Arya Agrahari

[Arya Agrahari @A_rya_7113]

@SwatejReddy @akash_mishra_x exactly

[Arya Agrahari @A_rya_7113]

My boyfriend always has a logical answer for everything 😭🤦‍♀️ I just couldn’t take it anymore, so I had to build something that gives me the emotional responses I actually deserve 🥹💅❤️
Try it out: https://t.co/sk3RMbW0PX
Github: https://t.co/So3lib5m7t

[Arya Agrahari @A_rya_7113]

@akash_mishra_x you should use this as your personal guide by the way

[Arya Agrahari @A_rya_7113]

@nitesh_singh5 interested

[Arya Agrahari @A_rya_7113]

@monami_ai01 drive

[Priyanka Vergadia @pvergadia]

🚂 All Aboard the 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗔𝗚 Express!

AI Agent-based retrieval systems are the backbone of modern enterprise AI. But an agent is only as powerful as the infrastructure supporting it.

We mapped out the perfect "Journey" to building a robust Agentic RAG ecosystem. Think of it as a train line where every station adds a critical layer of intelligence to your application.

Here is your CloudGirl Guide to the 9 Stations of the Stack:

1️⃣ 𝗦𝘁𝗮𝘁𝗶𝗼𝗻 𝟭: 𝗗𝗲𝗽𝗹𝗼𝘆𝗺𝗲𝗻𝘁 (𝗟𝗲𝘃𝗲𝗹 𝟬)
The foundation. Where agents live and scale.
🛠️ Tech: Groq, AWS, Google Cloud, https://t.co/GXPjdlukRI

2️⃣ 𝗦𝘁𝗮𝘁𝗶𝗼𝗻 𝟮: 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻
If you can't measure it, you can't improve it. Continuous scoring of retrieved data.
🛠️ Tech: LangSmith, Phoenix, DeepEval, Ragas

3️⃣ 𝗦𝘁𝗮𝘁𝗶𝗼𝗻 𝟯: 𝗟𝗟𝗠𝘀
The "Thinking Core." Reasoning, planning, and decision-making.
🛠️ Tech: Llama 3, Claude 3.5, Gemini, GPT-4o

4️⃣ 𝗦𝘁𝗮𝘁𝗶𝗼𝗻 𝟰: 𝗙𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸𝘀
The orchestration layer managing tool usage and routing.
🛠️ Tech: LangChain, Haystack, DSPy

5️⃣ 𝗦𝘁𝗮𝘁𝗶𝗼𝗻 𝟱: 𝗩𝗲𝗰𝘁𝗼𝗿 𝗗𝗮𝘁𝗮𝗯𝗮𝘀𝗲𝘀
The retrieval engine for similarity search.
🛠️ Tech: Pinecone, Chroma, Milvus

6️⃣ 𝗦𝘁𝗮𝘁𝗶𝗼𝗻 𝟲: 𝗘𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴 𝗠𝗼𝗱𝗲𝗹𝘀
Grounding concepts by converting text to dense representations.
🛠️ Tech: Nomic, Ollama, Voyage AI, OpenAI

7️⃣ 𝗦𝘁𝗮𝘁𝗶𝗼𝗻 𝟳: 𝗗𝗮𝘁𝗮 𝗘𝘅𝘁𝗿𝗮𝗰𝘁𝗶𝗼𝗻
Pulling structured data from the wild (Web/PDFs).
🛠️ Tech: Firecrawl, Scrapy, Docling, LlamaParse

8️⃣ 𝗦𝘁𝗮𝘁𝗶𝗼𝗻 𝟴: 𝗠𝗲𝗺𝗼𝗿𝘆
Giving agents persistence across sessions.
🛠️ Tech: Zep, Mem0, Cognee, Letta

9️⃣ 𝗦𝘁𝗮𝘁𝗶𝗼𝗻 𝟵: 𝗔𝗹𝗶𝗴𝗻𝗺𝗲𝗻𝘁 & 𝗢𝗯𝘀𝗲𝗿𝘃𝗮𝗯𝗶𝗹𝗶𝘁𝘆
Ensuring safety, tracking costs, and monitoring behavior.
🛠️ Tech: Guardrails AI, Arize, Helicone, Langfuse

Building an Agentic system isn't just about the LLM—it's about the ecosystem. Which station are you currently building at?

