Use peer agent communication only for the research stage of a content system
At a glance
Christopher Johnson describes keeping most of a 13-agent content pipeline hierarchical while giving market, technology, and policy researchers peer messaging, followed by a synthesizer producing the same downstream brief format. This workflow is listed under builder, claude-code, agent-teams, research-synthesis, workflow-design.
An appraiser in South Korea reports spending two months building a report-writing program with Claude Code, then having colleagues test it and discussing adoption within the firm.
A Technically writer documents a month-long Claude Code experiment managing a Meta Ads account: fresh sessions read prior logs, pull performance data, decide, act or abstain, and commit the updated history.
Product Hunt’s Cronloop lets you describe a recurring job in Markdown, pick Codex or Claude Code, connect tools, and run agents on a loop with durable memory that can self-improve each run.
Show HN: Statewright's Rust engine enforces plan/implement/test states for Claude Code (and other CLIs) via MCP hooks—wrong tools are blocked structurally, shrinking death spirals for both small and frontier models.