Head of Ecosystem @dosu_ai
Los Angeles, CA
Joined November 2008
- Tweets11.2K
- Following1.7K
- Followers3.6K
- Likes48K
Taylor Dolezal retweeted
From Prototype To Production Agents That Remember nitter.cf/i/broadcasts/1AxRnZQjn…
I'm SO excited about @GoEntire's Trails. Code changes, agent reviews, and findings all in one place! It's been enlightening to follow findings through to a fix and see why the agent marked it resolved. Congrats on the launch, @ashtom, @lizziepika, and team!
Agents reinvented how we produce code. It changed our tools and half of our workflow. It’s time for the other half to catch up.
Today, we’re shipping Entire: the Git forge for agent-human collaboration. We’ve built @GoEntire using Entire. Now we want to see what you'll build with it.
Here’s why and what’s different. 🧵
Taylor Dolezal retweeted
if coding agents are running in their own cloud environment and verifying their work before pushing, do we even need a separate CI system?
Taylor Dolezal retweeted
Love markdown, hate markdown tables.
I just released tableau (github.com/pragdave/ts-table…), a different way of marking up nice-looking tables in Markdown docs. Support for common MD preprocessors; easy to add more. And it's AI friendly.
Field journal, vol. 01 📓 AGNTCon + MCPCon, San Jose!
So far it's rain, palms, a full room for @dexhorthy's State of the Software Factory, a Bigfoot and a glazed T-rex.
Here through Friday. Building agents or MCP? Say hi and let’s talk! 👋 😄
Taylor Dolezal retweeted
Attention Deficit Ep. 8 is outtt!!! check it out :D @onlydole
GPT-6 Luna vs Sol. Can a harness close the gap? attentiondeficitpod.substack…
Taylor Dolezal retweeted
I'm starting to feel that @linear should be for human planning + tracking and there should be a separate ticketing system for agents
Taylor Dolezal retweeted
JetBrains studied 4,782 real coding-agent sessions.
~94% of SWE-Bench Pro tasks are features or bug fixes. In real use, that’s under half. The rest: explaining code, planning, reviews.
No benchmark is universal. Measure how your team uses agents.
In Naresh Jain's one-task test, GPT-6 Luna passed 3 of 10 attempts alone and 10 of 10 with a harness, at two-thirds of Sol's estimated cost. It took 35 minutes to Sol's under 7. Would you wait? More on Attention Deficit Ep. 8 with @alexa_griffith_! youtu.be/NwpN-glza4U
ALT Attention Deficit Episode 8 thumbnail. Alexa Griffith and Taylor Dolezal stand in front of a starfield above Earth, with a blazing sun and the word SOL on the left and a violet moon and the word LUNA on the right.
Taylor Dolezal retweeted
regret not buying duet.ai back when I had the chance in 2023 💸
Taylor Dolezal retweeted
It's Dosu Drop Day! 🎃
Dosu answers with live context from connected MCP servers like Sentry, Datadog, GitHub, and Confluence. Connect one to a Library with MCP Tools (beta), starting with read-only credentials.
go.dosu.dev/drop-oct26-x
Taylor Dolezal retweeted
This coming Monday, we're bringing together three incredibly talented engineers and founders to dig into a question and theme for the night: Are we running too many agents?
Josh Bleecher Snyder (@exedev)
@josh_wills (@datologyai)
@beyang (@ampcode)
We're already at 240 RSVPs! That's so fantastic. :-) This meetup is focused on a technical audience, so come learn and make some new friends. There will be an open Q&A at the end to ask questions and share thoughts. luma.com/0qr6bxcw
Taylor Dolezal retweeted
This feels short-sighted. The goal shouldn't be to measure the productivity of your individual developers.
The goal should be to build a system (i.e software factory) that minimizes the need for developers to be in the loop (i.e maximizes agent autonomy).
What if your AI budget went to the engineers who use it best?
Blanket usage caps are a hiring freeze in disguise.
Introducing efficiency-based auto-approvals for your most productive engineers, plus Devin Coach to help everyone get there.
devin.ai/blog/efficiency-bas…
