←
Google Cloud Tech26,571 posts
Google Cloud Tech avatar✓

Google Cloud Tech ✓

@GoogleCloudTech

Follow along for how-tos, demos, product news, and more. For company updates, check out @GoogleCloud.

◷ Joined August 2008▧ 8,332 Photos and videos
Google Cloud Tech avatar
Google Cloud Tech@GoogleCloudTech·11h

Best practices for GKE—all in one place. This document provides a consolidated overview of best practices for designing, building, and operating apps on GKE. Follow these recommendations to optimize for cost, performance, security, and reliability → goo.gle/4j0JtJR

Post attachment
Google Cloud Tech avatar
Google Cloud Tech@GoogleCloudTech·16h

Apigee Hybrid 1.17 now supports MCP! Expose your existing APIs as governed MCP tools across on-premises and multicloud environments without writing or maintaining custom MCP servers → goo.gle/4iPhdti

Post attachment
Abdel SGHIOUAR avatar
⟳ Google Cloud Tech retweeted
Abdel SGHIOUAR@boredabdel·Nov 17

48 hours until Project Masar Season 2 goes live! 🚀 Season 1 brought hundreds of developers across MENA together to deploy serverless apps and foundational agents in Arabic. This Wednesday, November 18 at 7:00 PM KSA (GMT+3) / 6:00 PM Cairo, we are taking the next step moving from single agents to Multi-Agent Systems with the Agent Development Kit (ADK). Here is what we are building live over the next 5 episodes: 🔹 Ep 1: Empowering AI Agents with Tools 🔹 Ep 2: Stateful & Personalized Agents (Memory) 🔹 Ep 3: Interoperability with MCP & A2A 🔹 Ep 4: Multi-Agent Apps with MCP Toolbox 🔹 Ep 5: Multi-Agent Workflow Patterns 100% Arabic, 100% hands-on live coding, zero slides. RSVP now: 👉 g.dev/cloud/masar #MasarByGoogle #GoogleCloud #ADK #MultiAgent #DevRel #MENA

Post attachment
Google Cloud Tech avatar
Google Cloud Tech@GoogleCloudTech·Nov 16

5. Encode operational habits, not documentation dumps Re-evaluate your skills every time you upgrade the underlying AI model. If a new model performs just as well without the skill, delete the skill to keep code clean.

Google Cloud Tech avatar
Google Cloud Tech@GoogleCloudTech·Nov 16

4. Separate efficiency and security from correctness so agents can't reward-hack Don’t let agents game the system. Isolate your grading environment and keep your evaluation metrics separate to avoid reward hacking.

Google Cloud Tech avatar
Google Cloud Tech@GoogleCloudTech·Nov 16

3. Measure paired WITH vs. W/OUT ablation, not vibes When a test case shows the same success rate with no efficiency gains, stop optimizing. Your custom skill isn’t speeding up the run. It's just adding context bloat. Delete it.

Google Cloud Tech avatar
Google Cloud Tech@GoogleCloudTech·Nov 16

2. Never trust an eval that runs on a developer laptop Running skill benchmarks directly on your workstation? Your numbers are lying to you. Slower file scans and subprocess timeouts can cause the agent to abandon search paths prematurely.

Google Cloud Tech avatar
Google Cloud Tech@GoogleCloudTech·Nov 16

1. Gate trigger collisions and security risks before spinning up containers No eval benchmark improvement after adding a plugin? Before rewriting SKILL.md instructions, check if the agent actually loaded the skill.

Google Cloud Tech avatar
Google Cloud Tech@GoogleCloudTech·Nov 16

Testing agent skills files? Don’t just paste a prompt, watch it pass once on a laptop, and merge to main. Here are five rules for evaluating skills before they bloat your context window ↓

Google Cloud Tech avatar
Google Cloud Tech@GoogleCloudTech·Nov 16

How to build an AI harness around your coding agent in four steps: 1. Context and memory (sessions, state) 2. Tools and workflows (MCP, ADK) 3. Sandboxes and prompt injection defense 4. Evals (code, LLM judge, human) Watch the crash course → goo.gle/3XtB36o

0:29
Google Cloud Tech avatar
Google Cloud Tech@GoogleCloudTech·Nov 15

Knowledge Catalog, Google Cloud's universal context engine, turns knowledge into shared business context so agents answer and act with higher accuracy and trust ↓

1:16