Learn how to deploy M365 Agents to Teams, Copilot, web, email, and SMS. Master channel adapters, Azure Bot Service registration, and write-once-run-everywhere architecture. #m365agents #m365 #agentssdk #m365agentssdk #teamsagents #copilotagents

Agents are talked about everywhere. Agentic is the new 2025 buzzword. OpenAI is going heads on against Anthropic when it comes to…

YouTube video by Applied AI - GenAI, ChatGPT et LLM-powered apps

OpenAI、AIエージェント開発のための新機能を追加 TypeScript版「Agents SDK」や音声エージェント構築向け機能など #AgentsSDK #ITニュース

OpenAI、新API「Responses API」発表 – AIエージェント開発のハードルを下げる新ツール #ResponsesAPI #AgentsSDK #ITニュース

Loving this How to run gpt-oss locally with Ollama and great work adding the section on AgentsSDK Integration with LiteLLM, just in time for my lecture tomorrow. Assuming I can use this in a Google Collab notebook as well for demos

Actually you are on to something and didn’t get you wrong so all good there! I just noticed this : OpenAI compatibility  |  Gemini API  |  Google AI for Developers so my plans change yet again and this calls for a heads down hackathon with my team while we support ongoing customers. Thank you for asking the tough questions. I slightly agree to disagree on the ease of use with responsesAPI, I am a lone developer and cobbled everything together with chatCompletions and hence I don’t want to change it unless I have to! However, a lot of naive software developers - fresh grads/seasoned folks new to AI want to start with something simple to grasp the concepts in detail so it’s a human / talent question - there is a huge gap between folks who started developing since gpt3.5 vs now and that slows down momentum in going to market and getting revenue.

kavitatipnis: > I am unclear on what you mean by proprietary corner ? The Responses API is the proprietary corner. Currently you can switch models easily to other providers using Chat Completions. (don’t get me wrong, I’m a huge OpenAI fan and user, but I’m also keen on good strategy) kavitatipnis: > Proprietary is where the new AI Platforms ( LLM OS concept) is headed I’m not sure I’d agree with you. Yes, OpenAI is trying to see if that’s possible. kavitatipnis: > responsesAPI offers a few capabilities natively which involves less overhead if you are a really tiny startup. Seriously, I’m a single developer and have written two Chatbots with web search and web crawl with just Chat Completions (and loads of complex behaviour in addition). It’s a non-issue. kavitatipnis: > Using any model via LiteLLM - OpenAI Agents SDK I’m actually a contributor to that project (albeit one PR )

For sure it takes longer and Responses API is super convenient

I am unclear on what you mean by proprietary corner ? Also it’s tangential to my original question. Proprietary is where the new AI Platforms ( LLM OS concept) is headed - OpenAI, Google & Anthropic and we can use any model that fits our usecase/s. We are already “proprietary” if we place our bets on OpenAI and frankly the ease of access to developers is unmatched. More specifically, between the API choices, it’s a decision that needs to happen with any software upgrade - responsesAPI offers a few capabilities natively which involves less overhead if you are a really tiny startup. AgentsSDK does support different models : Using any model via LiteLLM - OpenAI Agents SDK However, given where things are at in production for a lot of companies, “upgrading” their LLM stack is complex because of the orchestration - we have OpenAI, Langchain/Langsmith and the interoperability is what I need for getting the best of both vendors.

AgentsSDK with ResponsesAPI is powerful, however, all the current prod implementations that we have are of chatCompletionsAPI and at minimum I want to port the Langchain components over and refactor the RAG Chatbot using AgentsSDK (natively use ResponsesAPI to get state management and streaming natively). This is proving to be a tedious effort with the examples so far being limited to simple use cases. Think of this as a major upgrade that most “static” RAG chatbot type applications will have to pursue if they have to become “agentic” chatbots. For most production applications, there are external vector stores and Langchain helps in orchestrating the basic flow as “runnables” natively. What I am noticing is that doing a complete rewrite is an R&D effort { ~2 months} including evals delaying other priorities for enhancing the product and introducing new products. Looking for pointers on a more comprehensive guide or examples.

I am in the middle of a poc to upgrade our v-1 rag chatbot using chatCompletions API to AgentsSDK with access to tools - vector search etc, however, I am wondering if there are tools to port the existing langchain implementation over that generates citations as well. citations are a huge part of our chatbot and I do not see an easy migration path. Further how do I keep my existing langchain implementation in the AgentsSDK ? Our v1 is live and in prod so the v2 has to have the same functionality at minimum. Appreciate any pointers from folks who are in the middle of an upgrade to the newer AgentsSDK for RAG chatbots.

Should be able to watch the recorded session on-demand: webinar.openai.com ### Build Hour: Agentic Tool Calling Create powerful agents capable of executing long-horizon tasks, leveraging tools while they reason. Highlights include:Chain-of-thought...

Any updates or a preferred design pattern for this invocation ? I am skeptical of adding too many wrapper methods for every tool call.

This appears to be a bug, if I annotate regular methods with the @function_tool and try to debug them outside of the agent logic, I get a FunctionTool object not callable. Removing the annotation works, however, I think this should not be a blocking TypeError as most existing methods should be elevated as function tools. Alternately, I can create a wrapper around existing functions and decorate with @function_tool but that is extraneous code.

【 #ITニュース 】OpenAI、AIエージェント開発のための新機能を追加 TypeScript版「Agents SDK」や音声エージェント構築向け機能など #AgentsSDK #CodeZine

OpenAI has announced the new Responses API, the Agents SDK, and observability tools to address the challenges that creating production-ready agents pose, such as building custom orchestration, and…

YouTube video by AI超元域

Cloudflare launches toolkit to boost AI agent development. #AI #Cloudflare #AgentsSDK