Assistant Professor in CSE | 📚📝Hybrid Human-AI | Postdoc Research - AI in EdTech | 🇮🇳 🇳🇱 🇩🇪 | https://teapawt.net/t.co/qcFTbxo31M | 🎥
CAREER Advice SUBSCRIBE 👇👉
Joined October 2012
- Tweets7K
- Following760
- Followers817
- Likes22.1K
Pinned Tweet
An experience of a lifetime when you end something significant! PhD done :)
Thank you everyone, thanks to my supervisors and the committee for this awesome experience! Especially, my supervisors made this time period a memorable one which will be etched in my memory forever.
Dr. Sambit Praharaj retweeted
Transformer Architecture
Explained in 3 ways here:
- Encoder only
- Deconder only
- Encoder - Decoder both
Dr. Sambit Praharaj retweeted
We're publishing our most detailed threat intelligence report to date.
It covers how people tried to misuse Claude—for cyberattacks, influence operations, surveillance, biology, and building weapons—and how we found and stopped them.
We disrupted every operation in the report, and used the lessons from them to strengthen our safeguards. Where appropriate, we also shared what we found with authorities and other AI companies.
These cases are not typical: we’re highlighting some of the most sophisticated misuse we’ve seen. But they’re especially important to discuss, because they show us where AI misuse is headed, where our safeguards work, and where they need to improve.
We’re publishing this report so others can spot the same activity on their own platforms, and so we can give the public a clearer view of how emerging threats develop.
Read the report: anthropic.com/threat-intelli…
Dr. Sambit Praharaj retweeted
🤖 Day 1/30 - AI Agents Series
In this first post, we'll understand what AI Agents are, how they differ from traditional LLM applications, and why they are becoming the foundation of modern AI systems.
What Are AI Agents?
An AI Agent is a software system that can perceive information, reason about a task, make decisions, and perform actions to achieve a specific goal with minimal human intervention.
Unlike a traditional chatbot that simply responds to prompts, an AI Agent can plan, use tools, remember previous interactions, retrieve information, and execute multi-step workflows.
LLMs vs AI Agents
A Large Language Model (LLM) generates text based on the prompt it receives.
An AI Agent uses an LLM as its "brain" but combines it with additional capabilities such as:
Memory
Planning
Tool usage
Decision making
External APIs
Knowledge retrieval
Multi-step reasoning
Think of it this way:
LLM = Thinks and generates responses.
AI Agent = Thinks, decides, and takes actions.
What Is an AI Workflow?
An AI workflow is a predefined sequence of steps.
For example:
User uploads a PDF.
System extracts the text.
LLM summarizes the content.
Summary is emailed back to the user.
The flow is fixed and predictable.
What Is an Autonomous AI Agent?
An autonomous AI Agent decides what to do next without requiring instructions for every step.
For example, a coding agent can:
Read a GitHub repository.
Analyze the codebase.
Find bugs.
Generate fixes.
Run tests.
Repeat until the task is complete.
Instead of following a rigid workflow, it adapts its actions based on the current situation.
Building AI Agents this way makes applications more scalable, flexible, and capable of solving complex real-world problems.
Project: Build Your First AI Chatbot Agent
Today we'll build a simple AI chatbot agent.
The chatbot will:
Accept user questions.
Send them to an LLM.
Generate intelligent responses.
Maintain conversation history.
Remember previous messages during the session.
This project introduces the fundamental architecture behind AI agents and serves as the foundation for every project we'll build throughout this series. In the coming days, we'll continue expanding it with memory, tools, retrieval, APIs, planning, and autonomous capabilities.
Grab the Building AI Agents from Scratch Ebook: codewithdhanian.gumroad.com/…
#AIAgents #LLM #GenerativeAI #ArtificialIntelligence
Building AI Agents from Scratch Tutorial Series (AI Era Edition) in 30 days.( If interested say hi 👋)
Master modern AI agent engineering by building production-ready autonomous AI systems from the ground up.
1. Day 1: What Are AI Agents? – LLMs, Agents, Workflows, and Autonomous Systems
Project: Build your first AI chatbot agent.
2. Day 2: Setting Up the Development Environment – Python, VS Code, APIs, and Virtual Environments
Project: Configure a complete AI agent development workspace.
