Great talk sharing agentic harness e2e pipeline success from a real playing field.
Plus, I found the accompanying article on the custom harness called 'case' (OS repo inside):
https://t.co/MvdHGtGK23
Not something you can plug and play, but good read for Pi harness inspiration
@TravelingTice I think I know what you mean. Like a single thread of complex tasks, but still funny how seamlessly socials melt in and out of that one thread we have free. 😅
Definitely curious to try out agents on hyper speed. BUT I'm not writing code anymore but self-contained tasks, so agent-forced breaks are inevitable: self-validation (test runs), research, generation (eg docs). The time window in between, you use for agent number 2 & kill IG ;;)
Actually that increase in speed is maybe a 50x return on productivity bcs it is finished before my internal attention span prompts me to open IG to doomscroll for 10+ minutes
I just pulled SaaStr’s Replit bill for last month.
Our two AI VPs cost us $254 for the entire month. Combined.
- 10K (our AI VP of Marketing): $94.51
- Qbee (our AI VP of Customer Success): $159.55
Two human VPs at the same level would run $500K-$800K a year, all-in.
A few things before anyone takes shots at it:
The $254 is real. But it’s only true for agents we built ourselves on Replit. Our third-party AI agents (Artisan, Qualified, Agentforce, Momentum) run $25K+/yr each. Apples to oranges.
The $254 also doesn’t include the soft costs. We update 10K daily. Qbee a few times a week. Budget as much as 0.2 FTE of human attention per production agent. The “deploy and forget” pitch is wrong. Buy don’t Build / Vibe it yourself … if you can. If it exists and meets your needs.
But even with daily improvements and maintenance, managing these two AI VPs is still less time than managing one human VP, much less two.
No 1:1s. No comp conversations. No PIPs. No backfill recruiting. The maintenance IS the management. Every hour tuning the app directly ships output.
A few more numbers from the bill:
– Total Replit bill: $2,324/mo
– Runs 6 production agents + 14 published apps
– 1.9M+ requests served/mo
– Whole stack costs less than one mid-tier SaaS tool
We run SaaStr with 3 humans + 20+ agents. Revenue went from -19% YoY to +47% YoY in the same period.
The full cost of running an agent-augmented business in 2026 is more like $50K-$200K/month, not $254. Still dramatically less than the human-only equivalent.
But the headline is real: two AI VPs. $254. One month.
That’s the new baseline.
(And we’ll show you how to build your own AI VP Marketing + AI VP Customer Success at SaaStr AI Annual 2026, May 12-14 in SF Bay. Join us!!)
Prediction: Utility-class CSS (aka Tailwind) is dead in the water. AI is completely capable of writing and maintaining real, well-factored componentized stylesheets. The mass return to semantic CSS is inevitable.
I for one am breathing a sigh of relief at the prospect of readable view templates again.
AI right now feels like it's for engineers and tech founders.
It's not. The biggest opportunities are for the people closest to real business problems — consultants, marketers, service providers, solopreneurs.
They just need the right on-ramp.
@PassiveSphere@itsolelehmann Thanks for sharing, Denis! So yeah, it might be more beneficial if you are setting up a corporate structure and less when you are a freelancer or similar.
@itsolelehmann I don't understand the tax argument everyone talks about. 🤔 It's slightly lower corporate tax (15%?) and 35% income tax. And a bunch of tax programs that aren't super easy to see through. Compared to EU states like Spain or Schland it's a plus, but not a reason for moving?
@PassiveSphere@itsolelehmann I don't understand the tax argument everyone talks about. 🤔
It's slightly lower corporate tax (15%?) and 35% income tax. And a bunch of tax programs that aren't super easy to see through. Compared to EU states like Spain this might be great, but not a reason for moving?
We've partnered with @rails to give away free tickets to Tropical on Rails 2026, happening April 9–10 in São Paulo.
If you're part of the developer community, this is your chance. Apply now 👇
https://t.co/5AmjvuyHm2
@Lukealexxander Not saying you should recommend us, for that I know too little about your setup. Sorry you had a bad experience with the team! I just was curious what your team considers the state of the art of AI agency tooling since I am navigating that space myself right now. 🏊
@Lukealexxander any tools you recommend to run AI agencies? You mentioned a lot can be vibe-coded, but you probably wouldn‘t want to do so further down the line and have to maintain a bunch of stuff. Are HubSpot or GHL still the way? Anyone in your group using ClickFunnels?
Our video explaining why Y-combinator is asking people to start AI native agencies got 260k views last week..
So we just released a step by step guide to how anyone can build one ASAP
@Lukealexxander CF recently launched an agency model & is powering up on AI capabilities daily, you might be recommending us soon!😅
In your coaching do you sometimes recommend HubSpot or GHL etc.? I the video you mention Claude Cowork, OpenAI & Nano Banana but no other concrete platforms/tools
When you became an engineer, you signed up for lifelong learning. If you find it as hard as ever to know what to learn next, future engineering work will evolve from "build this thing" to "build systems that fix & improve themselves". Plenty of space to learn & practice. 🛠️
Been off X for a long time. Coming back because what's happening in AI right now is too interesting not to talk about — and we're right in the middle of it. Going to share what we're actually building and how. Less polished takes, more real stuff.
@SichDotDev Mine? The Dream for the https://t.co/G22fyAlTsh app is indeed to have "agents" to help you manage your collab partners (and later customer convos) network. Download the list or let our agents manage it on CF.
Or is yours a manager of AI networks? 🤣
In any case, let's goooo! :D