Kyle Penfound

I've seen a lot of people worried that AI will ruin their codebase, which it totally can, but its also entirely preventable with the same processes experienced teams have been following for decades. So I wrote about that dagger.io/blog/evolution…

Your CI/CD system wasn’t built for AI-generated code at scale, and now your team’s velocity is hitting a wall. Join @jpadamspdx and @kylepenfound on July 15th with @BretFisher for a virtual workshop where we’ll explore: •Why legacy CI/CD can't keep up with AI-generated code •How agent-based automation reduces manual toil •How to build LLM-powered tools like an agentic code reviewer

@mitchellh The next step is giving the agent a formatter for when it writes files. Like `gopls format/imports`. Saves a ton of tokens

@mitchellh Yeah just like with devs, giving the right tools goes a long way. They're good at guessing correctly for languages they're familiar with. Reminds me of back in school taking blue book exams where I had to write Java. Not sure how much would actually compile lol

Agents are getting much better at Zig already. But the real unlock is making sure they have access to build the exe and run tests. I find agents can do better at things like Swift apps without that cycle but with Zig they MUST build/test to avoid the mistakes.

Are your CI workflows getting messy? YAML growing, scripts piling up, CI hard to maintain? Define CI once in real code with Dagger—reuse it locally and in @github Actions. In the video below, @kylepenfound shows how to: - Trigger Dagger functions - Reuse logic across dev + CI - Pass secrets securely

What is Agentic CI, and why do you need it now? Join @kylepenfound, @jpadamspdx, and @BretFisher on July 15 for a live engineering deep dive. Get the what, why, and how of AI-powered CI/CD. Register below!

Watch @kylepenfound's full demo here: youtube.com/watch?v=9HP8T7…

@warpdotdev I've been using this since launch and its honestly great. The flow of having an agent in my terminal feels so much more natural than in my IDE or a standalone app. Here it is in action with container-use! youtube.com/watch?v=9HP8T7…

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

What if your AI agent could test multiple ideas without touching your main branch? @kylepenfound's demo shows how to prototype UI changes in parallel, each in its own isolated environment. Fast, clean, and agent-native.

Do I know anyone who works at Hashicorp and can help us with an issue we have with the Terraform Registry? 🙏✨

Explore the @aiDotEngineer schedule with my new @dagger_io module! It gives the built in Dagger agent tools to interact with any llms-full.txt file #use-this-tool-in-agent-mode" target="_blank" rel="nofollow noopener">github.com/kpenfound/llms…

Standing room only at the "Ship Agents that Ship: A Hands-On Workshop for SWE Agent Builders" at @aiDotEngineer by @kylepenfound and @jpadamspdx If you missed out, check out our quickstart and join our Discord to ask questions!

If you're in Timișoara on June 19 and want to hear about @dagger_io, join the Cloud Native Timișoara meetup: community.cncf.io/events/details…

3 days. 3 talks. 1 goal: AI agents that ship with confidence. Catch Dagger at @aiDotEngineer World's Fair: 🛠️ June 3 – Workshop w/ @jpadamspdx & @kylepenfound 🤖 June 4 – @sam_alba on delivery trust 🗝️ June 5 – @solomonstre on containing chaos

Announcing our speakers for the SWE Agents track! Speakers include: @gdb, President & co-founder, @OpenAI @ScottWu46, CEO, @cognition_labs @bcherny, Claude Code, @AnthropicAI @rustinb, Product Manager, AI Coding, @GoogleLabs @TomasReimers, CPO & Co-founder, @withgraphite @ericdahoe, Member of Technical Staff, @augmentcode @itamar_mar, CEO, @QodoAI @k_dumez, DevRel Lead, @withgraphite Anish Agarwal, CEO and Co-founder, Traversal @EnoReyes, CTO, @FactoryAI Matthew Schoenbauer, Founding Engineer, Traversal Raj Agrawal, CTO, Cofounder, Traversal Raaz Dwivedi, Chief Scientist, Traversal @joshalbrecht, CTO and Co-founder, @imbue_ai @kylepenfound, Solutions Engineer, @dagger_io @jpadamspdx, Head of Ecosystem, @dagger_io @sam_alba, Co-Founder, @dagger_io @rbren_dev, CEO, @allhands_ai @MishaLaskin, CEO & co-founder, @reflection_ai World's Fair is 18 miniconferences all co-located in one place in SF so you can meet everyone who matters: - MCP - Tiny Teams (ARR > employees) - LLM RecSys - GraphRAG - Agent Reliability - Infrastructure - Product Management - Voice Al - Reasoning + RL - SWE-Agents - Evals - Retrieval + Search - Security - Generative Media - Design Engineering - Robotics/Autonomy And for the first time TWO two-day leadership tracks for CTOs and VPs of Al: Al in Fortune 500 and Al Architects Join us from Jun 3-5 in SF!

Build AI agents into your software delivery workflows — with full control, observability, and portability. LLMs are now a core building block in Dagger. utm.guru/uijSi

@olearycrew Yes! I literally just published a post about this minutes ago dagger.io/blog/automate-…

If we figure out how to get an AI agent to fix this, we win.

Hot off the press: a new tutorial landed on iximiuz Labs! > Learn how to test and release Helm charts with Dagger Follow the hands-on guide and play with the tech right on the web page without leaving the browser. Learning by doing is the way 🚀 labs.iximiuz.com/tutorials/test…

@dhh I talked about this idea including your specific approach at Kubecon NA '24 and how teams can think of CI in a different way youtube.com/watch?v=tsH3eT…

Local CI in less than 10 seconds for our new product. Who needs cloud runners complicating things?

If you're wondering what the heck AI agents are and why they might matter, start here! We kick it off with where they actually provide value (and where they don't) and go all the way to building a simple agent and showing off some agents I've built