#AgenticRAG #AI #MachineLearning #TechStack #CloudComputing #DevOps #LLMs

[Arya Agrahari @A_rya_7113]

@AvinashSingh_20 Ai

[Abhishek Nair @thatGTMdude]

2020:
> Remote role
> $300k salary (negotiable, bro just work for us)
> Requirements: IQ more than a chimpanzee

2025:
> In office
> No salary, first month is a free trial
> Requirements: knowledge of every technology ever created. + Video editing + 100k followers + must look handsome/pretty
> Bring your own laptop, chair and coffee mug

[Arya Agrahari @A_rya_7113]

Learning about AgentSDK which was recently cooked by @OpenAI was one of the best parts of #GenAi with @ChaiCodeHQ.
@piyushgarg_dev explained it and gave a walkthrough of what went wrong for LangGraph and what went right for AgentSDK. Building agents were never this easy.🙇🏼‍♀️

[Arya Agrahari @A_rya_7113]

I won't stop posting about the content I learnt in this journey anyways. So let's deep dive in the world of GenAi with me. Let's go 🚀😁

[Arya Agrahari @A_rya_7113]

Been a little inconsistent on X but not with #GenAi with @ChaiCodeHQ
Joined the cohort late but completed my backlogs. Completed each lecture live and what an experience it was.
@piyushgarg_dev and @Hiteshdotcom sir you guys made this journey so interesting, forever grateful.🙇🏼‍♀️

[Arya Agrahari @A_rya_7113]

Been a little inconsistent on X but not with #GenAi with @ChaiCodeHQ
Joined the cohort late but completed my backlogs. Completed each lecture live and what an experience it was.
@piyushgarg_dev and @Hiteshdotcom sir you guys made this journey so interesting, forever grateful.🙇🏼‍♀️

[Arya Agrahari @A_rya_7113]

@sayanreply @ChaiCodeHQ @piyushgarg_dev @Hiteshdotcom Yeah sure

[Arya Agrahari @A_rya_7113]

3 weeks into #GenAi with @ChaiCodeHQ Didn't even realise we came this far, big shoutout to our mentors @piyushgarg_dev @Hiteshdotcom.
This will surely be an incredible journey.🤞🏼
Looking forward to making the most out of this cohort, surely it is one of the best.

[Sam ☕ @samirande_]

Top 3 reasons to delete Instagram :

[Arya Agrahari @A_rya_7113]

@NoorAla62921364 It's 9pm to 11pm on Monday, Wednesday and Friday

[Arya Agrahari @A_rya_7113]

Day 1 of #GenAi with @ChaiCode
After a solid foundation of Machine learning. Today I started my journey with Generative Ai from the best once @piyushgarg_dev and @Hiteshdotcom. Day1 was all about learning tokes, the OG Transformer Architecture, LLMs, vector embeddings extraction.

[Hitesh Choudhary @Hiteshdotcom]

What a fun class today. Live ka mza hi alag h. The discussions are priceless. We covered Agent SDK, and somehow showed them custom built judge0 with cloudflare workers and e2b company for AI sandbox.

Love the live sessions.

[Arya Agrahari @A_rya_7113]

Day 2 of #GenAi with @ChaiCodeHQ.
"System Prompting", one of the most powerful ways to guide an LLM's behaviour.
@piyushgarg_dev taught us the art of System Prompting on this cohort and the various types of it. Looking forward to learning more.
@Hiteshdotcom #PromptEngineering

[Arya Agrahari @A_rya_7113]

@Apoorv654123 Yeah sure.🙏🏼

[Arya Agrahari @A_rya_7113]

@RamitRosha10031 JavaScript, you must know how to build a full stack app using js.

[Arya Agrahari @A_rya_7113]

@Apoorv654123 Thankyou, I joined a bit late I hope I'll be able to cope up.