Founder, V12 Labs. 10+ yrs shipping software. Now building AI agents, RAG and workflow automation that ask a human before anything risky. Notes from real builds
We're building Vyra on @eve by @vercel.
Show it your website and it learns the rest. Company context gets researched once and reused across every campaign.
Campaign → audience → discovery → research in parallel → evidence → qualify → enrich → draft → review → send → learn
Not enough evidence? It loops back and digs more. ICPs and messages wait for the owner's approval before anything goes out.
Thanks @andrew_barba@coltonpadden for making agents as files this easy.
building agents is still all about context engineering
new CDMs from scaledown help you "scale down" your context and only give the model exactly what it needs, with low latency and cost
learn how to use w/ langchain: https://t.co/wogcjvUFnw
Building an AI-native services company.
Would love to connect with founders, agency owners, and industry folks to learn, collaborate, and grow together.
#LetsGoX
We shifted this to @bot
Oh man it’s far better in remembering what happened in previous steps and never pauses a single bot in the team.
Already got few positive responses.
Honestly if anyone wants to start checkout few templates/guides available on grok bot website.
We built our outbound sales engine using 14 ChatGPT scheduled tasks.
Not one giant “AI SDR.”
Basically a state machine with AI workers around it.
Wrote down exactly how we built it:
https://t.co/c3tIYYOkuX
Anyone here building an AI services business?
How do you cut through the noise and actually land clients?
Would love to hear what’s working.
Lets #connect
Has anyone built a genuinely smart AI agent for a niche industry?
Not another generic chatbot. Something that solves a real, interesting problem.
Would love to see what you’ve built.