Catalog
Browse stacks
Filter by use case, model, framework, cost basis, and how recent the writeup is. Cost is only filled in when the source states it — otherwise it's “Not stated.” Separately, a dashed “Est.” tag is a WhatWeRun estimate from public list prices, with its assumptions shown on the stack page. Writeups older than about six months are marked as an older setup, not hidden.
Cost per outputSome teams report what one finished piece of work costs (a code change, a request, an investigation) instead of token prices. We tag that only when the writeup states it, and label benchmark or eval figures. Show those stacks.
2 stacks matching
blog.duolingo.comDuolingo AI STR Fix bug agent
Investigating and fixing Shake-to-Report bug tickets: gathering context (relevant code, tracking events, experiment states, recent PRs, repro steps) and proposing a fix for engineers to verify
ODSEA's LangGraph + Next.js + Supabase production stack
A production platform that 'serves thousands of users' and 'processes AI agent workflows 24 hours a day', documented as a set of public architecture decision records