Kaslin Fields @kaslinfields

GKE & OSS K8s Dev Advocate at Google, co-host of @KubernetesPod, CNCF Ambassador, tech comic creator. She/Her. https://t.co/EvEW0wbHVQ kaslin.rocks Bellevue, WA Joined April 2014

Tweets

14K
Followers

6K
Following

2K
Likes

45K

Nnenna 👩🏽‍💻✨ @nnennahacks

16 hours ago

After going on a global AI conference tour from Tokyo to Amsterdam, speaking about agent harnesses and using Claude Code as my primary example: Anthropic: ew. You are an ambassador with that *other* AI platform. Your ambassadorship role here has been terminated, effective immediately. Me: also just used MY connections with an Executive Fellow at Harvard to secure Harvard Business School as the venue for the newest Claude Boston meetup… and was up at 4am with Claude ambassadors planning extensively (who are fantastic ppl btw). Anthropic: leave and never come back. I was already proud to be an ambassador for both Agentic AI Foundation and Codex. But this unique encounter made it all the more clear to me the difference between genuine community for the people and arrogant marketing levers disguised as community. I will continue leaning heavily into AAIF and Codex, which is where I’m treated well and where I’m wanted.

Nnenna 👩🏽‍💻✨ @nnennahacks

2 days ago

I did it. I gave my talk at AGNTCon + MCPCon Europe on governed agent autonomy patterns. The demo gods weren’t on my side, but the audience was! Thank you, Amsterdam. And thank you @AgenticAIFdn 🙏🏽

5 1 56 11K 0

9 9 101 10K 26

View Details

Sarah Drasner @sarah_edo

16 hours ago

"why do you still draw if AI can do it for you?" "why would you still assemble a PC" because some things I do for fun, creative outlets, and flow state I use AI to make my life easier, not to replace the joy

18 29 314 10K 17

View Details

David East @_davideast

3 days ago

😳 wow... I can't believe what I'm seeing. Firebase has spending caps. Like honest to god limits, not warnings. It's not for every service but wow what a start.

12 11 99 11K 10

View Details

Drew Bradstock @dbradstock

2 days ago

Great to see Google Cloud's continued movement into being a leader and the recognition from @Gartner_inc

Google Cloud @googlecloud

2 days ago

For the ninth consecutive year, @Gartner_inc has named Google a Leader in the Gartner Magic Quadrant™ for Strategic Cloud Platform Services, positioned furthest for Completeness of Vision. Read more and download the complimentary report → goo.gle/4y1JsLV

4 12 66 12K 8

0 1 1 251 0

View Details

Karl Weinmeister @kweinmeister

2 days ago

When you fix a bug, AI agents usually add a test in the final step. The problem is, the generated test often doesn't replicate the original bug. I use TDD, or test-driven development, to ensure that I'm not just adding code coverage. My next problem is: when agents do TDD, they tend to add a specific, brittle test for that issue. Over time, my test files become a disorganized and duplicative mess. So, lately I've been adding something like this to my prompt: "Use TDD, and don't just bolt on a new test. Where helpful, refactor the test suite as you go. Consider the structure, DRY principles, and whether this should be a parameterized test case." This should be in my AGENTS.md file, but I'm still fine-tuning the approach. What are your tips on writing tests with AI agents?

2 1 6 424 2

View Details

Kaslin Fields @kaslinfields

3 days ago

@moficodes It's agents all the way down

0 0 0 56 0

View Details

Kaslin Fields @kaslinfields

3 days ago

The GKE engineering team has designed a multi-agent system for managing Kubernetes clusters and released it on GitHub. If you're interested in how agents might help with cluster management, you can check it out yourself! github.com/gke-labs/kube-…

2 3 45 3K 30

View Details

Kaslin Fields @kaslinfields

4 days ago

An interesting trend I'm seeing both at my job and in Open Source is that the higher velocity of technical work is hitting sharp edges/friction points of bureaucracy or guardrails (sometimes missing guardrails) more frequently, exacerbating existing process problems.

0 0 1 229 0

View Details

Angie Jones @techgirl1908

a week ago

My course on Agent Skills is being distributed through Johns Hopkins University, Merrimack College, Kean University, and Calvin University. So good to see the next generation of software engineers picking up these newer skills (no pun intended lol)

5 20 178 9K 43

View Details

Richard Seroter @rseroter

6 days ago

I think @mipsytipsy (and @GergelyOrosz) have it right. If you're using AI in personal interactions (emails, perf reviews) you're being lazy. Offensive, if we're being honest. For more functional work (code, some artifacts)? Ok, go for it. charity.wtf/p/confessions-…

1 5 48 4K 36

View Details

Kaslin Fields @kaslinfields

6 days ago

These days, we write code via AI - whether that's app code or #Kubernetes resource definitions. AI also presents a really compelling opportunity to debug & resolve infra issues fast by minimizing context switching. Try it out in this tutorial by @olivi_eh! g.dev/events/ai-tool…

0 0 4 248 1

View Details

Shubham Saboo @Saboo_Shubham_

a week ago

Google engineers dropped security review skills for AI coding agents. It can find, reproduce and patch vulnerabilities autonomously. 100% Opensource.

25 62 439 33K 699

View Details

Sarah Drasner @sarah_edo

a week ago

🔥 It was an absolute pleasure to talk about WebMCP among other AI on the web topics with @domfarolino on the latest @syntaxfm! Along with the rest of the internet, @wesbos and @stolinski are heroes of mine. Thank you for hosting us! youtube.com/watch?v=xtVvkR…

13 21 155 25K 72

View Details

Chris Aniszczyk @cra

2 weeks ago

👀

Akihiro Suda (@[email protected]) @_AkihiroSuda_

2 weeks ago

Rootless Kubernetes is now in beta. Try it with kind, minc (MiniShift), minikube, k3s, or Usernetes github.com/rootless-conta…

0 18 64 6K 10

0 1 10 1K 2

View Details

Kaslin Fields @kaslinfields

2 weeks ago

@rakyll Best wishes for a smooth treatment and recovery, @rakyll!

0 0 1 69 0

View Details

Franziska Hinkelmann, PhD @fhinkel

3 weeks ago

Oh hello new friend! #gemini

7 4 54 3K 1

View Details

Sundar Pichai @sundarpichai

3 weeks ago

Today we’re introducing a new 3.8 Flash model, our 3rd Flash release in just 6 wks. It delivers significant leaps from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. On DeepSWE v1.1, it outperforms most larger frontier models in autonomously solving complex engineering problems end to end, at a fraction of the cost. More details here: blog.google/innovation-and…

549 779 9K 560K 649

View Details

Kaslin Fields @kaslinfields

3 weeks ago

@tdesseyn Very true. I think livetweeting has made me better at quick summarization.

1 0 1 45 0

View Details

Angie Jones @techgirl1908

3 weeks ago

ok I'm getting annoyed by the anti-skill rhetoric. skills are for REPEATABLE workflows that the model would not inherently know how to do consistently. why on earth would i want to burn time and tokens having agents figure the same thing out over and over when I could simply provide it in a skill?! skills are not for "do X". they are for "do X the way my team needs it done and here's some context so you don't have to go looking through a bunch of stuff to put the puzzle pieces together yet again". im afraid you all have lost the plot

Ryan Lopopolo @_lopopolo

3 weeks ago

@heatdeathdrone I do not aspire to need to invoke things for the agents. If I have to do this, I have failed to empower them to figure it out on their own.