You're Spending Too Much on AI. You're Also Using Too Little. — Ramp Builders Blog
engineering.ramp.com · 110 words · saved by 3 readers
A big AI bill does not mean you are using too much AI. It means you are buying it wrong.
How we agentically found, validated, and patched ~100 security issues in a 1-week experiment. Agents acting on behalf of a user provides a natural starting point for finance teams beginning to adopt agents, as well as for fully autonomous companies. A big AI bill does not mean you are using too much AI. It means you are buying it wrong. Start routine work on the cheapest model that clears your quality bar. Move up only when the task demands it. Fast mode off, paired with medium reasoning. Latency will still be faster than provider defaults. How and why we built a real-time AI spend and usage p
saved by
related reading
- Building Effective AI Agents \ Anthropicanthropic.com
- What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
- Hard Truths From the AI Trenches - Jason Liujxnl.github.io
- Building Effective AI Agents \ Anthropicanthropic.com
- Router by Ramprouter.com
- AI Is Slowing Downwheresyoured.at
- AI Token Spend Management | Track Token Usage & Spend by Provider, Model, and User | Rampramp.com
- Thoughts on slowing the fuck downmariozechner.at
- Your New Job Is to Onboard AI Agents: How AI Native Companies Actually Operatecreatoreconomy.so
- Ramp: Agentic Workflow Automation for Financial Operations - ZenML LLMOps Databasezenml.io
- Navigating the High Cost of AI Compute | Andreessen Horowitza16z.com
- How much I'm paying for AI productivity software (and the future of AI use)jacquesthibodeau.com