Forward Future founder Matthew Berman launches Loop Library, a directory of repeatable, verified AI agent workflows · Digg

Forward Future founder Matthew Berman launches Loop Library, a directory of repeatable, verified AI agent workflows · Digg

Posts from X

Most Activity

VIEWS62.5KBOOKMARKS1.1KLIKES622RETWEETS24REPLIES25

Matthew Berman@MatthewBerman

One of my new favorite loops from Peter Steinberger (@steipete):

“Refactor until you are happy with the architecture. After each significant step, live-test the system, run autoreview, and commit. Track progress in /tmp/refactor-{projectname}.md.”

https://signals.forwardfuture.ai/loop-library/loops/architecture-satisfaction-loop/

Matthew Berman@MatthewBerman

Just launched Loop Library - a curated list of agent loops you can use right now.

Find loops, submit your own, tokenmaxx!!

https://signals.forwardfuture.ai/loop-library/

4h62.5K6221.1K

Matthew Berman@MatthewBerman

My favorite loop: "Continue optimizing the code for speed. After each significant change, measure page-load performance across every page under the same repeatable test conditions. Continue until every page loads in under 50 ms."

https://signals.forwardfuture.ai/loop-library/loops/sub-50ms-page-load-loop/

Matthew Berman@MatthewBerman

Just launched Loop Library - a curated list of agent loops you can use right now.

Find loops, submit your own, tokenmaxx!!

https://signals.forwardfuture.ai/loop-library/

8h38.4K370429

Matthew Berman@MatthewBerman

New Loop submitted!!

By my friend @hnshah - A workflow that turns a ticket, failing behavior, or customer complaint into a proven root cause, minimal patch, and reviewer-ready handoff.

Full prompt here:

https://signals.forwardfuture.ai/loop-library/loops/ticket-to-pr-ready-loop/

Matthew Berman@MatthewBerman

Just launched Loop Library - a curated list of agent loops you can use right now.

Find loops, submit your own, tokenmaxx!!

https://signals.forwardfuture.ai/loop-library/

2h14.3K6670

Matthew Berman@MatthewBerman

There are two kinds of loops: > deterministic (ex: when site speed less than 50ms) > LLM as judge (ex: when the website is fast enough)

LLMs are becoming fantastic judges. This opens up significantly more knowledge work to be looped.

Matthew Berman@MatthewBerman

Just launched Loop Library - a curated list of agent loops you can use right now.

Find loops, submit your own, tokenmaxx!!

https://signals.forwardfuture.ai/loop-library/

1h3.2K3617

Matthew Berman@MatthewBerman

Shout out to http://here.now for hosting and partnering!

Matthew Berman@MatthewBerman

Just launched Loop Library - a curated list of agent loops you can use right now.

Find loops, submit your own, tokenmaxx!!

https://signals.forwardfuture.ai/loop-library/

8h10.9K2921

Will Washburn@willwashburn

Very cool, will check it out. Looks like you have 1 builder and 1 reviewer and they don’t directly communicate is that right? Does that ever get stuck for you? Or maybe I’m misunderstanding but I’m my experiments I’ve seen the reviewer and builder go back and forth in perpetuity without a third vote. Found real time context sharing to be useful in that regard as well as opposed to one builder going down a path too deeply before getting feedback.

2h4611

Ethereal@inferencegod

yeah you read it right, they coordinate through committed git state, not direct chat. the back-and-forth-forever thing is real for pure two-party loops, but two things stop it here. the reviewer isn’t just voting, it runs a mechanized gate (revert the fix and confirm the test goes red, coverage ratchet, patch coverage) so the verdict is pass/fail against real code, not an opinion that can ping-pong. and there’s a no-progress breaker: consecutive waves with no tree change park the loop to me instead of looping forever.

your “going too deep before feedback” point is fair though. i’ve actually watched the reviewer pull the builder back from a bad path a few times, so commit-then-review catches more than you’d think. real-time sharing getting feedback earlier is a real edge, i won’t pretend otherwise. 0.6.0 (live now) already adds a planner that grills the spec before the builder builds, basically the third perspective you’re describing, just upstream instead of a runtime vote. the coordination stuff you’re hitting is exactly what i’m building next, more coming tonight !

2h201

Elix@eliautobot

@MatthewBerman @steipete Loops are prompts..prompts to loop..that prompt the loop to loop... I still don't get how loops aren't just prompts to "check your work before you are done" 😵‍💫 am I missing something?

3h1791

Brad Mills 🔑⚡️@bradmillscan

@RohithThakurwar @MatthewBerman dang this is a cool visualization. Can you drag things around and add from this screen?

4h352

Matthew Berman@MatthewBerman

@RyanTanaka thanks got any loops you use?

8h741

Matt Van Horn@mvanhorn

@MatthewBerman Smart

7h581

Alpha Batcher@alphabatcher

@MatthewBerman congratulations with another great launch

let me check this Loop Library

8h521

Matthew Berman@MatthewBerman

@alphabatcher please submit your loops :)

8h401

Matthew Berman@MatthewBerman

@willwashburn say more

8h84

Ethereal@inferencegod

@MatthewBerman Nice! will submit autonomy-loop

7h141

Gautham Pai@gauthampai

@MatthewBerman I don't see how "The overnight docs sweep" is a loop. Are you calling it a loop because it runs every night?

44m121

Ryan Tanaka@RyanTanaka

@MatthewBerman Not yet!

8h111

Sonia_Tam@soniatamayodiaz

@MatthewBerman i did a loop with video yesterday in CC and worked great. even if youve created a template, sometimes it drifts...and nailed the first one. try it!

7h41

Matthew Berman@MatthewBerman

@gauthampai The goal of the loop is documentation completeness

35m14

Matthew Berman@MatthewBerman

@bradshannon @steipete yes!

2h14