Reading up on Ralph
6 deep · digging since jan 24
- if your team is too busy doing their 'normal job' to experiment with AI, you're preparing them to be replaced
Managers must prioritize AI experimentation for their teams or risk rendering them obsolete, as AI skills have become essential for job security in 2026.
- if your team is too busy doing their 'normal job' to experiment with AI, you're preparing them to be replaced
Managers must allow teams time to experiment with AI, or they risk leaving employees unprepared and vulnerable to replacement in today's market.
- snarktank/ralph: Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.
Ralph is an autonomous AI agent loop that repeatedly runs Amp or Claude Code to implement PRD items until all are marked complete, using git and progress files for memory.
Takes
Here's my AI coding workflow and all the skills I'm using:Idea -> /write-a-prd -> PRDPRD -> /prd-to-issues -> Kanban BoardKanban -> ralph.sh -> Ralph LoopRalph Loop -> Manual QALinks below to skills pic.twitter.com/rxWFFRUH83
@mattpocockuk
Just got Scout, my @openclaw agent, to use ralph to start grinding through a 154-file migration to implement RLSHere what I said to Scout in Telegram:> run a ralph loop using your ralph skill and the https://t.co/PE0XIEhBu7 file in /scripts/ralph. this loop should have 154… pic.twitter.com/p8AtseVMVV
@ryancarson
Claude Tasks are more powerful than I expected.Spent a few hours testing them against Ralph.The difference? When to use each? How to get the most out of them?Here's what I found: pic.twitter.com/UtlZWNymhv
@saasmakermac