AI Agent Tutorials & Automation Walkthroughs
Hands-on walkthroughs that show how to turn a recurring task into a working AI agent workflow. Follow the setup, adapt the prompt, and ship practical automation without managing code or servers.
GLM-5.3 reasoning_effort: low, high or max
GLM-5.3 reasoning effort has three levels and no off switch. What low, high and max cost in output tokens, and how to migrate without failed requests.
- 02 Tutorial Run GLM-5.3 in Claude Code: Full Setup
Set up GLM-5.3 in Claude Code with a GLM Coding Plan. The base URL, the model default that gives you GLM-4.7 instead, and how to fix error 1113.
- 03 Tutorial How to Use Grok: Every Access Path
How to use Grok 4.5 across Grok Build, Cursor, the SpaceXAI API, gateways, and Office add-ins: identity, cost, and whether you need a terminal.
- 04 Tutorial How to Use Kimi K3 in Codex
Run Kimi K3 inside Codex with codex-router: the guided install, the two Kimi auth routes, and what actually changes once K3 is driving the loop.
- 05 Tutorial Run Kimi K3 in an Agent, No Self-Hosting
Want Kimi K3 working in an agent without a GPU? A managed platform runs it with skills and memory, so you skip the 1.56TB self-host bill.
- 06 Tutorial I Made a Product Video With video-shotcraft
A real step-by-step run of video-shotcraft: making a 36-second product video with a coding agent and Remotion, with every command, error, and fix.
- 07 Tutorial How to Try Inkling AI Free Online (Playground Guide)
You can chat with Inkling AI free right now in the Tinker Playground, no download needed. Here's how to get in, plus every other way to use Inkling.
- 08 Tutorial How to Run Inkling AI Locally: Hardware & Setup
Inkling's weights are free on Hugging Face, but can your hardware handle 975B parameters? Realistic needs, NVFP4 vs BF16, and every supported runtime.
- 09 Tutorial How to Use ChatGPT Work for Research and Recurring Tasks
Learn how to use ChatGPT Work for research, reports, files, and recurring tasks, with a task brief for sources, constraints, evidence, and review checkpoints.
- 10 Tutorial Sonnet 5 vs 4.6: The Hidden Cost Jump
Sonnet 5 keeps Sonnet 4.6's per-token rates but a new tokenizer produces ~30% more tokens. Here is the real cost math and the migration traps to avoid.