Skip to content

By playing, you agree to uListen's Terms and Privacy Policy and YouTube's Terms of Service.

ClaudeClaude

How Ramp engineers work with AI agents at every step

Ramp runs AI agents across its entire engineering lifecycle: writing code, reviewing it, watching production, and root-causing incidents. Boris sat down with Austin Ray and Rahul Sengottuvelu of Ramp to talk about how they got there.

Rahul SengottuveluguestBorishostAustin Rayguest
Aug 6, 202621mWatch on YouTube ↗

Summaries, chapters, transcripts, and FAQs on this page are made by uListen, not YouTube.

At a glance

WHAT IT’S REALLY ABOUT

Ramp scales engineering velocity using AI agents, workflows, and guardrails

  1. Ramp used the Fable model to tackle hard monolith problems (import cycles and lazy-loading) and to build empirically verifiable CI improvements through shadow testing and production data validation.
  2. Dynamic workflows act like “max test-time compute,” orchestrating many sub-agents to profile, optimize, and iterate over days—helping reduce CI P50 from ~18 minutes to ~6 minutes.
  3. Ramp distinguishes loops (repeatable, known steps like PR babysitting and dead-code cleanup) from dynamic workflows (unknown-step tasks like system optimization and long-horizon experimentation).
  4. The company built internal agent products—Glass for non-technical users and Inspect as a tool-rich “digital coworker”—embedding agents into Slack/web and enabling multiplayer, VM-backed PR sessions.
  5. Ramp emphasizes least-privilege access, trace-by-trace debugging over aggregate benchmarks, decentralized automation building, and ROI-first cost thinking rather than per-engineer token budgets.

IDEAS WORTH REMEMBERING

5 ideas

Pick agent projects with measurable outcomes and low blast radius.

Ramp targeted CI/testing code where performance and correctness can be empirically validated, ran changes in shadow mode, and constrained worst-case impact before widening use.

Use dynamic workflows for problems where the next step is unknown.

They treat dynamic workflows as a higher “thinking dial,” letting the system spawn and orchestrate sub-agents to discover and validate successive optimizations rather than following a fixed plan.

Automations compound when agents can schedule follow-ups and learn from production data.

Fable landed code, scheduled itself to re-run after a day, profiled with real data, and repeated over multiple days until it achieved sustained CI wins and reported results.

Separate “horizontal” repetitive tasks from “vertical” end-to-end ownership.

Loops/routines handle repeated chores (rebasing, fixing CI, code review, dead-code deletion), while agents like Claude Tag/Inspect can run an entire experiment lifecycle with minimal human touchpoints.

Trace-level debugging beats aggregate benchmarks when operationalizing agents.

Ramp focuses on the “correct trace” (which tools/queries/commands should happen) and then adjusts prompts, tools, and access until the agent reliably follows that path.

WORDS WORTH SAVING

5 quotes

I told Fable to fix all our import cycles. I also told it to make our app lazy, so the app boots up, and it's an enormous amount of Python modules. And Fable did-- made a lot of progress in both of these. A lot of this code was merged.

— Rahul Sengottuvelu

Just yesterday, it actually reduced our, uh, CI time from, I think, eighteen-minute P fifty to six-minute P fifty.

— Boris

It'll crank up the exposure, make sure the experiment's running, and maybe a couple weeks later, it'll be like, "All right, I'm gonna ship this variant," and it puts up another PR for that, and I wasn't in the loop at all.

— Boris

Especially with the, the latest models, I, I think they, they require much less hand-holding, and sometimes you just gotta let them cook and get out of the way.

— Rahul Sengottuvelu

We've tried to give Inspect all the tools that a Ramp, uh, builder, so product engineering design person would have. So this includes access to GitHub and Linear and Slack and Datadog and Sentry and various other tools.

— Rahul Sengottuvelu

Fixing Python monolith import cycles and lazy loading with agentsShadow testing and empirical verification in CIDynamic workflows as test-time compute and sub-agent orchestrationLoops/routines for repeatable work vs. dynamic workflows for open-ended tasksAgent tooling: Glass, Inspect, Claude Code, on-call assistantGuardrails: trace analysis, least privilege, layered defensesCost/quality strategy: code review bots, cheap models for automations, ROI mindset, no token budgets

SPEAKERS

  • Rahul Sengottuvelu

    guest

    Engineering leader at Ramp focused on AI-agent infrastructure, CI/CD, and engineering productivity.

  • Boris

    host

    Host/interviewer from Claude who leads the discussion and closes by thanking the guests.

  • Austin Ray

    guest

    Engineering leader at Ramp describing internal AI-agent tools and a terminal-centric Claude Code workflow.

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

Read along on your phone, search it beside the video, or ask your favorite AI app what was said.

iOSAndroidClaudeChatGPTChrome