Loading video...

Video Failed to Load

Go Home

Introducing Warp 2.0: the Agentic Development Environment 1️⃣ Top overall coding agent: #1 on Terminal-Bench, 71% on SWE-bench Verified 2️⃣ Agent multi-threading: build features, debug, and ship all at once 3️⃣ The first all-in-one platform for agentic development 🧵 Learn more

1,445,551 views • 11 months ago •via X (Twitter)

10 Comments

Warp's profile picture
Warp11 months ago

⛓️ Warp is built for the future of development. The future is one where developers code by prompt instead of coding by hand. Agentic coding workflows don’t need another chatpanel, auto-complete platform, or CLI app. Agentic coding requires a platform that supports prompting, multi-threading and agent management, deep context, and human-in-the-loop collaboration.

Warp's profile picture
Warp11 months ago

⌨️ Tell your computer what you want to do A universal input for launching agents and running commands. Attach files, images and urls for context as you ask Warp to code, debug, pull logs, and more. Prefer to talk? Save time with voice input, which supports minutes-long, complex prompts just by talking to your computer.

Warp's profile picture
Warp11 months ago

🏗️ A state-of-the-art coding agent + an inline code editor Prompt agents to fix issues, build features, and ship production-ready code. They’ll search your entire codebase across repos, pull from your Warp Drive docs, run CLI tools, and use MCP servers to gather the context they need to tailor their responses. Directly edit code-diffs without context switching to another app.

Warp's profile picture
Warp11 months ago

🧠 By the way— Warp writes really high quality code and is the best in the world at agentic terminal tasks. We’re top four on SWE-bench Verified with 71%, and #1 on Terminal-Bench with 52%.

Warp's profile picture
Warp11 months ago

👫 Spin up an agent, and then spin up another Need to resolve merge conflicts, add a feature, and fix build errors? Run multiple agents in parallel. Warp agents notify you when they need human help: approving a code diff, running a kubectl command, approving a commit message. Plus, you can keep track of all your agents in one, centralized panel.

Warp's profile picture
Warp11 months ago

🕹️ Evolved from Warp’s best-in-class terminal Warp 1.0 aimed to create the best terminal in the world. We innovated on the command line, adding a code-editor for terminal commands, block based input and output, and a highly configurable design. In Warp 2.0, you get all of these benefits — and you can still use Warp as a great terminal if you’d like.

Warp's profile picture
Warp11 months ago

More AI, on us To celebrate Warp 2.0, we’re increasing monthly AI request limits for all paid users: Pro: 1,000 → 2,500/month Turbo: 3,000 → 10,000/month (+ unlimited Lite requests) Pay as you go available after you use your full allotment

Warp's profile picture
Warp11 months ago

🛠 Download Warp today, and try it for yourself.

Warp's profile picture
Warp11 months ago

🏆 Read more about what you get with Warp 2.0, and why we built it

Ben Holmes's profile picture
Ben Holmes11 months ago

I feel so lucky to be a part of this. The level of design thinking, attention to detail, and sheer engineering muscle on the Warp team is unmatched. Always bet on Warp 👏

Related Videos

🚀New Amazon Q Developer agent for software development is available to customers: This agent is based on a new agent architecture that has exciting results coming from the SWE-bench scores (on the full and verified benchmarks) representing AI models’ ability to resolve real-world coding problems. Interesting aspect of Q Agent is that with these newest updates, Q drove nearly 50% more successful coding tasks completed. What makes Q Dev Agent remarkable? The agent architecture is not just about using the best LLMs (which we do), but also giving the agent the ability to constantly explore multiple paths to find the best way to resolve a particular problem (and back tracking when it has reached dead end like a developer would do). Needless to say, we are just getting started on the developer agent and we are constantly pushing to advance our AI capabilities while maintaining quality, security, privacy, and reliability to keep Amazon Q Developer an innovative and trusted option available to our customers using agents for software development. We highlighted the results of our first SWE-bench submission of Amazon Q Developer back in June blog post; with these updates, our new agent resolves 51% more coding tasks than its previous iteration on the SWE-bench verified dataset, and 43% more on the full dataset. That’s the difference a few months make, and I can’t wait to share what our teams will deliver at re:Invent this December. Here's a quick demo showcasing our new Agent in action:

Swami Sivasubramanian

28,946 views • 1 year ago