Codex to install and configure Hermes inside a VM. Use Perplexity MCP, Context7, and Exa for up-to-date docs. Your agent sets up your customer's agents. 6. GPT 5.5 is the best model right now. Efficient with tool calls. Doesn't eat tokens like Opus 4.7. For cheaper tasks, GLM 5.1 from ZAI is the best open source option. 7. Set up watchdogs for gateway crashes so they auto-restore. Have agents email you when cron jobs break or skills fail. Your customer should never have to tell you something is broken. 8. Get customers through content. If someone jumps on a call and already knows who you are and what you sell, that's the position you want. Content is the most leveraged thing you can do in 2026. 9. Keep scope tight. One to two requests at a time, delivered in under 48 hours. Use Trello for customer-facing project management. Send Loom updates at random hours to show you're always working on their agents. 10. If you can set up Claude Code, Hermes, or OpenClaw, you have a skill that 99% of business owners don't have and would pay $5k/month for. You're probably not giving yourself enough credit. shoutout to @nickvasiles from @orgodotai for coming back on @startupideaspod and sharing the full playbook. tools, stack, fulfillment, everything. this type of episode isn't shared anywhere on the internet. this is the alpha people keep for themselves. i will keep sharing if you keep watching. you could watch netflix or you can watch this (link below) youtu.be/BI-MNjm1tTQ?si… watch

@sama @sama nice runescape reference 'level 99'

way cooler to help software developers pokemon-evolve into superheroes than to try to replace them it is insane what one really good person can do now

@Rasmic When

CONVEX IS HAVING A CONFERENCE I AM TOLD I WILL BE GIVEN A BUDGET TO DO SOMETHING INSANE YOU BETTER PULL UP BABY Abstract.

@VadimStrizheus Google just yeeted a chunky 4GB Gemini Nano AI squatter onto my drive without asking, like Chrome’s playing “on-device” but really just moved in rent-free and ate all my storage snacks 😂

🚨do you understand what just happened with Google?! Google Chrome has been secretly downloading a 4GB AI model onto your device. without you even knowing anything about it. It's called weights.bin. It lives deep in your system folders. Check your computer right now: %LOCALAPPDATA%\Google\Chrome\User Data\OptGuideOnDeviceModel To stop it: chrome://flags → disable Optimization Guide On Device Model → restart Chrome → delete the folder. Share this with all of your friends.

@gohighlevel good job ghl team

Lukewarm take: the best product updates aren't the flashy ones. They're the functional ones.

@claudeai Announced /Dreaming🥱💤😴 added Bigger Rate Limits, Spacex Partnership, Outcomes (temu /goals), and multi agent orchestration

@0xmaz_ try leaving /goal on for gpt xhigh 48 hours ($200/mo sub)

wtf 10x codex limits are actually insane im not even breaking 1% after running for an entire day ???

@LexnLin left /goal on for 48 hours

@LexnLin time to switch over to my second codex subscription 😂

what the actual fuck I've been codexmaxxing for an hour. 5projects in parallel and I'm FINALLY 1% down now 200x is insane

@pcshipp .co

Which domain better for SEO? .io .ai .app .xyz .com

@Franciscocrz @Replit That was fun buildathon @Replit team!

Huge shoutout to the @Replit engineering team for sticking around all night ahead of the 24 hour Replit 10 Buildathon 🎉 See you all live at 4:30amPT!

The Search Landscape is Evolving fast. Several AI platforms are pushing you to build AI websites and apps are being made for local businesses. But i found a major flaw. Yes it's easy to launch a @nextjs website but they are absolutely terrible out of the box at ranking for SEO. Local businesses who are adopting these websites are really paying the price in terms of foot traffic and @chatgpt biased search results. (I did a full analysis) HTML sites are being scraped by chatgpt and llms prioritizing them instead of the fancy AI generated ones.. Thus leading to nice human website, and very badly optmized for robot ai gptbot traffic. Anyone have a solution? @nextjs @ChatGPTapp

@xai Scary but cool

Voice Cloning is now live via the xAI API! Create a custom voice in less than 2 minutes or select from our library of 80+ voices across 28 languages to personalize your voice agents, audiobooks, video game characters, and more. x.ai/news/grok-cust…

@bridgemindai Load bridgemind on your tesla screen

Vibe Coding with Grok 4.3 in a FSD Tesla! This is the future.

@thsottiaux pinned conversations + past thread were disappearing after each mac update

It’s the little things that matter, what are some small papercuts you have noticed in Codex? We’ll fix as many as possible in the next week.

@EHuanglu we got temu gta6 before gta6

ChatGPT image 2 imagine gta6 in China

@MatthewBerman Good point about the business use cases, especially businesses that don't always need the frontier models deepseek and models alike are way more cost effective

DeepSeek is a major threat to United States AI dominance.

@alieniswonder @gdb Very cool @alieniswonder

@gdb Mini golf meets orbital mechanics gravitygolf.xyz

what are you building with codex?