Veeral Patel

head of applied ai 💳
investing

[Veeral Patel @vral]

@0interestrates Yup https://t.co/bKtKA2z5H4

[Veeral Patel @vral]

Increasingly think buy vs. build is becoming buy and build*

You'll buy trusted products for what they do well. Then use their APIs/MCP/CLI to make them your own.

*if you’re sufficiently AI pilled, high agency, or worried about giving yet another vendor access to your data

[Veeral Patel @vral]

Increasingly think buy vs. build is becoming buy and build*

You'll buy trusted products for what they do well. Then use their APIs/MCP/CLI to make them your own.

*if you’re sufficiently AI pilled, high agency, or worried about giving yet another vendor access to your data

[Veeral Patel @vral]

We've been making Ramp easier for your agents to use via MCP

Weekly users are up 4x since Q2 and now growing 13% WoW

What can we improve here? Reply or DM - our team is actively monitoring

[Veeral Patel @vral]

Very excited for the work @rene_sultan and team are doing to share more of our real world benchmarks

[Ramp Router @ramprouter]

Claude Fable 5.2 is live on Router. It’s the top Anthropic model on Ramp Accounting Bench, and it gets more tasks right on the first try than Opus 5.5.

Same API key, new model id:
https://t.co/fmsxY66GSJ

[Veeral Patel @vral]

@rahulgs Why is a credit card company working on efficiently encoding company data into models?

[Veeral Patel @vral]

We have this natively set up in Ramp btw

[Tanay Jaipuria @tanayj]

Cloudflare doesn't have token leaderboards or limits, but uses alerts for token spend management:

- $300 in a day: that employee gets an email
- $500: manager gets an email
- $1,000: VP gets an email

(via CTO @dok2001 on No Priors)

[Veeral Patel @vral]

@RampLabs Brb asking Glass to summarize this for me

[Veeral Patel @vral]

@ypatil125 🍳

[Veeral Patel @vral]

@alexsongis @tryramp How could it be improved?

[Veeral Patel @vral]

@adrienphila 👑

[Veeral Patel @vral]

We've been making Ramp easier for your agents to use via MCP

Weekly users are up 4x since Q2 and now growing 13% WoW

What can we improve here? Reply or DM - our team is actively monitoring

[Veeral Patel @vral]

@sshchoholiev This is MCP only!

[Veeral Patel @vral]

@_EricHu @yunyu_l

[Veeral Patel @vral]

@awilkinson https://t.co/lokJ0zUjgv

[Ramp Router @ramprouter]

AI spend needs guardrails. Ramp Router lets teams set budget caps for an organization, individual members, and API keys.

Here’s how the controls work 👇

[Veeral Patel @vral]

@ArushShankar Long Long Lake

[Veeral Patel @vral]

https://t.co/t6BpAYJ3Bz

[Karim Atiyeh @karimatiyeh]

https://t.co/HxYe8oNoeO

[Veeral Patel @vral]

@adithya_iyengar Agency is all you need

[Veeral Patel @vral]

Ramp Travel now allows you to filter by Starlink flights

[Devon Tivona @devontivona]

Yesterday I had five hours on a flight with Wi-Fi that barely worked. “Has Wi-Fi” is a pretty low bar. So I added a @Starlink filter to @tryramp travel. Now you can check the odds of getting Starlink before you book. 🚀

[Veeral Patel @vral]

Yeah this sounds like a good idea

[Evis Drenova @evisdrenova]

there's likely a new ramp/brex to be built specifically for AI-native companies around token economics

[Veeral Patel @vral]

Everyone has been asking me why Ramp is building a router

We started by helping companies manage spend.
As more of their money goes to buying intelligence, our job is to help 85k customers decide between models, too

Excited about the progress so far, but still a lot of work ahead

[Vals AI @ValsAI]

How do model routers compare to individual models on real agentic tasks? Introducing the Vals Router Index.

Routers promise to balance quality and cost across a fast-moving model frontier. We put that promise to the test with an independent evaluation of five routers (OpenRouter Auto, FireRouter, Ramp Router, Jev, Fugu Max) against every single model on the Vals Index, using the same agents, ~1,250 tasks and graders across finance, coding, law and tax.

We found that routing didn’t consistently deliver better value. Every router was beaten on both score and cost by at least one single model.

[Veeral Patel @vral]

@asciidiego Not yet, but we'd love to work with you on it. DM me?

[Veeral Patel @vral]

Ramp Router is literally free money if you're spending 5.5-8% on top of list prices with OpenRouter

I'll personally come to your offices in NYC or SF to get you onboarded

[Ramp Router @ramprouter]

Rolling something out to an entire engineering org means dealing with the less fun stuff: budgets, billing, data controls, and more.

We just shipped a bunch to make it easier for Admins to bring teams onboard:

1. Org management: Invite engineers and assign co-admins. Everyone gets their own API key, a one-line install for their coding agents, and routing strategies for what they're building.

2. Policies: Configure which models and providers people can use, and set data retention policy at the org and individual levels.

3. Spend controls: Set budget caps for the org, each individual, and each API key. See spending across the org.

4. Key management: See everyone’s key, share provider keys across the org, let personal keys take precedence, and control fallback to Ramp's shared key.

5. Payments: Prepay with a card or pay monthly based on usage.

6. One Ramp account, one bill: Already use Ramp? Sign in with your existing Ramp account and put Router usage on your monthly Ramp statement.

We want every engineer to have the best setup for their work, without making finance and IT nervous about what it's all going to cost.