Google Cloud Tech ✓

@GoogleCloudTech · joined 11 Aug 2008

Follow along for how-tos, demos, product news, and more. For company updates, check out @GoogleCloud. Watch #GoogleCloudNext on demand ⬇️

1 313 574Followers

1 597Following

26 401Posts total

189.1KViews on collected posts

Latest posts

Google Cloud Tech ✓@GoogleCloudTech5h

@GoogleCloudTech plugins for coding agents now huh 1 views · 0 likes · 0 reposts · 0 replies Open on X →

Google Cloud Tech ✓@GoogleCloudTech10 Sep

@GoogleCloudTech Plugins make sense when they remove setup work. The real test is whether the first install feels boring. 56 views · 0 likes · 0 reposts · 0 replies Open on X →

Google Cloud Tech ✓@GoogleCloudTech10 Sep

Introducing Google Cloud plugins for AI coding agents. Designed as installable bundles, agent plugins equip the AI agent of your choice with skills and tools to be more effective on Google Cloud. Learn more and start building → https://t.co/xndsKuzsuq https://t.co/YecRL2875k

35.2K views · 276 likes · 39 reposts · 11 replies Open on X →

Google Cloud Tech ✓@GoogleCloudTech10 Sep

https://t.co/S75IujZbgi 28.2K views · 201 likes · 33 reposts · 8 replies Open on X →

Google Cloud Tech ✓@GoogleCloudTech9 Sep

On this week’s livestream you’ll learn how Gemini Enterprise provides a single front door to company data, securely connecting SaaS apps to deploy grounded AI agents. https://t.co/wOaYKMRcgU 14.2K views · 69 likes · 9 reposts · 3 replies Open on X →

Google Cloud Tech ✓@GoogleCloudTech9 Sep

https://t.co/Oe5CiXdzvq 24.1K views · 129 likes · 23 reposts · 19 replies Open on X →

Google Cloud Tech ✓@GoogleCloudTech9 Sep

@GoogleCloudTech the missing fifth pattern is idempotency across side effects. once agents react in parallel, every write needs a dedupe key and a durable receipt. otherwise you've built a very fast machine for sending the same email twice. 1.1K views · 6 likes · 0 reposts · 2 replies Open on X →

Google Cloud Tech ✓@GoogleCloudTech9 Sep

Find the code path that runs after your fallback fires. If it skips a validation step, you're shipping two different products, while only testing one. 3.6K views · 7 likes · 0 reposts · 0 replies Open on X →

Google Cloud Tech ✓@GoogleCloudTech9 Sep

Pattern 4: Tiered routing before the expensive call Look at your own traffic distribution before assuming you need a bigger model. A cheaper first pass usually gets you further. 3.2K views · 15 likes · 0 reposts · 1 replies Open on X →

Google Cloud Tech ✓@GoogleCloudTech9 Sep

Read the full article ⬇️ https://t.co/Jr4pWXwmMO 4.5K views · 31 likes · 7 reposts · 3 replies Open on X →

Google Cloud Tech ✓@GoogleCloudTech9 Sep

Pattern 2: Let agents react to the same event in parallel Check whether two of your agents will need to react to the same signal. If your architecture makes one wait behind the other to do it, that's a single-threaded system wearing a multi-agent label. 4.2K views · 22 likes · 0 reposts · 1 replies Open on X →

Google Cloud Tech ✓@GoogleCloudTech9 Sep

Pattern 3: A fallback model still has to clear your bar Find the code path that runs after your fallback fires. If it skips a validation step, you're shipping two different products, while only testing one. 3.6K views · 14 likes · 0 reposts · 1 replies Open on X →

Google Cloud Tech ✓@GoogleCloudTech9 Sep

Pattern 1: The tools you built for yourself can serve other agents too If your agent talks to its own data over MCP internally, check how much extra work it'd take to expose those same tools externally. Do this before you build a second, human-only API that does the same job. 4.4K views · 31 likes · 4 reposts · 1 replies Open on X →

Google Cloud Tech ✓@GoogleCloudTech9 Sep

We just wrapped the Google for Startups AI Agents Challenge. Here are 4 production-grade patterns that you should steal for your next build ⬇️ 62.9K views · 540 likes · 47 reposts · 12 replies Open on X →

Against accounts of the same size

14 posts from the last 90 days, next to the 1M–10M follower range. below its peers on both reach and engagement.

Median views4 303this account14 569median for 1M–10M

Reach, %0.33%this account0.68%median for 1M–10M

Engagement, %0.64%this account0.92%median for 1M–10M

Metric	This account	Median for 1M–10M	Ratio
Median views per post	4 303	14 569	0.30×
Reach (views ÷ followers)	0.33%	0.68%	0.48×
Engagement rate	0.64%	0.92%	0.70×

Others in this range → Compare with another account → How these benchmarks are built →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

62.9K9 Sep

4.4K

3.6K

4.2K

4.5K

3.2K

3.6K

1.1K

24.1K

14.2K

28.2K10 Sep

35.2K

112 Sep

Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.95%9 Sep

0.82%

0.42%

0.55%

0.92%

0.50%

0.20%

0.74%

0.71%

0.57%

0.86%10 Sep

0.93%

0.00%

0.00%12 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 1M–10M accounts is 0.92%.

What the audience does

Likes46.2%1 341 in total

Reposts5.6%162 in total

Replies2.1%62 in total

Bookmarks46.1%1 337 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Latest posts

Against accounts of the same size

Growth & engagement

Views per post

Engagement rate per post

What the audience does

Similar accounts