AI-assisted coding
2:29How to cut Claude Code token usage
A workflow that saves tokens: index the codebase once with graphify and share it with the team, plan from the graph and requirements, confirm the plan, delegate to subagents, then validate.
1:26context-mode: keep tool output out of your context
How the context-mode plugin runs commands in a sandbox so only the answer reaches Claude, indexes large content for search, and restores relevant memory after compaction.
1:16Headroom: compress what the model reads
How Headroom, an open-source context-compression layer, shrinks tool output, logs and code before they reach the model, with content-aware compressors and reversible caching.
Backend runtimes
1:09Why Go?
Why Go exists: single-binary deploys, goroutines scheduled onto a few threads, and channels.
1:16Why Java?
Bytecode and the JVM, the JIT compiler, garbage collection, and why Java suits large systems.
1:12Why Node.js?
Why a single thread with an event loop suits I/O-heavy servers, and where it breaks down.
Why Scrum
1:12Why do we need Scrum?
The problems with plan-everything-first delivery: late feedback, changing requirements and rising cost of change, and how many small bets fix them.
1:17Why Scrum is empirical
Why complex work needs steering by evidence, and how transparency, inspection and adaptation depend on each other.
1:04Why short sprints?
Why timeboxes create fast feedback, smaller risk and protected focus.
1:27Why Scrum roles and events exist
The problem each Scrum accountability and event solves.
1:51Scrum vs Kanban
What the two share, and how they differ in cadence, limits, change, roles and metrics, plus when to choose each.