3. Day 3: Understanding Large Language Models (LLMs) – Prompting, Tokens, Context Windows, and Reasoning
Project: Connect your application to an LLM API.
4. Day 4: Prompt Engineering for AI Agents – System Prompts, Instructions, and Few-Shot Learning
Project: Build a prompt-driven coding assistant.
5. Day 5: Agent Architecture – Planning, Reasoning, Memory, and Actions
Project: Design a reusable AI agent framework.
6. Day 6: Building an Agent Loop – Observe, Think, Plan, Act, and Reflect
Project: Create an autonomous task execution agent.
7. Day 7: Tool Calling and Function Calling
Project: Build an AI agent that uses weather and calculator tools.
8. Day 8: Memory Systems – Short-Term, Long-Term, and Vector Memory
Project: Create an AI assistant that remembers previous conversations.
9. Day 9: Retrieval-Augmented Generation (RAG) Fundamentals
Project: Build a PDF question-answering agent.
10. Day 10: Embeddings and Vector Databases – FAISS, ChromaDB, and Pinecone
Project: Create a searchable knowledge base.
11. Day 11: AI Agent Planning Strategies – ReAct, Chain-of-Thought, and Tree of Thoughts
Project: Build a reasoning-based planning agent.
12. Day 12: Multi-Step Workflows and Task Decomposition
Project: Build an AI research assistant.
13. Day 13: AI Agents with MCP (Model Context Protocol)
Project: Connect an AI agent to external developer tools using MCP.
14. Day 14: AI Agents with LangChain
Project: Build a document analysis agent.
15. Day 15: AI Agents with LangGraph
Project: Build a stateful multi-step AI workflow.
16. Day 16: AI Agents with OpenAI Agents SDK
Project: Create a customer support AI agent.
17. Day 17: Browser Automation Agents
Project: Build an AI web automation assistant.
18. Day 18: Computer Use Agents
Project: Create an AI agent that automates desktop tasks.
19. Day 19: Coding Agents and Software Engineering Assistants
Project: Build an AI code review assistant.
20. Day 20: AI Agents with APIs and Databases
Project: Build an AI-powered CRM assistant.
21. Day 21: Multi-Agent Systems – Collaboration and Communication
Project: Build a team of specialized AI agents.
22. Day 22: AI Agent Security, Guardrails, and Safety
Project: Secure an AI agent against prompt injection.
23. Day 23: AI Agent Evaluation and Benchmarking
Project: Build an automated testing framework for agents.
24. Day 24: Voice AI Agents – Speech-to-Text and Text-to-Speech
Project: Build a voice assistant.
25. Day 25: Vision AI Agents – Image Understanding and Multimodal Models
Project: Build an AI image analysis assistant.
26. Day 26: AI Agents with Local Models – Ollama, LM Studio, and Open-Source LLMs
Project: Run an offline AI agent locally.
27. Day 27: Deploying AI Agents – Docker, Cloud, CI/CD, and Monitoring
Project: Deploy a production-ready AI agent.
28. Day 28: AI SaaS Architecture – Authentication, Billing, and User Management
Project: Build an AI Agent SaaS platform.
29. Day 29: Scaling AI Agents – Performance, Cost Optimization, Caching, and Observability
Project: Optimize an enterprise AI agent deployment.
30. Day 30: Final Capstone Project – Build a Production-Ready AI Agent Platform with Memory, RAG, MCP, Tool Calling, Multi-Agent Collaboration, Authentication, Docker Deployment, Monitoring, and Cloud Hosting.
Grab the Building AI Agents from Scratch Ebook:
codewithdhanian.gumroad.com/…
#AIAgents #AgenticAI #LLM #ArtificialIntelligence
Follow @e_opore to learn more.
Dr. Sambit Praharaj retweeted
10 GitHub repos so good they probably shouldn't be free.
1. OmniRoute
One endpoint. 231 AI providers. 50+ free-tier providers.
Connect Claude Code, Codex, Cursor, and Cline to Claude, GPT, and Gemini for free.
Compresses tokens by 15–95% with automatic fallback if a provider goes down.
