Learning Library

← Back to Library

AI Engineer

4 videos from this channel • View on YouTube ↗

Elevating Agentic Systems with Claude

  • Caitlyn, leading Anthropic’s “claw” developer platform, introduced the session by thanking Swix and emphasizing the audience’s experience building agents with LLM APIs.
  • The platform’s evolution centers on three pillars for maximizing Claude’s performance: exposing its reasoning capabilities, managing its context window, and providing Claude with a “computer” (tool‑use infrastructure).

The New Software Crisis: AI-Generated Code

  • The speaker admits that developers routinely ship generated code they can’t fully explain, a habit that’s become common across the industry.
  • He traces this “software crisis” back to recurring historical cycles—each leap in hardware or methodology (C, personal PCs, OOP, agile) expands demand faster than programmers can manage.

Memory-Centric AI Agent Architecture

  • The speaker promises to deliver high‑level, practical insights over the next 10‑15 minutes that will help listeners build believable, capable, and reliable AI agents within the next six months.
  • They emphasize shifting from current stateless LLM applications to stateful ones by embedding persistent memory, which reduces prompt engineering and enables agents to form lasting relationships with users.

Lab Session Updates and GitHub Copilot

  • The session room is full, but the exact same lab will be offered again at 3:30 PM in a different room for anyone who missed it.
  • Attendees must accept the invitation to the GitHub organization sent to their email to gain access to GitHub Copilot before the lab begins.