The demand for https://t.co/KrZUREk0hW has been wild. Some of the world’s largest engineering orgs are eager to get their hands on the tools behind how we build at @tryramp.
We’re taking it a step further: if you have 100+ engineers and want to bring your entire engineering workload to Inspect, we’ll fly your engineering leads to NYC for a white-glove onboarding with our team.
Invite batches are going out daily. DM me if you want in.
I'm excited to speak at @tryramp's first Cool Machines technical meetup this Thursday alongside engineering leaders from Crosby and Ro.
Engineers from Anthropic, Cursor, Datadog, Linear, Meta, OpenAI, Profound and more are joining us.
Register here: https://t.co/EG6sb0RbNi
we're so excited to bring Inspect to the world. we built inspect for ourselves with so much love and care. we really tried to get the details right.
when set up, everything just works. as any great tool, it lets you focus on the task at had, and is otherwise unobtrusive. it scales to a growing company with shifting priorities, to complex codebases, it's collaborative.
i can't wait for more people to try
https://t.co/xZAMN3AEo0
2023
Nobody:
Expedia: Let's build a ChatGPT plugin so people can book travel with AI.
2026
Me: I want to use Instinct to book my trip
Delta: The FUCK you will
We're hiring a Staff Security Engineer at Ramp to lay the foundation of our crypto custody stack! Come work on problems like signing infra, HSMs, enclave attestation with a small, focused team
https://t.co/NtVMUJkMDw
The Modern Data Stack is over, long live the Post-AI Data Stack🫡🤖
I wrote about how technological shifts change what a data team can build, the features of post-AI data stacks, what we've built at @tryramp, and what data teams can learn from @nbcsnl.
https://t.co/W3GEXDLdjY
ramp web services 🤔
more seriously, you could hire an olympic sprinter to walk your dog. it'd go great. it'd also be overkill. but that's basically how most companies run ai right now. a frontier model on every task, including the ones a model a fraction of the price would nail
our obsession is helping companies get more done with fewer dollars and hours, so we built ramp router to fix this for ourselves. it tests every new model on real work, then routes each request to the cheapest one that clears the bar. routing's just the start, it's making 100+ calls per request on what to cache, when to batch, when to reach for something stronger
output is same or better but already cutting costs by 30%+. the alpha group is run-rating 2.75T tokens/month, at 99.99% uptime. excited to open this up more. lots of founders asked about this after last week. we're onboarding companies a few at a time, drop your info on the link below from @vral, @rahulgs, and the @RampLabs team and we'll reach out asap, we'd love to work hard to cut your costs and help you ship the way ramp does
Every week, the price-intelligence-latency frontier shifts, and we expect this trend to continue
Across 100+ use cases in our product, keeping all up to date with the right model is a challenge -
Either we're losing out on intelligence for the dollars we spend, or we're spending too much money for the intelligence the feature needs
Ramp Router lets you benefit immediately without rewriting your application. We cut our LLM costs by 30%, while also making our features smarter and faster.
We built it for Ramp. Now we’re opening it up to everyone.
get access here: https://t.co/oGnv7GUHsl
Today we’re launching Ramp Router.
3 years ago, we built an internal LLM router at @tryramp that powers AI products for 70,000 customers.
Back then it was mostly about saving money.
Now it feels obvious: the best model changes constantly. GPT, Claude, Gemini, Grok, Qwen, DeepSeek, Kimi, GLM - prices and capabilities move every week.
So we’re opening up access to everyone.
One OpenAI-compatible endpoint. The right model for every request. Lower cost without rewriting your app.
Reserve access to use it.
We deployed 10,000 background agents to security-scan our codebase. The system is simple, scales with compute, and runs on publicly available models. From the scan, we fixed several high-severity vulnerabilities.
Fax Agent engineer here. Some details on how it works:
* It's not actually connected to Ramp in any meaningful way. It's just a gag.
* There's a real fax machine hooked up to Claude on the other side of this. I'm using https://t.co/aqMTB16QJT REST API to stand up "machines", retrieve & send faxes, and send a webhook. When the chatbot machine receives a fax, it sends a webhook to my webserver, Claude OCRs, the text, comes up with a response, renders a PDF with that response, and then sends it back.
* The "fax machine" I'm using in the video is just a printer/scanner that I've jury-rigged to behave like a fax. I'm not just manually printing and scanning. When I scan a doc, our printer email address sends me an email. When I receive a "fax" in my test fax machine (not the chatbot), it also sends me an email. I have a script on my machine that I run to scrape my inbox with playwright (yep) and either send the scanned doc as a fx to the chatbot machine or print the received fax to the printer using `lpr -P <name of printer> <name of pdf doc>`. I built this because it's impossible to find a self-service faxing service where you can both send and receive faxes. I tried.
I'll keep it running for the day in case anyone has a fax machine and wants to try it out.
Excited 🫠 to announce our newest product: the Ramp Fax Agent.
You can now submit receipts and memos for your transactions entirely through your fax machine. AI-powered. Enterprise-grade. Autonomous.
We built Ramp to meet customers where they are. For some of you, that's 1997.
Your work is now saved in Ramp Sheets.
Every sheet you build automatically backs up to the cloud. Open the menu to jump back into any past project instantly.