Activity
Mon
Wed
Fri
Sun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
What is this?
Less
More

Memberships

AI Automation Agency Hub

325.6k members โ€ข Free

AI Developer Accelerator

11.3k members โ€ข Free

24 contributions to AI Developer Accelerator
Sharing what new have built during last 5 months.
Hi all, I kind of dropped off from the community during last few months as I got a good gig at a large bank to build an AI AML platform for them. But I will be dropping in again .. Sharing how my SDLC agentic harness look like and how I make sure quality of code I produce is high. I am still doing all this inside Claude Code. Can give a demo or presentation if community is interested.
0 likes โ€ข 17d
Hey @Dmitry Avramenko , are you going to be at the meeting to talk about your method? It would really cool to hear it from you
AI Developer Accelerator โ€” Coaching Call - June 2nd
Brandon figured out how to make Codex argue with itself about your code quality while you sleep, and Scott's parking app made $5K over a single weekend. If you missed last week, you missed the memo on why some of us are suddenly very interested in "adversarial code review" and side projects that pay rent. ๐Ÿ“ž HOW THE CALLS WORK The calls can run 2+ hours. We want to make sure we're respecting everyone's time. Especially those of you who actually show up. Here's the structure: ๐Ÿ‘‰ Reply to this post with your questions before the call ๐Ÿ‘‰ If you submit a question and you're on the call, you go first ๐Ÿ‘‰ We work through questions in the order they came in ๐Ÿ‘‰ Then we open it up for everyone else If you can't make the call but want your question answered, drop it in the comments. We'll get to it. But priority goes to people who are there. The goal is simple: if you're taking the time to show up, you shouldn't have to wait behind questions from people who aren't even on the call. For those of you tracking the open threads: Alex is rebuilding his studio app from scratch with multi-tenant architecture, Bastian has healthcare partnership negotiations to report back on, and Hiral is restarting her vocabulary app with a proper ShipKit roadmap. If you were in the middle of any of these threadsโ€”or if you have questions about overnight Codex sessions, Hermes migrations, or PDF extraction that actually worksโ€”drop them below. ๐Ÿ”— ZOOM LINK (save this) https://us06web.zoom.us/j/81995207847?pwd=Xe6u6LmIQOmCP5VTnOwWYjDBfZNKGB.1 ๐Ÿ“… WHEN Tuesday June 2nd at 6PM ET Looking forward to seeing you on the call!
0 likes โ€ข 17d
Hey @Patrick Chouinard My questions regard as to how people are using the /goal function on Codex or Claude. I was considering Ralphy but people have beens teering me to /goal and I want to know how people are generally using for executing PRDs? Thanks you! Juan T.
Has anyone tried Ralphy for creating long agentic loops to tackle execution of PRDs
https://www.youtube.com/watch?v=cdIJ92Tx20Y https://github.com/michaelshimeles/ralphy Seems like a create way to fasten pace from PRD to first POC....would be interested in what people think?
0 likes โ€ข 21d
@Paul Miller thanks Paul...will check it out :)
How do you guys use Gemini CLI in your dev work
I heard some folks using it for online research....do you guys use it for design as well? Deciding whether or not add it to my stack
0 likes โ€ข May 12
@Nejc Skoberne great to know
0 likes โ€ข May 12
Agentic DevOps is what I heard from another engineer. Is it like Kiro CLI of AWS? I use it to review AWS resources.
AI Developer Accelerator โ€” Coaching Call - April 28th
Last week Brandon burned through $120 in Claude credits in 30 minutes while proving the "SaaSpocalypse" is realโ€”rebuilding a $20 SaaS in under an hour and making everyone panic about their lack of moats. If you missed the chaos, you missed the survival guide for what happens when AI makes code trivial to replicate. ๐Ÿ“ž HOW THE CALLS WORK The calls can run 2+ hours. We want to make sure we're respecting everyone's time. Especially those of you who actually show up. Here's the structure: ๐Ÿ‘‰ Reply to this post with your questions before the call ๐Ÿ‘‰ If you submit a question and you're on the call, you go first ๐Ÿ‘‰ We work through questions in the order they came in ๐Ÿ‘‰ Then we open it up for everyone else If you can't make the call but want your question answered, drop it in the comments. We'll get to it. But priority goes to people who are there. The goal is simple: if you're taking the time to show up, you shouldn't have to wait behind questions from people who aren't even on the call. We've got some delicious follow-ups brewing: Ty is running his ShipSafe security scanner against Morgan's catio site (cybersecurity meets cat patios), Patrick is polishing that elegant multi-model pipeline for open source release, and Tiran is stripping his landing page down to a single address input. Perfect time to jump back in if you want to see how the experiments land. ๐Ÿ”— ZOOM LINK (save this) https://us06web.zoom.us/j/81995207847?pwd=Xe6u6LmIQOmCP5VTnOwWYjDBfZNKGB.1 ๐Ÿ“… WHEN Tuesday April 28th at 6PM ET Looking forward to seeing you on the call!
0 likes โ€ข Apr 28
Hey folks, here is my questions: I noticed Claude Code slowing down significantly over the last two months. It's gotten to the poin in which I rely more and more on Cursor instead of Claude Code. In fact, I find GPT 5.5 in Cursor fast and really good at complex task that I would otherwise leave to Claude Code. Alternatively, do you guys rely on other CLI based models like GLM or Kimi k 2.5? I know @Bastian Venegas has been relying on GLM for tasks. A cost benenfit analysis discussion would be interesting.
1-10 of 24
Juancho Torres
3
32points to level up
@juancho-torres-8802
Data Scientist passsioante about finance and political economy

Active 9d ago
Joined Jan 19, 2025
San Diego
Powered by