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.
5 stacks matching
Pinterest's Analytics Agent and its tuning loop
An internal Analytics Agent that searches Pinterest's data ecosystem (tables, dashboards, metrics) to answer questions, plus an automated 'loop engineering' process that improves how reliably it follows required steps
langchain.comLangChain's GTM Agent sales artifacts
LangChain's internal GTM Agent building sales artifacts (account plans, proof-of-value docs, proposal decks, onboarding plans) from deal context, and suggesting the right one before customer calls
Datadog's Insights agent, tuned by its own traces
The agent behind Datadog Agent Observability Insights, which analyzes agent traces to find cost and reliability problems; Datadog uses Insights on that agent's own traces to cut tokens and fix failing tool calls
Netflix Pensive AI failure diagnosis
AI error extraction and on-demand root-cause debugging for failed data and ML workloads on Netflix's data platform (Maestro, Spark, Trino, Druid, Titus), where roughly 100,000 workloads fail on peak days
shopify.engineeringShopify River on Remote Dev (mobile)
Shopify's Slack agent River building, testing, and proving mobile (iOS and Android) changes on remote Macs, from bug fixes and PR feedback to overnight automated fixes