GitHub:
github.com/diegosouzapw/Omni…
2. OfficeCLI
The first Office suite built for AI agents.
Control Word, Excel, and PowerPoint from a single command line.
No Microsoft Office installation. No dependencies. Just one binary.
GitHub:
github.com/iOfficeAI/OfficeC…
3. System Prompts Leaks
Leaked system prompts from Claude, GPT, Gemini, Grok, Cursor, Copilot, and more.
Regularly updated.
GitHub:
github.com/asgeirtj/system_p…
4. OpenCut
An open-source CapCut alternative that runs in your browser.
No account. No telemetry. No subscription.
GitHub:
github.com/OpenCut-app/OpenC…
5. AI Job Search
A Claude Code-powered agent that applies for jobs for you.
Analyzes listings, tailors your resume, writes cover letters, and prepares interview questions.
GitHub:
github.com/MadsLorentzen/ai-…
6. Meetily
A fully local meeting transcription and summarization tool powered by Whisper and Ollama.
Built in Rust.
GitHub:
github.com/zaid-maker/meetil…
7. Vibe-Trading
Use natural language and AI agents to build and execute trading strategies.
GitHub:
github.com/HKUDS/Vibe-Tradin…
8. Strix
An AI-powered open-source vulnerability scanner.
Finds and helps fix security issues before attackers do.
GitHub:
github.com/usestrix/strix
9. Superpower
A self-hosted AI workspace with 250k+ GitHub stars.
GitHub:
github.com/superpowerlabs/su…
10. Firecrawl
Turn any website into clean, LLM-ready data in seconds.
The industry standard for RAG and data pipelines.
GitHub:
github.com/mendableai/firecr…
100% Open Source.
All of them are free.
All of them are worth bookmarking.
Dr. Sambit Praharaj retweeted
An asian guy has discovered a method to learn anything ten times faster using AI!
It just involves the Claude + Obsidian.
Most people learn the slow way: read, forget, re-read, forget again.
His flip: use Claude to turn anything you're learning into small, connected notes. Use Obsidian to link them so nothing you learn ever sits alone.
The slow way: highlight a book, move on, forget it in a week.
The fast way: Claude breaks it into atomic notes, and Obsidian links them into a growing web of knowledge.
Six months in, one new idea instantly connects to twenty things you already know.
Dr. Sambit Praharaj retweeted
Train your own language model from scratch in 5 minutes. 🥹
Most people think training LLMs is rocket science.
it ridiculously simple:
No PhD, No massive cluster, you can Runs in browser,
Just one Colab notebook The entire pipeline data gen, tokenizer, training, inference,
This is the best "how LLMs actually work" demo I've seen. Perfect for beginners
- github.com/arman-bd/guppylm
Dr. Sambit Praharaj retweeted
Turn Claude Code into a full academic research team with this guide.
> Deep Research: 13 agents, 8 modes
> Academic Paper: 12 agents, 11 modes
> Academic Paper Reviewer: 7 agents
> Academic Pipeline: 10-stage orchestrator with citation verification
Free for non-commercial use.
Dr. Sambit Praharaj retweeted
🚨 BREAKING: Research just became 10x faster.
Claude can now turn dozens of academic papers into clear, structured insights — like a top-tier researcher.
No more overwhelm. Just clarity.
Here are 9 prompts to get straight to the point 👇
Bookmark this 🔖
Dr. Sambit Praharaj retweeted
THE GUY WHO WON ANTHROPIC'S HACKATHON JUST GAVE AWAY HIS ENTIRE CLAUDE CODE PLAYBOOK FOR FREE. 10 MONTHS OF WORK, ALL PUBLIC
Affaan Mustafa won the Anthropic x Forum Ventures hackathon by building a full startup in 8 hours with Claude Code. Then he open-sourced the exact setup that did it. It's called Everything Claude Code, and it turns Claude from one assistant into an entire engineering team
Repo: affaan-m/ecc
This isn't a prompt pack. It's a system he refined over 10+ months of daily use shipping real products
What's inside:
A huge library of skills, dozens of specialized subagents, and ready-made commands, all working together. Each piece does one job. One subagent reviews security against OWASP standards. One optimizes memory so Claude stops forgetting earlier decisions around hour three. One learns from your past sessions and projects so the setup gets smarter the more you use it. Others handle planning, test-driven development, and language-specific code review
Instead of one assistant writing code, you get an orchestrated team. A main session delegates to the right specialist when the task calls for it, the way a real dev team splits work
The best part: it's not locked to one tool. It runs in Claude Code, Cursor, Codex and OpenCode, across Windows, Mac and Linux. Free, MIT licensed
This is the difference between using Claude like a search box and running it like a team that ships. The guy spent 10 months figuring out what actually works so you don't have to
Bookmark this
Dr. Sambit Praharaj retweeted
Claude Code can now run an entire PhD-level research pipeline by itself.
