Yong Hong Tan
Founder of Kavela. Runs a team of Claude Code and Codex agents every day, and writes about orchestrating them: routines, approvals, and getting more out of the AI you already pay for.
Kavelakavela.aiHow to use Claude Code and Codex for non-coding tasks (and keep them running)
Claude Code and Codex are strong at non-coding work: research, writing, files, reports and recurring ops. How to set up a folder for it, what each tool does differently on schedules and approvals, where the DIY setup costs you, and how to run it in Kavela.
Kavelakavela.aiWhat would you pay $20 to get automated? That's your use case
What can I automate with Claude, Claude Code or Codex? Use a simple $20 test for picking the right job, six recurring jobs that pass it, what not to automate, the honest cost of running them yourself, and a prompt to start one in Kavela.
Kavelakavela.aiHow to build an agent orchestration pipeline: stages, architectures, and what breaks
A production agent orchestration pipeline has eight stages: trigger, plan, route, isolated execution, approval gates, deliverables, memory and resume. How each works, which multi-agent architecture to pick, what breaks in practice, and how Kavela runs it.
Kavelakavela.aiHow to auto post on your LinkedIn with an AI agent (and approve every post)
Set up an AI agent that drafts LinkedIn posts from your notes, launches and Notion pages, runs on a weekly schedule, and posts from your own account only after you approve the exact text. Inputs, voice, cadence, API vs browser, and the setup in Kavela.
Kavelakavela.aiClaude calendar: how to schedule Claude Code tasks and run Claude Code on a schedule
How to run Claude Code on a schedule: cron with the headless CLI, GitHub Actions, and Claude Code's own schedulers. The pitfalls (expired logins, a sleeping laptop, runs nobody sees) and how a calendar of routines running in the cloud on your Claude plan avoids them.
Kavelakavela.aiClaude Code orchestration: how to run multiple Claude Code agents without losing track
What Claude Code orchestration means in practice: subagents, parallel sessions in git worktrees, and a lead agent that splits the work. Where it breaks (handoffs, ownership, approvals, sessions that die) and how to run it with a manager agent on your own Claude plan.
Kavelakavela.aiCan Claude manage other agents? How to set up a Claude manager agent that delegates
Yes, Claude can manage other agents. How the manager and worker pattern works, how to prompt a lead agent to delegate well, the three ways it fails (the manager does the work, context gets lost, nobody reviews) and how to run workers on your own Claude plan.
Kavelakavela.aiClaude task management: give Claude Code a real task board instead of one long chat
How to manage tasks with Claude Code: one task per piece of work, each with an owner, a due date, a status and a deliverable. Set it up by hand with markdown task files, see where that stops working, and how a calendar of tasks filed by a manager agent fixes it.
Kavelakavela.aiCodex orchestrator: how to run multiple Codex agents at once
How to orchestrate Codex agents in parallel: split the work, give each agent its own worktree or cloud task, track owners, collect diffs, route approvals and keep runs alive. Plus how Kavela runs Codex workers on your own Codex plan.
Kavelakavela.aiHow to coordinate multiple AI agents so they stop stepping on each other
Running several AI agents brings file collisions, orphaned tasks, duplicate work, lost context and silent waits. How to coordinate multiple AI agents: one coordinator, one owner per task, isolated workspaces, shared context, one approvals queue and a visible schedule.
Kavelakavela.aiChoosing an IDE for agent orchestration: what you need to run many AI agents
What a tool needs to orchestrate AI agents: one view of all work, clear ownership, schedules, approvals, logs and deliverables, and agents that keep running with your editor closed. How an editor, terminal multiplexing and a calendar workspace compare.
Kavelakavela.aiToo many Claude Code sessions? How to manage multiple AI agent sessions without the friction
Managing many Claude Code or Codex sessions means tab sprawl, runs that die when the laptop sleeps, lost context and constant checking. Practical fixes (names, worktrees, tmux, notes, notifications) and the structural one: sessions as tasks on a calendar.
Kavelakavela.aiHow to use AI more efficiently: delegate whole outcomes instead of prompting turn by turn
How to be more efficient with your AI use: write briefs with a goal and done criteria, batch and schedule recurring work, keep context in one place, review deliverables instead of watching runs, and get full use from the Claude or Codex plan you already pay for.
Kavelakavela.aiUGC farm with Claude: hooks, scripts and a weekly plan with Claude Code
How to run a UGC farm with Claude: audience research, hook writing, script variants in your brand voice, reviewing generated videos against reference clips, and a weekly content plan, with your approval before anything posts. Plus how to run it in Kavela on your Claude plan.
Kavelakavela.aiUGC farm with Codex: how to build an AI UGC pipeline
Build a UGC content farm with Codex: the pipeline stages from hook research to video generation, captions, scheduling and metrics, the code Codex should write and run, the rules that get accounts in trouble, and why every post needs a human approval.