The Deep Dives10 Jun 2025

Real GenAI Support for Platform, SRE & Security with ADK

Is your Platform, SRE, or Security team feeling the pressure to innovate while keeping systems reliable and secure? Generative AI is offering more than just buzz – it’s providing concrete tools to revolutionize how we handle complex operational challenges.

In this episode, we take a deep dive into Google's Agent Development Kit (ADK), a powerful open-source, code-first toolkit that lets you build, evaluate, and deploy sophisticated AI agents. Forget generic chatbots; we're talking about creating specialized "digital team members" tailored to your specific internal systems and needs.

Join us as we explore:

What makes ADK a game-changer for technical teams demanding control and flexibility.
The core concepts of building an agent, emphasizing how crucial well-defined tools and precise instructions are for an agent's success.
Inspiring real-world applications: from AI assistants that accelerate bug diagnosis and streamline on-call duties to agents that audit LLM outputs for compliance and security.
A look at advanced capabilities like multi-agent systems, A2A/MCP for true interoperability, and the importance of robust evaluation.
Essential best practices for developing effective, reliable, and secure GenAI agents, plus common pitfalls (like over-complexity and the "black box" amplification risk) to avoid.

This episode is packed with insights for Engineering Managers, SREs, DevOps engineers, and C-Level executives looking to practically apply GenAI to empower their teams and transform their operations. Tune in to learn how you can start building your own GenAI support structure.

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(18)

The Most Important SRE Metrics & How to Track Them

Are you constantly caught between your team's desire to ship new features and the C-suite's demand for unwavering stability? In this episode, we demystify Site Reliability Engineering (SRE) metrics an...

1 Okt 20256min

The Velocity Paradox: Turning Tech Debt into Your Innovation Engine

Is your team constantly firefighting instead of innovating? The culprit is likely technical debt, a silent drag on productivity that costs the industry over $85 billion a year. But what if we've been ...

29 Sep 20256min

Why Your Next Business Strategy Should Be Site Reliability Engineering (SRE)

Is your company treating system reliability like a technical chore for the IT department? You could be overlooking a $400 billion blind spot. In today's digital economy, uptime isn't just about "keepi...

8 Sep 20256min

Titans of Reliability: Lessons from Google, Netflix, and Meta

In the relentless pursuit of uptime, who do you turn to for inspiration? The titans of tech who operate at a planetary scale. While Google pioneered Site Reliability Engineering (SRE), Netflix mastere...

30 Jul 20256min

Startup SRE: Building Reliability from Day One

In the chaotic world of startups, the pressure to ship features often pushes reliability to the back burner, a debt to be paid "later." But what if this approach is fundamentally flawed? In this episo...

28 Jul 20258min

SRE for Web3 and Quantum Computing

The rulebook for Site Reliability Engineering is being rewritten. For years, we've focused on the stability of centralized systems, but two technological revolutions are forcing a paradigm shift. In t...

15 Jul 20257min

AI in the War Room - Beyond the AIOps Hype

Is AIOps the silver bullet for incident management, or is it just a marketing buzzword burning through your budget? As engineering managers for Platform, SRE, and Security teams, we're promised a futu...

11 Jul 20256min

The Engineer's Operating System: Installing Psychological Safety

In this episode, we're moving past the buzzwords and getting into the code of team culture. While we invest heavily in technical systems, we often neglect the human operating system they run on. The s...

26 Jun 20256min