AI ยท Article
AWS Launches Kiro Bots, Dedicated AI Agents for Each Software Development Stage
์บ๋์ค๊ทธ๋ํฝ์ค ยท

At a glance
Amazon Web Services (AWS) has launched Kiro bots, long-running AI agents that each handle one stage of software development inside its Kiro Crew workspace. Developers can assign each bot a role, set its direction, and review its results. The bots run parallel work and ask for help only when a decision is needed.
Key points
- Each bot has its own name, avatar, and one ongoing chat window, and records key decisions and open issues on a shared dashboard.
- Bots can start and monitor parallel sessions, fix off-track work, and gather results into one chat. They can also run scheduled tasks like overnight build failure checks.
- Each bot has separate permissions and memory. A research bot can only read files and search the web, while a deploy bot needs approval for every change.
- AWS shows four example bots: issue intake, build status (checks CI every 30 minutes), code review, and release preparation. Developers can pick a separate AI model for each bot.
Why it matters
This shows how AI agents may take over more of the routine work in software development, while people keep control over key decisions and approvals.
Original source
AWS, ๊ฐ๋ฐ ๋จ๊ณ๋ณ ์ ๋ด AI ์์ด์ ํธ โํค๋ก ๋ดโ ์ถ์
์บ๋์ค๊ทธ๋ํฝ์ค ยท Nov 17, 10:34 KST
Read on ์บ๋์ค๊ทธ๋ํฝ์ค โAI summarized the original article. Check the original for accuracy. Copyright belongs to ์บ๋์ค๊ทธ๋ํฝ์ค.
Other coverage
- ํ๋ํ (Platum) ยท ์ด์ ๋ถ๋ฅยท๋น๋ ์ ๊ฒยท์ฝ๋ ๋ฆฌ๋ทฐ๋ฅผ ๋ด๋ง๋ค ๋ฐ๋กโฆ AWS, ์ญํ ๋๋ ๋งก๋ ๊ฐ๋ฐ ์์ด์ ํธ ์ถ์
- ํ์ด๋ธ์ ๋ด์ค ยท "๋ฒ๊ทธ ์ฐพ๊ณ ์ฝ๋ ๊ฒํ "โฆAWS, ๊ฐ๋ฐ์์ฉ 'ํค๋ก ๋ด' ์ถ์
- Chosunbiz ยท AWS, ๊ฐ๋ฐ ํ๋ก์ธ์ค๋ณ๋ก ์ ๋ฌด ์ ๋ดํ๋ AI ์์ด์ ํธ โํค๋ก ๋ดโ ์ถ์
Amazon Web Services ยท Ranking and more news
More from this field
- PostNord Swaps Its Phone Support AI for ElevenAgents, Lifting Call Resolution to 60%
PostNord, the leading postal and logistics company in the Nordics, replaced its AI phone system in Sweden with a new one built on ElevenLabs' ElevenAgents. The old system was fully shut down in about 90 days, and the share of calls resolved without escalation rose from 45% to 60%.
ElevenLabs blog ยท Nov 17, 21:00 KST - Nvidia Scandal Suggests Trump Administration Put China Race Over US Security
A New York Times opinion piece argues that the Nvidia scandal shows the Trump administration ignored national security while claiming to win the AI race with China. The writer says the administration loosened AI rules, often citing that race. The article text was partly cut off, so the summary covers only the visible part.
The New York Times ยท Nov 17, 10:18 KST - Laon Secure Links Google Device Trust to Its Zero-Trust Security Products
Laon Secure, a Korean AI security and authentication company, announced that it has linked Google's Device Trust to its core authentication and device management products. It also joined Google's Android Enterprise partner program.
๋จธ๋ํฌ๋ฐ์ด ยท Nov 17, 09:02 KST - SlipStream Speeds Up Flash Memory for GPU AI Models Using Smart Prefetching
Researchers from Georgia Tech, NVIDIA Research, and Stanford University published a paper called SlipStream. It is a way to make High-Bandwidth Flash (HBF) work well as memory for GPU systems running large language models. Flash memory can hold much more data than DRAM-based memory, but it responds much more slowly.
Semiconductor Engineering ยท Nov 17, 08:52 KST