#Sub-Agent best practices
61 related articles
·3 min
Deep Dive into ChatGPT Ultra's Parallel Sub-Agent Architecture: Parameters, Configuration, and Best Practices
A deep dive into ChatGPT Ultra mode's parallel sub-agent architecture, covering concurrency limits, delegation depth, token optimization, and configuration best practices for GPT-5.6.
Read more →
·3 min
Kimi K3 Hands-On Tutorial: Claude Code Sub-Agent Configuration & GPT-5.6 Comparison Test
Complete guide to configuring Kimi K3 as a Claude Code sub-agent, including API setup, YFlow workflow building, and head-to-head comparison with GPT-5.6 and Claude Fable 5.
Read more →
·4 min
Claude Code from Scratch: A Complete Guide from Installation to Enterprise-Grade Development
A complete guide to Claude Code from beginner to enterprise practice: covering CLI installation, connecting domestic LLMs via CC Switch, basic commands, Git workflow integration, automated bug fixing, and engineering capabilities like MCP and SubAgents.
Read more →
·3 min
The AI Coding Landscape: Model Tiers, Tool Camps, and a Deep Dive into MCP/Skills/CLI
A systematic map of today's AI coding landscape: the evolution from ChatGPT to Claude Code, LLM capability tiers, tool camps like Cursor/Copilot, and the three key weapons of the Agent era — MCP, Skills, and CLI.
Read more →
·8 min
LangChain Crash Course: A Complete Roadmap from Zero to Agent Development
A systematic roadmap from LangChain and LangGraph to multi-agent development, covering RAG, Tool Calling, MCP, and more, helping developers break into AI app development.
Read more →
·5 min
AI Coding Getting Worse With Every Edit? Skills v1.1 Reveals the Real Cause and Solution
AI code getting messier with edits? The root cause isn't weak model capability but a lack of context and process. A deep dive into Matt Pocock's Skills v1.1: grilling, vertical-slice tickets, TDD, and WebFinder.
Read more →
·2 min
23K Stars on GitHub: The Hackathon Champion's Ultimate Claude Code Configuration Guide
A Claude Code open-source config with 278 skills and 67 sub-agents helps developers ship a full MVP in 8 hours. Covers security scanning, silent failure detection, and experience migration. Free under MIT license, compatible with Cursor and Codex.
Read more →
·3 min
Codex Practical Guide: A Complete Roadmap from Beginner to Advanced AI Programming
Master Codex AI programming assistant with this complete guide: CLI setup, slash commands, agents.md governance, MCP protocol, multi-agent systems, and enterprise plugin development.
Read more →
·3 min
40-Hour Stress Test: An In-Depth Evaluation of GPT-5.6's Coding Capabilities
A developer spent 40 hours exhausting Codex Pro's weekly quota to benchmark GPT-5.6 on real enterprise projects. Key findings: proactive root cause tracing, stronger global codebase understanding, and stable long-task execution.
Read more →
·3 min
The Complete OpenAI Codex Practical Guide: From Installation to Enterprise Deployment
A complete guide to OpenAI Codex: CLI setup, slash commands, AGENTS.md, MCP integration, multi-agent collaboration, and a RAG customer service project walkthrough.
Read more →
·4 min
Agent Loop in Practice: A Guide to Building Self-Improving Automation with Guardrails
A deep dive into building verifiable, self-evolving Agent automation loops with Claude Code and Codex — covering Loop Contracts, four trigger types, three-phase execution architecture, and Evolve Loops.
Read more →
·3 min
Complete Codex Practical Guide: From Getting Started to Enterprise-Grade AI Programming
Master OpenAI Codex end-to-end: CLI setup, slash commands, AGENTS.md design, MCP protocol, multi-agent coordination, and enterprise plugin development.
Read more →
·5 min
ChatGPT Work Officially Launches: How GPT-5.6 Is Reshaping the Way You Work
OpenAI launches the GPT-5.6 model family (Sol/Terra/Luna) and ChatGPT Work, enabling automated financial analysis, local file operations, Codex coding, and cross-app workflows—AI officially becomes a real work partner.
Read more →
·6 min
GPT-5.6 Hands-On Deep Dive: ChatGPT and Codex Merge, Full Analysis of the Sol Model
GPT-5.6 is officially released, merging ChatGPT and Codex into one app and launching the three-tier Sol, Terra, and Luna models. A detailed breakdown of 16 hands-on tests plus Worker mode and Codex dev upgrades.
Read more →
·7 min
The Five Pillars of Production-Grade AI Agents: A Battle-Tested Guide from Demo to Deployment
Databricks tech lead Sandy shares a five-pillar framework for production-grade AI Agents—evaluation, observability, data foundation, orchestration, and governance—with a £85K retail banking failure case to bridge the demo-to-production gap.
Read more →
·6 min
Omnigent Open-Sourced: A Meta-Harness for AI Coding Agents Built by Databricks
Databricks open-sources Omnigent, a Meta-Harness for orchestrating Claude Code, Codex, and more AI coding assistants together—with built-in guardrails, cross-model workflows, and real-time collaboration. Get started in 10 minutes.
Read more →
·3 min
Claude Code Caching Explained: A Practical Guide to Saving Money and Speeding Up
A deep dive into Claude Code's Prompt Caching mechanism, covering the three-layer cache structure, invalidation rules, lifecycle management, and best practices to reduce API costs and boost response speed.
Read more →
AI Engineer World's Fair Closing Day: …
·2 min
AI Engineer World's Fair Closing Day: The Loops Debate, State of the Industry, and What to Build Next
AIEWF closing day recap: the agent loops debate, the State of AI Engineering report, and a keynote on what to build next — covering AI engineering's key divides and trends.
Read more →
·7 min
Claude Code Command Orchestration: One-Click Content Research and Auto-Publishing
Learn how to orchestrate Claude Code custom commands to chain content research and social media publishing agents into a fully automated workflow with one command.
Read more →
·3 min
Benchmarking Popular Claude Skill Libraries: A 5-Step Core Pattern for AI Agent Development
A deep-dive evaluation of Addy Osmani, Matt Pocock, and Gary Tan's skill libraries, distilling a 5-step Research→Prototype→Plan→Build→Test agent dev loop and why the best skill system is always your own.
Read more →