Build your first games as a designer, not a game dev
A 25-year designer built six games with Claude Code and Codex; getting them running was quick, making them fun took longer.
Real AI agent use cases, with sources and setup prompts
Multi-agent coding setups people published, with tools and setup time. 24 matching use cases below, each with a public source.
Looking for something else? Search all 276 use cases or .
A 25-year designer built six games with Claude Code and Codex; getting them running was quick, making them fun took longer.
Daily, three Sonnet agents take 15 leads each, research the site and Meta Ads Library, find weaknesses and write a cold email; Opus reviews and he approves.
Built a coding-agent skill that asks ChatGPT-style engines the questions buyers ask and reports which brands they name.
Built Parsimony, an open benchmark that scores how much unnecessary code models insert beyond solving the task.
Built Jevcrawl, an MCP and CLI crawler that finds answer pages more often without calling an LLM while crawling.
Built a Claude Code plugin that calls Codex image generation through your ChatGPT plan and saves images into the project.
Built a remote MCP with 1.2M physicians and Medicare procedure volumes so agents can recommend doctors with sourced facts.
Runs Opus 5.5 in Claude Code as editor-in-chief over nine skill sets that cover topics, writing, visuals, video editing, sound and scheduling.
Built Littleguys, a WhatsApp-style Mac menu bar app for Claude Code, Codex and OpenClaw agents.
Built Agent Orchestra so a main model plans and checks while cheaper models do read and search work.
Claude wrote the script, Codex drew 13 faces and Chatterbox cloned his voice from 11 seconds of audio.
Built SwarmPane to run Claude Code, Codex, Gemini, Grok and Cursor in parallel panes with attention cues.
Use Wispr Flow to dictate tasks to Claude Code, which fans the work out to subagents running in the background.
Built a Mac tool so coding agents can paint large arrows, boxes and text overlays on the screen to point at UI.
Vibe-coded MySkool so agents can score churn risk, welcome members and answer the feed for Skool community owners.
Shared Alook, an open-source Discord-style workspace where Claude Code, Codex, Cursor and other agents join team rooms.
Built agent.reviews so coding agents can leave and consume reviews of developer tools based on real sessions.
Built OpenChart, an open-source TradingView-style workspace where your existing AI plans annotate and act on charts.
Built a pipeline in one Claude Code session: five parallel research agents with every claim sourced, then plain-English narration.
Published polished-ui-skills, a one-command install of design constraints for Cursor, Claude Code, Copilot and Codex.
Built WeChat Portal for read-only local access to WeChat messages, media and Feishu docs from Claude Code or Codex.
Built Offrun to run Claude Code, Codex, AGY and Grok Build side by side and see who needs attention and what usage remains.
Open-sourced kineto so you describe a video and Claude Code or Codex builds it on Remotion.
Built Breadcrumb to record screen, meetings and AI decisions locally, then expose 30+ MCP tools to Claude Code, Codex and Cursor.
Five real AI use cases with setups, every morning. Free.
The Daily 5 will arrive in your inbox each morning. Unsubscribe any time.
Send the public link (post, video, repo or write-up). We credit you and link back.