ZEE

I don’t use AI, AI uses me…

@threepointone exactly, I’ve recently been letting my remote orchestration agents tunnel in and open us Claude sessions on my machine so I can be in the loop with what’s happening. It’s the reverse of what everyone’s doing

if you want an agent to be able to work locally/remote, switching whenever however, you probably want the harness to be running remote (and tunnelling _into_ your laptop) etc.

@TTrimoreau 12

Be honest… How many unfinished SaaS projects do you have?

@TTrimoreau think more*

Founders, Is AI helping you think better or think less ?

@FredKSchott @flueai only on Vercel? not for long…

some thoughts on eve, especially re: @flueai and the larger agent builder space. The biggest surprise: eve is vercel-only. You can't deploy it outside of vercel and it requires a full bet on their stack -- vercel runtime, vercel sandbox, vercel workflows, vercel cron jobs, etc. etc. short-term limitation, or the start of a larger "managed agents" play by vercel? eve is filesystemmaxxing. this feels specifically optimized for agents, who love the codebase consistency and have no trouble keeping track of 10+ magic file and folder conventions as the project scales to 100s of files. (^^ this is probably the most interesting design decision here. I have a ton of respect for anyone taking a big swing like this if this is intentionally optimized for agents. makes total sense.) eve has a custom-built harness. probably not interesting to most people. I'm curious if they will leverage the new ai sdk HarnessAgent concept to swap different harnesses. otherwise there's a lot of great stuff here. lots of good features. The dev-server-as-TUI is great. you can tell how much attention and care went into this. excited to see our two projects continue to explore the same space from different directions!

@gregisenberg sometimes I avoid working till everyone’s left the office so I can go full stream of consciousness down the mic to Claude

Once you get used to using voice-to-text AI to get your computer to do things, typing on a keyboard feels kinda painful.

@MrBeast you never watched any vampire movies bro? those mother fuckers depressed

Would you rather stop aging for 100 years or receive 1 billion dollars right now?

@CliftonSellers see what I did there

@CliftonSellers it’s almost literally an oxymoron

Need opinions: Is passive income a myth?

@ThePrimeagen x.com/codewithzeee/s…

What the fuck is a graph?

not sure there’s ever been a more appropriate time for this meme - the best “AI engineering” cross over

@boristane you bet

@CodeWithZeee show me

everyone's talking about graphs, last week i built agent knowledge graphs as a service, i call them promise networks. let me know if you want to try it

@jpalioto what’s your take on the old promise network concept x.com/codewithzeee/s…

Started at graph thank you very much. You’re so far behind it’s not even funny.

@KentonVarda I can’t work out of this is a good or a bad thing, I hate the sound of it but if it worked…

I asked Sol to debug a very specific bug with a provided reproduction. It spawned a tree of dozens of sub-agents, 6-8 layers deep, asking itself to do things like write a report on all RPC interfaces in the project. It's like watching a government agency at work.

@steipete x.com/CodeWithZeee/s…

Are we still talking loops or did we shift to graphs yet?

@onusoz snap x.com/CodeWithZeee/s…

acpx v0.4 ships Agentic Workflows, or as I like to call them "Agentic Graphs" It let's you create node-based workflows on top of ACP (Agent Client Protocol), to drive any coding agent (Codex, Claude Code, pi) through deterministic steps This let's you automate routine, mechanical legwork like triaging incoming PRs, bugs in error reporting, and so on... For example, OpenClaw receives 300~500 new PRs per day. A lot of them are low quality, but they still relate to real issues, so you have to address them somehow You need to: - extract the intent - cluster them based on intent - figure out if the proposed changes are legit, or whether they are slop local solutions, like trying to catch flies instead of drying out the swamp - if the PR is too low quality or the intent is not clear, close them - run AI review on them them and address any issues that come up - refactor them if the changes are half-baked - resolve conflicts - and so on... So that when the PR is presented to the attention of the maintainer, all the routine legwork is done and the only remaining thing is the decision to (a) merge, (b) give feedback to the PR author, or (c) take over the PR work yourself I wanted to build this feature since a couple months now, since Codex got so good. OpenAI models are now good at judging implementation quality, so I found myself repeating the same steps I wrote above over and over I also tried putting all this in a single prompt. But I believe there are workflows that should not be a single prompt, but a sequence of prompts in the same session That is because like humans, LLMs are prone to PRIMING. I claim that putting all steps in the same prompt at the beginning of the context will generally give suboptimal results, compared to revealing the intention to the model step by step Creating such a workflow also gives more OBSERVABILITY into the each step that an agent is supposed to take. Agent generates JSON at the end of each step, and that structured data can be used to monitor thousands of agents running at the same time in an easier way, on a dashboard Similar features have been introduced in e.g. n8n, langflow. But AFAIK they are not integrating ACP like the way I do I wanted to have a fresh approach, and to build an API that I can develop freely the way I want, so I created a new workflow API inside acpx The video is from the workflow run viewer, but that is not where you build the workflow. You build it by using the acpx flow typescript API. See examples/pr-triage in acpx repo Before building that, I started from a Markdown file with a Mermaid chart of the flow I had in mind. The Markdown file acts as a spec for the flow, and I have built the workflow through trial and error. I call this process "workflow tuning" I started working on acpx repo PRs one by one, tuning the flow, slowly scaling to more PRs. Finally, when I felt confident, I ran it in parallel over all external open PRs in the acpx repo. I believe it already saved me hours this week My next goal, if well received, is to set this up on a cloud agent so that it can process the 300~500 PRs the OpenClaw repo receives every day, in real time, as they come in I believe this will save all open source maintainers around the world countless hours and make it much easier to herd and absorb external contributions from everyone!

@dexhorthy say “working backwards” in the mirror 3 times and Jeff will appear and grant you 1 wish

today's fun ai coding tricking - when doing the high-level part of your plan, do an amazon-style "working backwards" approach - write the customer-facing blog post about the feature BEFORE you start building this can surface so many edge cases and help you dial in on prioritizing the important parts, and just is much nicer to read (plus you can post it after you ship 🙂)

@kelvinbuildss Jira

Name an app that literally nobody hates

going to launch 7 start ups in a week, not sure which week but it’s going to be a week that’s for sure