it runs a 10-stage workflow from blank page to publication-ready PDF, replacing the work of a PhD advisor, three peer reviewers, and a copy editor in one repo.
→ Deep research with 13 agents (PRISMA + systematic review)
→ 12 agents write the paper section by section
→ 5-person peer review (Editor + 3 Reviewers + Devil's Advocate)
→ Integrity agent catches fabricated citations + stat errors
→ Final output: LaTeX → PDF, ready to submit
After the paper is finalized, it runs a Collaboration Quality Evaluation that scores YOU, across 6 dimensions, 1–100. Direction setting, intellectual contribution, quality gatekeeping.
It tells you exactly where you were the bottleneck.
Drop it into .claude/skills/ and the whole pipeline auto-loads. Works in Claude Code, Cowork, and as a Claude Project.
100% open source. CC-BY-NC 4.0.
Dr. Sambit Praharaj retweeted
10 WEBSITES EVERY STUDENT SHOULD USE BEFORE GRADUATION.
Bookmark every single one. Your university will never tell you about most of these.
1. notebooklm.google
Upload every textbook, lecture, and PDF for a course. Ask questions across all of them. Built by Google DeepMind.
2. sci-bot.ru
Search scientific research fast. Ask any question and get answers with links to relevant papers in seconds.
3. annas-archive.gl
The world's largest open library. Almost any textbook your professor assigned is on here for free.
4. perplexity.ai
Research assistant that cites every source. Replaces 90% of Google searches for academic work.
5. zotero.org
Free reference manager that builds your bibliography automatically. Saves 20+ hours per semester.
6. wolframalpha.com
Solves math, physics, chemistry, and engineering problems step by step. Shows the full working.
7. handshake.com
The job platform built specifically for students. 1.4 million employers actively recruiting on it right now.
8. fastweb.com
Matches you to scholarships you actually qualify for. Over $3.4 billion awarded to students every year.
9. coursera.org/learn/learning-…
Free Barbara Oakley course taken by 4 million people. The science of how to actually study and remember.
10. linkedin.com/learning
Free with most university logins. 16,000+ courses on everything from Excel to AI engineering.
The students who graduate with the biggest head start are not smarter. They just found the right tools earlier.
Dr. Sambit Praharaj retweeted
🚨Breaking: Someone open sourced a knowledge graph engine for your codebase and it's terrifying how good it is.
It's called GitNexus. And it's not a documentation tool.
It's a full code intelligence layer that maps every dependency, call chain, and execution flow in your repo -- then plugs directly into Claude Code, Cursor, and Windsurf via MCP.
Here's what this thing does autonomously:
→ Indexes your entire codebase into a graph with Tree-sitter AST parsing
→ Maps every function call, import, class inheritance, and interface
→ Groups related code into functional clusters with cohesion scores
→ Traces execution flows from entry points through full call chains
→ Runs blast radius analysis before you change a single line
→ Detects which processes break when you touch a specific function
→ Renames symbols across 5+ files in one coordinated operation
→ Generates a full codebase wiki from the knowledge graph automatically
Here's the wildest part:
Your AI agent edits UserService.validate().
It doesn't know 47 functions depend on its return type.
Breaking changes ship.
GitNexus pre-computes the entire dependency structure at index time -- so when Claude Code asks "what depends on this?", it gets a complete answer in 1 query instead of 10.
Smaller models get full architectural clarity. Even GPT-4o-mini stops breaking call chains.
One command to set it up:
`npx gitnexus analyze`
That's it. MCP registers automatically. Claude Code hooks install themselves.
