context management
9 videos across 4 channels
Context management is the disciplined handling of information AI systems rely on—preserving state, prompts, caches, and guardrails to keep tools aligned with real-world goals. The videos illustrate practical techniques, from AI-assisted editors with clear workflows and rules to plan-mode and websocket-enabled state across calls, while cautioning against brittle prompts and overreliance on static agent docs. The focus is on building reliable, scalable development processes where context feeds better decisions and outputs.
ADLC: Claude Code's New Lifecycle for AI Coding
The video explains why traditional SDLC is inadequate for agentic AI systems and introduces the Agentic Development Life
The expanding toolkit
The talk reframes the model as an expanding toolkit where tool use, context management, code execution, and computer use
It’s Broken… The Claude Code Vs Codex Debate Is Finally Over
The video pits Opus 4.7 against GPT 5.5 across usability, planning, building, debugging, memory, and agent capabilities
I don’t really like GPT-5.5…
The video critically evaluates OpenAI GPT 5.5, noting impressive capabilities and strong code generation but significant
How does Claude Code *actually* work?
The video explains what a harness is in AI coding assistants, how it provides tools and context to the model, and why th
Cursor Crash Course & AI Coding For Beginners
The video introduces Cursor as an AI-assisted coding environment, outlining its interface, pricing, and how to use AI at
AI mistakes you're probably making
The video argues that AI tools are evolving quickly and outlines practical mistakes to avoid, focusing on problem framin
I can't believe nobody's done this before...
A deep dive into OpenAI's websocket move, why it matters for maintaining state across tool calls, and how it enables muc
Delete your CLAUDE.md (and your AGENT.md too)
The video argues that agent MD and Claude MD files are not a guaranteed boon for AI coding tasks and emphasizes context