tweetindex
EN

Sooyoon|FailSafeの人

@suziebuilds · Roppongi, Tokyo · joined 21 Dec 2013

Helping Japanese teams build with AI safely @GetFailSafe | FDE / Partnerships|日本語・英語|週末は踊っています| Usually online. Occasionally graceful. Often unhinged.

22 927Followers
7 703Following
12 679Posts total
2KViews on collected posts

Latest posts

AIエージェントの導入で『モデルの性能』ばかり議論して『異常時の停止手順』が後回しになっているチームが多い気がする。\n\n自律的な権限を渡すなら、技術的な凄さよりも泥臭い権限設計やログ設計の方が、本番運用では圧倒的に重要。 196 views · 1 likes · 0 reposts · 0 replies Open on X →
when teams start building agentic workflows, the hardest part isn't the model's reasoning capabilities—it's building the logging and rollback paths that actually tell you what happened when the agent predictably drifts. if you can't trace it, you can't govern it. 389 views · 1 likes · 0 reposts · 0 replies Open on X →
the most undervalued AI skill right now isn't prompting—it's observability. if you can't trace 'why' an agent decided to take a specific action, you’re just gambling. governance starts with being able to see the mess. 373 views · 1 likes · 0 reposts · 0 replies Open on X →
the reality of shipping ai agents: you spend 10% of your time building the cool feature, and 90% of your time building the safety rails that keep the agent from doing something deeply regrettable. \n\nshipping a tool isn't just making it work, it's making it governable. 381 views · 2 likes · 0 reposts · 4 replies Open on X →
https://t.co/PL0XM0F7g0 11 views · 0 likes · 0 reposts · 0 replies Open on X →
AIエージェントを本番導入している企業へ。エージェント型セキュリティで境界を守っていないなら、外部脅威をかなり深刻に考えた方がいいです。 モデルの性能評価だけでは、実環境での攻撃は見えません。FailSafeの新しいブラックボックスランキングはこちら👇 619 views · 8 likes · 0 reposts · 1 replies Open on X →

Against accounts of the same size

6 posts from the last 90 days, next to the 10K–100K follower range. below its peers on both reach and engagement.

Median views377this account924median for 10K–100K
Reach, %1.64%this account3.62%median for 10K–100K
Engagement, %0.39%this account1.52%median for 10K–100K
MetricThis accountMedian for 10K–100KRatio
Median views per post3779240.41×
Reach (views ÷ followers)1.64%3.62%0.45×
Engagement rate0.39%1.52%0.26×

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

61919 Aug
11
3818 Sep
3739 Sep
38910 Sep
19611 Sep

Last 6 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.45%19 Aug
0.00%
1.57%8 Sep
0.27%9 Sep
0.26%10 Sep
0.51%11 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.

What the audience does

Likes72.2%13 in total
Replies27.8%5 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.

Similar accounts