Your AI agent has been coding blind. This fixes that.
9.4K GitHub stars. 1.2K forks. Already trending.
100% Open Source.
(Link in the comments)
Dr. Sambit Praharaj retweeted
the polymath is not a person who collects hobbies.
it is a person who refuses artificial borders.
• art and science
• engineering and philosophy
• history and design
for most of history, these were not separate worlds.
the polymath by peter burke shows that broad thinkers shaped culture by moving between domains.
they borrowed methods
translated ideas
connected distant fields
specialists optimize inside systems.
polymaths redesign the map itself.
in an age of narrow expertise, synthesis becomes rare leverage.
Dr. Sambit Praharaj retweeted
🚨 The creator of Claude Code just shared a full walkthrough on how to actually use it the right way.
30 minutes. Free. Straight from the person who built it.
Watch the workshop and save it for later.
You’ll likely get more practical value from this than from most expensive coding courses online.
Most people are only scratching the surface of what Claude Code can do.
Then check out the guide below.
Dr. Sambit Praharaj retweeted
100 Claude Repos that will completely change your life:
(save this)
1. Terminal AI coding agent github.com/anthropics/claude…
2. Ready-to-use starter apps github.com/anthropics/claude…
3. Official agent skills github.com/anthropics/skills
4. Plugin marketplace github.com/anthropics/claude…
5. Full ecosystem github.com/orgs/anthropics/r…
6. Master list github.com/hesreallyhim/awes…
7. 1000+ plugins github.com/quemsah/awesome-c…
8. Huge skills library github.com/sickn33/antigravi…
9. Curated skills github.com/VoltAgent/awesome…
10. Cross-platform skills github.com/alirezarezvani/cl…
11. LLM pipelines github.com/langchain-ai/lang…
12. Agent workflows github.com/langchain-ai/lang…
13. Multi-agent systems github.com/microsoft/autogen
14. Team-based agents github.com/crewAIInc/crewAI
15. AI dev team github.com/metaGPT/metaGPT
16. Code agents github.com/gpt-engineer-org/…
17. Auto PR fixes github.com/sweepai/sweep
18. AI coding assistant github.com/continue-repl/con…
19. Code search github.com/BloopAI/bloop
20. Agent standards github.com/agentprotocol/age…
21. Productivity plugins github.com/anthropics/knowle…
22. AI SDK github.com/vercel/ai
23. Memory layer github.com/upstash/context7
24. Voice agents github.com/fixie-ai/ultravox
25. Deploy agents github.com/superagent-ai/sup…
26. Web agents github.com/xlang-ai/OpenAgen…
27. Reasoning agents github.com/ysymyth/ReAct
28. Long-term memory github.com/mem0ai/mem0
29. AI apps infra github.com/helixml/helix
30. API layer github.com/trpc/trpc
31. Clean UI github.com/ChatGPTNextWeb/Ne…
32. Self-hosted UI github.com/open-webui/open-w…
33. Modern UI github.com/mckaywrigley/chat…
34. Desktop app github.com/lencx/ChatGPT
35. Next.js clone github.com/Nutlope/chatGPT-c…
36. Template github.com/vercel-labs/ai-ch…
37. Claude-ready UI github.com/Yidadaa/ChatGPT-N…
38. Minimal UI github.com/ivanfioravanti/ch…
39. Lightweight UI github.com/louislam/ChatGPT-…
40. Adaptable UI github.com/zk-ml/chatglm-web
👇
Dr. Sambit Praharaj retweeted
Stop wasting hours trying to learn AI. 📘📚
I have already done it for you.
