It started by teaching our non-technical staff how to prototype their ideas in HTML files using Claude Code.
It's a much better way of communicating ideas than writing product specs.
We now have an agent harness that lets them build their ideas directly into our app.
Most of our smaller app PRs are now submitted and merged by non-engineers.
Today, OpenAI released Agents API.
We got early access a couple months ago and it's enabled us to think differently about how we can architect complex, multi-step workflows.
We used to write prompt chains and manage our own set of tool calls, but now we can use agents directly in our code much like how Codex works on your laptop.
It’s already helped us solve several problems that would’ve otherwise required us to build custom agent infrastructure.
4
6
449
If your goal is to add value to the world, don’t constrain your thinking to only problems that could be solved with a website. There are so many problems in the world. Most can’t be solved with NextJS & Stripe.
2
228
We've been doing the same thing. Last month we got hit with a $4,900 bill from LlamaParse. Within 24 hours we had our own vibe-coded document parser live in prod. Our monthly spend on document parsing went from $4,900 to $250.
✨ I replaced all these SaaS with my own vibe coded now, so about $25,000/mo savings:
- Weather API -> My own vibe coded weather service using Norway's meteorology API
- Image resizing API -> My own vibe coded image resizing API with NodeJS's Sharp + Redis (saves ~$1,500/mo)
- Google Vision NSFW detection -> My own $0/mo vibe coded NSFW detection service with Python's NudeNET (saves ~$2,500/mo)
- Cloudflare Streaming -> My own $0/mo Nginx VPS video streaming (saves ~$250/mo)
- API Flash -> My own $0/mo screenshot service (for social images) (saves ~$250/mo)
- New Relic + IPHub -> My own $0/mo error monitoring, DDOS blocking and fleet management service (called error2telegram) (saves ~$250/mo)
- Human moderators -> My own moderation on all my sites with @xAI (saves ~$10,000/mo)
- IFTTT -> Telegram bot (saves ~$100/mo)
- Photopea as editor inside Photo AI -> Vibe coded my own photo editor (saves ~$100/mo)
- Mapbox -> Vibecoded my own free replacement with OpenFreeMaps (saves ~$500/mo)
- Uptimerobot -> My own $5/mo Uptime Canary app running on Kuma (saves ~$50/mo)
- Ghost blog -> My own $0/mo blog platform
- Customer support -> @featurebasehq + AI support bot (saves $5,000/mo)
- Scrapingbee/SerpAPI -> My own $1/mo scraper with Patchright (save ~$250/mo)
I think I have reached my final limit of replacing my SaaS services as I have these left, but that'd mean becoming an ICANN registrar (I don't want 😁), managing my own email (I don't want), managing my own hard drives at home in a storage (I don't want) and managing my own servers at home too (I don't want) and running my own GPU rig at home (I don't want):
- Cloudflare Domains
- Cloudflare Email Sending
- Cloudflare R2 Storage
- Backblaze B2 for backups
- Hetzner for all my servers for all my sites (VPS)
- xAI for all LLMs for all my sites (so many things like moderation, writing emails, anything)
6
375
Cole Striler retweeted
In 2014, I took on real estate brokers w/ my company Opendoor
In 2023, I took on the $500B insurance broker industry
Now we protect $50B in revenue across 1000+ clients
Don't be deceived by insurance brokers. I’ll personally show how we can help: [email protected]
My brother recently graduated from Air Force SERE school and told me about a concept they teach there called “quitting by action.”
He said many people who fail aren’t incapable. They quit internally, but stick around until they get kicked out because it’s easier to say “I didn’t make it” than to admit “I quit.”
This applies to work, relationships, and almost everything else.
Either be all in or be out. But don’t quit by action.
So great is man’s hunger for truth that he will gladly devour a lie, provided it has the taste of certainty.
1
446
Cole Striler retweeted
Not exaggerating: WithCoverage's growth team's calendar is booked back-to-back until mid July... but old school AEs won't succeed here.
I'm hiring if you are:
- IQ + EQ
- Curious + Kind: every client is a puzzle to solve
- HUSTLE
Great comp + equity. DM me
Cole Striler retweeted
WithCoverage Engineering is < 10 people
Huge opportunities to own scope across Growth, Platform, and Product. NYC, in person. Doubled team since Jan, Cashflow Positive in April
You:
- Experienced with a history of excellent work, OR
- Young, smart & ambitious
- DM/Reply!
ChatGPT can write code, pass the bar exam, and explain quantum physics but it still can't convert a .heic to .jpeg
1
517
Two years ago, I got introduced to JD.
I knew nothing about insurance. Turns out it's a $300B+ market that still runs on emails and PDFs. Brokers are incentivized to sell expensive policies. Customers end up overcharged and underinsured at the same time.
The pitch: use AI to give every business the kind of risk management that only Fortune 2000 companies could afford. I wanted in.
We've spent the last two years building tools that let us operate differently than any other brokerage. AI that audits policies line by line. Systems that catch what brokers miss. Software that replaces the endless manual work this industry runs on.
This is how we save customers up to 30% while actually improving their coverage.
Today we announced our $42M Series B led by Sequoia and Khosla.
Really proud of what we've built. Hiring engineers if you want to come break stuff with us.
This quoted post is unavailable.
Cole Striler retweeted
Replying to @big_duca
Not useless a gun is much more useful in a navy's seals hands then some random shooter. You're the navy seal
We're hosting a dinner in NYC tomorrow for engineers & founders. 15 spots. Come meet interesting people and share ideas. DM me.
3
312






