Topic mix

AI coding agents

12 moments from 12 videos · 30:27 min total

This playlist collects expert insights on building and deploying autonomous coding assistants. Learn how they automate refactoring and code generation to streamline your development workflow.

What Production Knows: Closing the Loop Between AI Agents and the Systems They Build
Play section The promise and risk of AI coding agents
The promise and risk of AI coding agents thumbnail

The promise and risk of AI coding agents

High-velocity AI adoption increases individual developer effectiveness but introduces severe software delivery instability.

Boost your coding productivity with Github Copilot Agent
Play section Defining the capabilities of an AI coding agent
Defining the capabilities of an AI coding agent thumbnail

Defining the capabilities of an AI coding agent

A coding agent embeds a large language model with tool-calling mechanics to actively evaluate tasks and execute workflows.

Stop using Node.js like in 2020! What changed and what you can do today with Node.js
Play section Training AI coding agents to utilize modern runtime capabilities
Training AI coding agents to utilize modern runtime capabilities thumbnail

Training AI coding agents to utilize modern runtime capabilities

How to augment prompt context so coding assistants generate software relying on contemporary native APIs.

Code Is Cheap. Software Isn’t.
Play section The reality of using AI coding agents in legacy codebases
The reality of using AI coding agents in legacy codebases thumbnail

The reality of using AI coding agents in legacy codebases

Coding agents struggle to infer hidden constraints and invisible knowledge scattered throughout large enterprise applications.

The AI-Native Engineering Org: What’s Real, What’s Hype, What’s Next
Play section Accelerating right of code workflows with AI agents
Accelerating right of code workflows with AI agents thumbnail

Accelerating right of code workflows with AI agents

AI speeds up code reviews, deployment, and incident management to keep pace with increased code volume.

Completing the Feedback Loop
Play section Expanding AI agents for code review and security scanning
Expanding AI agents for code review and security scanning thumbnail

Expanding AI agents for code review and security scanning

Specialized software agents automatically manage code reviews, scan for security vulnerabilities, and handle repository merges.

When Agents Meet Legacy: Never Change a Running System
Play section Evaluating AI agents for iterative legacy code modernization
Evaluating AI agents for iterative legacy code modernization thumbnail

Evaluating AI agents for iterative legacy code modernization

Using AI agents to analyze legacy applications provides an iterative, low-risk approach to handling difficult codebases.

Unlocking the AI Black Box: Building Trust in the Era of Agentic Production
Play section Tracing agentic capabilities and step-by-step code execution
Tracing agentic capabilities and step-by-step code execution thumbnail

Tracing agentic capabilities and step-by-step code execution

Observing what coding agents execute behind the scenes, including underlying bash scripts and token consumption.

Humanoid Runs Wild, Google Rewrites Headlines and Slow AI - Justin Halsall and Schepp
Play section Web tools sabotaging AI and Mozilla agent coding resources
Web tools sabotaging AI and Mozilla agent coding resources thumbnail

Web tools sabotaging AI and Mozilla agent coding resources

A tool artificially slows chatbots while Mozilla proposes a code-sharing platform for AI agents.

From Vague Ideas to Precise Specifications – AI as Process Catalyst
Play section Feeding structured software requirements into autonomous AI coding agents
Feeding structured software requirements into autonomous AI coding agents thumbnail

Feeding structured software requirements into autonomous AI coding agents

Clean requirements improve the implementation plans of autonomous coding tools while aiding broader team cultural adoption.

5 things I wish I hadn’t done building my AI agent
Play section Defining and measuring success for AI coding agents
Defining and measuring success for AI coding agents thumbnail

Defining and measuring success for AI coding agents

Capturing transaction outcomes like acceptance, ignorance, and explicit rejection reveals true product viability.

The LLM Evolution: From Sequence Imitation to Verifiable Reasoning
Play section Connecting reasoning engines to autonomous coding agents
Connecting reasoning engines to autonomous coding agents thumbnail

Connecting reasoning engines to autonomous coding agents

Interfacing conversational generators with robust executable external APIs organically creates persistent autonomous frameworks capable of programming.

Your mix. Instantly.

More mixes