980: AI Coding Explained

Key takeaways

Keep up with the evolving terminology and tools in AI coding to stay effective.
Choosing the right editor and model is crucial for a successful AI coding experience.
Agents and subagents facilitate delegating tasks and managing workflows efficiently.
Standardizing files like agents.md can improve consistency in AI interactions.
Understanding the distinction between skills and agents can enhance task management.
Leverage slash commands and hooks to streamline coding processes and maintain code quality.
Explore plugins and MCPs to expand the capabilities of your coding tools.

Summary

Introduction to AI Coding

Scott Talinsky and Wes Boss introduce the podcast episode, aiming to explain AI coding in 2026. They acknowledge the rapid change in terminology and tools in AI coding, highlighting the confusion caused by numerous files, agents, models, and techniques.

Tools for AI Coding

The hosts discuss various tools for AI coding, emphasizing the importance of text editors like VS Code and GUI applications such as Open Code. They outline their personal preferences for coding tools and the functionalities they find most beneficial.

Understanding AI Models

Wes and Scott delve into the importance of choosing the right AI model. They share their experiences with different models, explaining how each can drastically change the experience and outcomes in coding tasks. They highlight the distinction between models suitable for detail-oriented tasks and those better suited for creative work.

Agents and Subagents

The episode covers the concept of agents in AI coding, explaining their role in making modifications to files. They explore subagents as a means to delegate specific tasks while allowing the main agent to operate simultaneously.

Managing Agents with agents.md

The hosts discuss the agents.md file, which provides prime context for AI interactions in coding projects. They express frustration over the lack of standardized practices for such files but recognize their necessity in guiding AI results effectively.

Skills vs. Agents

Scott and Wes compare the usage of skills and agents in workflows. They discuss how skills can define specific tasks while agents manage ongoing interactions, providing insights into optimizing both for productive coding.

Slash Commands and Hooks

The utility of slash commands and hooks in streamlining coding processes is highlighted. The hosts explain how these functions allow for quick, reusable prompts and automate checks on code quality.

Plugins and MCP

They conclude with a discussion on plugins and MCP (Model Connection Protocol), emphasizing their roles in enhancing functionality and interconnecting AI tools with external services.

Show notes

Wes and Scott talk about the state of AI coding in 2026—from editors and models to agents, skills, slash commands, MCPs, and more. They unpack what these things actually do, how they overlap, and how to use them effectively without overcomplicating your setup.

Show Notes

00:00 Welcome to Syntax!

01:39 The tools: editors, terminals, GUIs

05:27 Wes’ and Scott’s current AI setups

13:17 Picking the right model

18:58 How exactly do agents work?

22:32 Subagents and parallel workflows

24:29 Brought to you by Sentry.io

24:54 What goes in agents.md (and what doesn’t)

26:47 Skills vs agents

Skills

Superpowers

34:03 Slash commands as reusable prompts

36:02 Hooks and keeping your code from going off the rails

38:00 Plugins and bundling your setup

39:24 What MCP is and why it’s powerful

40:54 Cloud agents and running jobs remotely

43:47 Choosing the right AI tool

47:41 Sick Picks + Shameless Plugs

Sick Picks

Scott: ULTRALOQ Bolt Fingerprint WiFi Smart Lock

Wes: St. Denis Medical

Shameless Plugs

Syntax YouTube Channel

Hit us up on Socials!

Syntax: X Instagram Tiktok LinkedIn Threads

Wes: X Instagram Tiktok LinkedIn Threads

Scott: X Instagram Tiktok LinkedIn Threads

Randy: X Instagram YouTube Threads