Ashwin benchmarked Jev as a replacement for LLM-based reranking in Ramp's accounting product, and the results are very promising
Jev matches current accuracy on GPT-5.6 Luna, but decreases tail latency by 10x to 300ms at 3x lower cost
We're excited to get this into production for 70k customers as soon as we stop running into rate limits :)
The first thing I did at @tryramp was set up distributed tracing, structured logging, and metrics for Inspect, our background coding agent.
We now have full visibility in to everything the system is doing: the browser, CF workers/DOs, @modal sandboxes, database calls, etc.
Most importantly, Inspect now has visibility in to itself. It can self-triage runtime errors it encounters and create PRs to fix them.
Every morning, it reviews the past 24 hours of its own @datadoghq dashboard, identifies systemic issues, new errors, and long tail latencies, and has a summary + PR waiting for me at 9am.
@steipete@cirrus_labs Makes sense for you to try that first since you’re already on GH actions so no need to migrate especially if you have custom actions as dependencies.
@steipete I agree with you in theory but in practice GH actions UI is actually quite bad, especially at streaming logs in realtime which is kind an important piece of it.
Buildkite’s web UI puts the rest of the CI space to shame, it’s not even fair.
Would you pull Saquon Barkley off the field to file expense reports?
You better not say yes.
Welcome @tryramp’s newest, fastest partner and investor, and the star of our very first big game ad — @saquon! Let’s go birds 🦅
Amazing / rare opportunity! Ramp (fastest growing startup of all time, iykyk) is looking for Android contractors to help build their rocket ship. Option for full time available too (1/2)
I was laid off from Lyft today, so I'm looking for work!
If you're hiring remote or in Montreal, hit me up.
12 years iOS experience, 9 years Swift.
My DMs are open.