Helping Airbnb hosts improve listings with data. Building Hostalytics. Software engineer + real estate operator sharing experiments and what improves bookings.
When you change your Airbnb title or cover photo, @hostalytics tracks the impact: click rate, page views, booking rate. But a beta tester asked me "is 4.2% click rate good or bad?" and I had no answer. No competitive context anywhere.
So I built one. Planned, reviewed, and shipped in a single session using @garrytan's gstack. It gives you a team of specialists as slash commands inside Claude Code: a CEO who challenges your product thinking, a tech lead who diagrams your architecture, a staff engineer who finds the bugs your tests miss, and a release engineer who gets the work shipped. Solo founder, full engineering org on demand.
I’m one person building @hostalytics, a Chrome extension + Next.js dashboard + Supabase backend + Stripe billing + 34 SEO pages + an AI audit tool + a Google Ads funnel.
290 commits in 75 days. No employees. No contractors. Just Claude Code and a very detailed CLAUDE.md file. Being a dev in 2026 is wild.
The gap between “idea” and “real product” has never been smaller. But the gap between “real product” and “product people pay for” is exactly the same size it always was
@conductor_build is my new favorite tool to build product with. It gives each AI agent its own git worktree. An isolated copy of the repo. Agent A can’t break Agent B’s build. They merge independently.
I had 6 PRs merge into the same branch tonight. Zero conflicts. This is what parallel development actually looks like for a solo founder.
Github commits in 2026:
January: “bug fix” “anoter fix” “mor bug fixes”
March: “fix: self-heal Redis keys that lost their TTL after EXPIRE failure — if INCR succeeds but EXPIRE fails, the key would live forever with no expiry, potentially blocking all audits permanently”
Same developer. The difference is Claude Code writes commits like it’s testifying before Congress
My bet is the biggest winners from AI aren’t random non-technical users becoming developers overnight.
It’s developers becoming massively more leveraged.
That’s where Jevons Paradox comes in. As software gets cheaper to make, people use more of it, not less.
The result is more workflows getting automated, more edge cases becoming worth solving, and more custom use cases becoming economically viable
A bespoke software revolution? I don't buy it.
It'll exist. It already exists. Small consultants and big consulting firms have made custom software for years. It almost always sucks. It’s bloated, confusing, and because the client pays, it’s built wrong in all the ways.
Who’s excited about bespoke software? Software makers! Of course they're excited about building bespoke software — that's what they do. X is full of them. Your feed is full of people who love making software talking about making software. Of course they’re excited about the revolution. Echo, echo, echo...
Most people don’t like computers. Nobody in tech wants to say that out loud. People tolerate computers. They use them because they have to. Given the choice, most would rather not think about them at all.
So when someone suggests that AI means everyone will build their own custom tools, ask who "everyone" is. The three-person accounting firm drowning in client paperwork? They want the paperwork gone, not a new system to maintain. The regional logistics company with 40 trucks? They want the routes optimized, not Joe spouting off about this new system he’s been messing around with. The law firm billing 70-hour weeks? They want leverage on their time, not a software project to design.
They don’t hate technology. But building and maintaining their own critical systems isn’t their wheelhouse, regardless of how much faster and easier it’s become. It's another job on top of the job.
Will these people use AI? Absolutely, for all sorts of things. Will some outliers go deep and build real custom systems? Sure, but they're almost always people who already had some pull toward software. The curiosity was already there. They were dabblers before.
Giving everyone access to software building tools doesn't mean everyone becomes a builder. A powerful excavator doesn't turn a homeowner into a contractor. Most people just want the hole dug by someone else. They don’t want the responsibility either.
The strongest point here is the maintenance burden. Building something is exciting. Owning it is not. Versioning, permissions, exceptions, integrations, onboarding, and reliability are where the romance dies. That is why many businesses will still prefer products over bespoke systems, even if bespoke becomes much cheaper
The best part about using @conductor_build with @garrytan’s GStack to build @hostalytics:
I didn’t write prompts for 34 pages. I said “build SEO pages for our new positioning” and agents that already understood the product did keyword research, planned the architecture, wrote the content, ran tests, and shipped a PR
before: “write me a blog post about airbnb SEO” → generic 500 words
now: orchestrate agents that read your codebase, understand your product positioning, do competitive keyword research, build DRY infrastructure, write 34 pages with real internal links and structured data, test everything, and ship a PR
That’s the difference between a chatbot and an agent system
@conductor_build orchestrated the agents. @garrytan’s GStack ran the reviews. One agent did keyword research. another planned architecture. another built shared infrastructure. Others wrote pages in parallel. A design review agent audited every layout.
total human input: “build SEO pages for our new positioning”, "/design-review", and “/ship”
@Jmark_who pointed out that the @hostalytics homepage needed before/after screenshots to sell the wins harder. Shipped it today. This is the feedback loop I come to @X for
@jcastillo @alexwtlf@hostalytics airbnb ab testing tool? smart niche. site loads fast but screenshots would sell the wins harder — before/after booking lifts?
Should I charge $1 for a trial or give it away free? Sounds trivial. It’s not.
Arguments for free:
- Lower friction
- More signups
- Can always add payment later
Arguments for $1:
- Filters out people who will never pay
- Credit card on file = higher conversion to paid
- $1 with 30-day money-back guarantee = effectively free but with commitment
- You learn faster whether people will actually pay
When you're just getting started, you need signal, not volume. One person paying $1 teaches me more than 100 free signups who ghost.
Nobody wants your feature. They want the outcome it produces. Here’s what that looks like in practice:
Before: "Know exactly which listing changes grow your bookings"
After: "Rank higher on Airbnb."
Before explains the mechanism.
After promises the outcome.
Before is accurate. After is motivating. Both describe the same product.
One sounds like a developer wrote it. The other sounds like a problem worth paying to solve.
Stop describing your product. Start describing the outcome.
Dear @X algo,
I am looking to connect with people interested in:
- Builders
- AI Tech
- Hackers
- Building in Public
- Real Estate
- Short Term Rentals
Say hi & let's grow together ���
@Jmark_who@alexwtlf@hostalytics Thanks for the feedback! I’ll update the landing page to show some more prominent product screenshots. Right now it’s just showing zoomed in captures of some of the UI cards