Found 1 bookmarks
Custom sorting
๐Ÿšจ OpenAI ๐—ท๐˜‚๐˜€๐˜ ๐—ฎ๐—ป๐—ป๐—ผ๐˜‚๐—ป๐—ฐ๐—ฒ๐—ฑ ๐˜๐—ต๐—ฒ๐—ถ๐—ฟ ๐—ผ๐˜„๐—ป ๐—”๐—ด๐—ฒ๐—ป๐˜ ๐—•๐˜‚๐—ถ๐—น๐—ฑ๐—ฒ๐—ฟ.
๐Ÿšจ OpenAI ๐—ท๐˜‚๐˜€๐˜ ๐—ฎ๐—ป๐—ป๐—ผ๐˜‚๐—ป๐—ฐ๐—ฒ๐—ฑ ๐˜๐—ต๐—ฒ๐—ถ๐—ฟ ๐—ผ๐˜„๐—ป ๐—”๐—ด๐—ฒ๐—ป๐˜ ๐—•๐˜‚๐—ถ๐—น๐—ฑ๐—ฒ๐—ฟ.
๐Ÿšจ OpenAI ๐—ท๐˜‚๐˜€๐˜ ๐—ฎ๐—ป๐—ป๐—ผ๐˜‚๐—ป๐—ฐ๐—ฒ๐—ฑ ๐˜๐—ต๐—ฒ๐—ถ๐—ฟ ๐—ผ๐˜„๐—ป ๐—”๐—ด๐—ฒ๐—ป๐˜ ๐—•๐˜‚๐—ถ๐—น๐—ฑ๐—ฒ๐—ฟ. [And no โ€” it didnโ€™t kill 99% of startups overnight.] Itโ€™s calledย AgentKitย โ€” aย no-code, full-stack platformย to build, deploy, and optimize AI agents. The UI looks surprisingly clean, but letโ€™s be clear: this doesnโ€™t instantly replaceย Zapier, Make, n8n, or Lindy. AgentKit is impressive, yes โ€” but itโ€™s still early, still developer-focused, and far from being a plug-and-play automation killer. ๐—›๐—ฒ๐—ฟ๐—ฒโ€™๐˜€ ๐˜„๐—ต๐—ฎ๐˜ ๐—”๐—ด๐—ฒ๐—ป๐˜๐—ž๐—ถ๐˜ ๐—ถ๐—ป๐—ฐ๐—น๐˜‚๐—ฑ๐—ฒ๐˜€: โฌ‡๏ธ 1. Agent Builderย โ€“ a visual interface to design and connect multiple AI agents โ†’ You can drag and drop steps, test them instantly, and track versions โ†’ Comes with built-in safety checks (guardrails) โ†’ Itโ€™s in beta โ€” I havenโ€™t tested it yet, but the interface looks quite polished 2.ย Connector Registryย โ€“ a control center for all your data connections โ†’ Possible to manage integrations with MCP โ†’ Adds content and tools to keep it organized, secure, and compliant for enterprise use 3. ChatKitย โ€“ provides an interface to add chat to your product โ†’ Turns agents into a chat interface that looks native โ†’ Handles threads, live responses, and context automatically 4.ย Evals 2.0ย โ€“ a system to test and improve your agents โ†’ Lets you run evaluations using datasets and automated grading โ†’ According to OpenAI companies which used it saw up to 30% higher accuracy after using it None of the announced capabilities are truly new, and I doubt that building agents with OpenAI will offer a better experience than platforms like n8n or Zapier. The output still generates code, and the whole setup clearly targets developers (for now) โ€” which explains why it was introduced atย DevDayย rather than rolled out to the broader user base. And for enterprise-ready AI agents, you still needย solid frameworksย likeย LangChainย orย CrewAI, not another drag-and-drop automation layer. AgentKit is a strong step, but thereโ€™s still a way to go before it becomes a production-grade enterprise solution and kills "99% of all other tools". ๐—ฃ.๐—ฆ. ๐—œ ๐—ฟ๐—ฒ๐—ฐ๐—ฒ๐—ป๐˜๐—น๐˜† ๐—น๐—ฎ๐˜‚๐—ป๐—ฐ๐—ต๐—ฒ๐—ฑ ๐—ฎ ๐—ป๐—ฒ๐˜„๐˜€๐—น๐—ฒ๐˜๐˜๐—ฒ๐—ฟย ย โ€” ๐˜„๐—ต๐—ฒ๐—ฟ๐—ฒ ๐—œ ๐˜€๐—ต๐—ฎ๐—ฟ๐—ฒ ๐˜๐—ต๐—ฒ ๐—ฏ๐—ฒ๐˜€๐˜ ๐˜„๐—ฒ๐—ฒ๐—ธ๐—น๐˜† ๐—ฑ๐—ฟ๐—ผ๐—ฝ๐˜€ ๐—ผ๐—ป ๐—”๐—œ ๐—ฎ๐—ด๐—ฒ๐—ป๐˜๐˜€, ๐—ฒ๐—บ๐—ฒ๐—ฟ๐—ด๐—ถ๐—ป๐—ด ๐˜„๐—ผ๐—ฟ๐—ธ๐—ณ๐—น๐—ผ๐˜„๐˜€, ๐—ฎ๐—ป๐—ฑ ๐—ต๐—ผ๐˜„ ๐˜๐—ผ ๐˜€๐˜๐—ฎ๐˜† ๐—ฎ๐—ต๐—ฒ๐—ฎ๐—ฑ ๐˜„๐—ต๐—ถ๐—น๐—ฒ ๐—ผ๐˜๐—ต๐—ฒ๐—ฟ๐˜€ ๐˜„๐—ฎ๐˜๐—ฐ๐—ต ๐—ณ๐—ฟ๐—ผ๐—บ ๐˜๐—ต๐—ฒ ๐˜€๐—ถ๐—ฑ๐—ฒ๐—น๐—ถ๐—ป๐—ฒ๐˜€. ๐—œ๐˜โ€™๐˜€ ๐—ณ๐—ฟ๐—ฒ๐—ฒ โ€” ๐—ฎ๐—ป๐—ฑ ๐—ฎ๐—น๐—ฟ๐—ฒ๐—ฎ๐—ฑ๐˜† ๐—ฟ๐—ฒ๐—ฎ๐—ฑ ๐—ฏ๐˜† ๐Ÿฎ๐Ÿฌ,๐Ÿฌ๐Ÿฌ๐Ÿฌ+ ๐—ฝ๐—ฒ๐—ผ๐—ฝ๐—น๐—ฒ. https://lnkd.in/dbf74Y9E
ยทlinkedin.comยท
๐Ÿšจ OpenAI ๐—ท๐˜‚๐˜€๐˜ ๐—ฎ๐—ป๐—ป๐—ผ๐˜‚๐—ป๐—ฐ๐—ฒ๐—ฑ ๐˜๐—ต๐—ฒ๐—ถ๐—ฟ ๐—ผ๐˜„๐—ป ๐—”๐—ด๐—ฒ๐—ป๐˜ ๐—•๐˜‚๐—ถ๐—น๐—ฑ๐—ฒ๐—ฟ.