Skip to main content
AgentsUse

Curated workflows

Curated Agent Stacks

A stack is a recipe, not a ranking: a specific job, the verified components that do it, the order they run in, the credentials they touch, and the points where a person stays in charge. Every component links to its source-verified profile, and each stack names what to do when a step breaks.

Web research and briefingResearch Briefing StackTavily finds and extracts sources, a LangGraph loop plans and drafts, and Langfuse keeps every run inspectable. 3 verified components. 2 human checkpoints.Browser QA and regression checkingBrowser QA StackPlaywright runs the checks that must pass every time; the Playwright MCP server lets an agent investigate the failures. 3 verified components. 2 human checkpoints.Turning websites and documents into agent-ready dataWeb Data Pipeline StackCrawl4AI crawls pages, MarkItDown converts documents, Mem0 keeps what was learned, and LangSmith shows where bad answers come from. 4 verified components. 2 human checkpoints.Coding assistance with project contextCoding Assistant StackFilesystem and Git give the agent hands, Context7 keeps library docs current, and Sequential Thinking structures the hard problems. 4 verified components. 2 human checkpoints.