With one list. Zero confusion. And no fluff
📹 Videos:
1. LLM Introduction: lnkd.in/dMqbaZdK
2. LLMs from Scratch: lnkd.in/dYYwEhYy
3. Agentic AI Overview (Stanford): lnkd.in/dArmMt2i
4. Building and Evaluating Agents: lnkd.in/dBWd2W8u
5. Building Effective Agents: lnkd.in/dHfdebqw
6. Building Agents with MCP: lnkd.in/dXuNHrRJ
7. Building an Agent from Scratch: lnkd.in/da3ANw3w
8. Philo Agents: lnkd.in/dq-BfZE5
🗂️ Repos
1. GenAI Agents: lnkd.in/d3UDtwwv
2. Microsoft's AI Agents for Beginners: lnkd.in/dHvTmJnv
3. Prompt Engineering Guide: lnkd.in/gJjGbxQr
4. Hands-On Large Language Models: lnkd.in/dxaVF86w
5. AI Agents for Beginners: lnkd.in/dHvTmJnv
6. GenAI Agentshttps://lnkd.in/dEt72MEy
7. Made with ML: lnkd.in/d2dMACMj
8. Hands-On AI Engineering:lnkd.in/dgQtRyk7
9. Awesome Generative AI Guide: lnkd.in/dJ8gxp3a
10. Designing Machine Learning Systems: lnkd.in/dEx8sQJK
11. Machine Learning for Beginners from Microsoft: lnkd.in/dBj3BAEY
12. LLM Course: lnkd.in/diZgGACG
🗺️ Guides
1. Google's Agent Whitepaper: lnkd.in/gFvCfbSN
2. Google's Agent Companion: lnkd.in/gfmCrgAH
3. Building Effective Agents by Anthropic: lnkd.in/gRWKANS4.
4. Claude Code Best Agentic Coding practices: lnkd.in/gs99zyCf
5. OpenAI's Practical Guide to Building Agents: lnkd.in/guRfXsFK
📚Books:
1. Understanding Deep Learning: lnkd.in/dgcB68Qt
2. Building an LLM from Scratch: lnkd.in/g2YGbnWS
3. The LLM Engineering Handbook: lnkd.in/gWUT2EXe
4. AI Agents: The Definitive Guide - Nicole Koenigstein: lnkd.in/dJ9wFNMD
5. Building Applications with AI Agents - Michael Albada: lnkd.in/dSs8srk5
6. AI Agents with MCP - Kyle Stratis: lnkd.in/dR22bEiZ
7. AI Engineering: lnkd.in/gi-mQcXa
📜 Papers
1. ReAct: lnkd.in/gRBH3ZRq
2. Generative Agents: lnkd.in/gsDCUsWm.
3. Toolformer: lnkd.in/gyzrege6
4. Chain-of-Thought Prompting: lnkd.in/gaK5CXzD.
🧑🏫 Courses:
1. HuggingFace's Agent Course: lnkd.in/gmTftTXV
2. MCP with Anthropic: lnkd.in/geffcwdq
3. Building Vector Databases with Pinecone: lnkd.in/gCS4sd7Y
4. Vector Databases from Embeddings to Apps: lnkd.in/gm9HR6_2
5. Agent Memory: lnkd.in/gNFpC542
Repost for your network ♻️
Dr. Sambit Praharaj retweeted
🚨 BREAKING: Someone just built the exact tool Andrej Karpathy said someone should build.
48 hours after Karpathy posted his LLM Knowledge Bases workflow, this showed up on GitHub.
It's called Graphify. One command. Any folder. Full knowledge graph.
Point it at any folder. Run /graphify inside Claude Code. Walk away.
Here is what comes out the other side:
-> A navigable knowledge graph of everything in that folder
-> An Obsidian vault with backlinked articles
-> A wiki that starts at index. md and maps every concept cluster
-> Plain English Q&A over your entire codebase or research folder
You can ask it things like:
"What calls this function?"
"What connects these two concepts?"
"What are the most important nodes in this project?"
No vector database. No setup. No config files.
The token efficiency number is what got me:
71.5x fewer tokens per query compared to reading raw files.
That is not a small improvement. That is a completely different paradigm for how AI agents reason over large codebases.
What it supports:
-> Code in 13 programming languages
-> PDFs
-> Images via Claude Vision
-> Markdown files
Install in one line:
pip install graphify && graphify install
Then type /graphify in Claude Code and point it at anything.
Karpathy asked. Someone delivered in 48 hours.
That is the pace of 2026.
Open Source. Free.
Dr. Sambit Praharaj retweeted
I made a Claude Code skill that turns any arxiv paper into working code.
Every line traces back to the paper section it came from & any implementation detail the paper skips will be flagged, and not assumed.
open sourcing it -
github.com/PrathamLearnsToCo…