Excited to announce the new preview for Microsoft Foundry Agents 🎉! You can now build, run, and deploy your agent using any model, any framework, any harness in the cloud 🧑‍💻 - check out the demo below This is not just any cloud compute environment; it's an agent-optimized platform with: 🖥️ Persistent microVMs - securely scale up and down without losing context 🛠️ Built-in tools (1000+) 👀 Observability and evaluations 👷 Guardrails 🔐 Private networking... and more
35
96
16
668
158,136
The creator of Claude Code teaches more about vibe-coding in 30 minutes than most tutorials do in hours. Save this — it'll change how you build forever.
11
The Simplified GraphRAG Stack: Unified Memory Over Fragmented Databases "Building a Graph RAG System without a Graph Database" sounds like a contradiction in terms. Recently, an architecture for implementing Graph RAG without a graph database emerged. Store entities, relations, and passages in 3 Milvus collections linked by IDs. Graph traversal becomes ID lookups. No Cypher. No separate infrastructure. Now a similar principle appears again, but with MongoDB as the unified memory layer instead of Milvus. The pattern: consolidate all memory - documents, vectors, and graph links - into a single system. Stop fragmenting knowledge across databases. Here's how it materializes with MongoDB: The ingestion layer pulls data from URIs, notes, emails, docs. Normalized into a single schema in MongoDB. Raw documents stored durably. The memory pipeline processes each document: Clean text + metadata. Graph extraction (entities + relationships). Normalization (merge "Abi" vs "Abi Aryan").  Embeddings with Voyage AI. Output: knowledge graph objects with triplets, vectors, and metadata. The unified layer lives in a single knowledge_graph collection with three index types working in parallel: Text index for keyword recall.  Vector index for semantic recall. Graph links for multi-hop traversal. All in one place. Retrieval happens through an MCP server exposing GraphRAG as tools. Natural language query for compact retrieval. Deep search for progressive graph expansion. Ingest for new data. The agent layer (Claude Code) orchestrates reasoning. It decides when to retrieve, when to write memory, when to expand context via graph traversal (2-3 hops). Skills bridge the gap: Assistant-memory harnesses semantic retrieval. Assistant-learn pushes insights back to memory. Two independent architects, two database choices, one architectural insight: simplification beats infrastructure sprawl.  Unified memory is the flywheel. Everything else—retrieval, traversal, reasoning—becomes faster and cheaper when you stop syncing multiple systems. The emerging pattern: whether Milvus, MongoDB, or something else, the question is not "which database?" It is "can we consolidate graph, vector, and document memory in one coherent layer?" linkedin.com/posts/pauliuszt… #GraphRAG #UnifiedMemory #MongoDB #AgenticAI #VectorSearch #AIArchitecture -- 📩 The Year of the Graph Spring 2026 newsletter issue is out! Beyond Context Graphs: How Ontology, Semantics, and Knowledge Graphs Define Context 👇 yearofthegraph.xyz/newslette… All things #KnowledgeGraph, #GraphDB, Graph #Analytics / #DataScience / #AI and #SemTech. Subscribe and follow to be in the know. Reach out if you'd like to be featured
8
59
238
10,000
Rajat retweeted
The game has changed. In 2026, building a startup no longer requires millions in capital. Look at this stack: → Claude, ChatGPT, Perplexity for intelligence → Cursor, Replit for building → Figma, Canva for design → Zapier, n8n for automation You don’t need a team. You don’t need funding. You don’t even need to code. Development cost → near zero AI builds your MVP in days, not months. Content cost → near zero AI creates videos, posts, landing pages instantly. Operational cost → near zero Automation replaces entire teams. So what’s the bottleneck now? Not product. Not tech. Not capital. 👉 It’s product-market fit 👉 And distribution The winners in this era won’t be the best builders. They’ll be the best: • Storytellers • Distributors • Audience builders Because when everyone can build… Attention becomes the only moat. This is the new startup equation: Build fast → Test fast → Distribute faster If you nail: 1.A real problem 2.A product people actually want 3.A distribution engine You don’t just build a startup. You’re on the path to a unicorn. The barrier to entry is gone. The barrier to success just moved.
18
8
3
23
1,772
Announcing: Agentic Document Extraction! PDF files represent information visually - via layout, charts, graphs, etc. - and are more than just text. Unlike traditional OCR and most PDF-to-text approaches, which focus on extracting the text, an agentic approach lets us break a document down into components and reason about them, resulting in more accurate extraction of the underlying meaning for RAG and other applications. Watch the video for details.
272
845
90
6,132
690,011
Great post on #ReverseMigration
Indians are dying to live abroad But NRIs living there want to come back to India The Crazy Part? 80% of NRIs in Australia, 75 % in the US & 70% from the UK want to return to India THREAD: what’s causing the reverse migration of NRIs🧵
16
USBP and partners successfully returned illegal aliens to India, marking the farthest deportation flight yet using military transport. This mission underscores our commitment to enforcing immigration laws and ensuring swift removals. If you cross illegally, you will be removed.
922
875
748
2,812
1,361,764
India is taking a bold step into AI with its own AI chip, targeting a 2027 rollout! This is a great step by #IndianGovernment ! Ready to contribute in this journey @AshwiniVaishnaw @GoI_MeitY @nasscomCoEIoT Exciting times ahead ! #AI #Semiconductors #IndiaTech
8
Here’s how to do 4-7-8 breathing: 1. Breathe in through your nose for a 4-second count. 2. Hold your breath for a 7-second count. 3. Exhale for an 8-second count, making a "whoosh" sound through pursed lips. 4. Repeat up to four times, twice per day.
27
1,359
77
10,209
What can we learn - A lot actually! India needs to give away its traditional way of education & promote progressive ways #India
Finland’s education system is one of the best in the world 🇫🇮 wef.ch/2Ig0jpJ
“Business is next to love, it is the creator and preserver of civilisation.” Great meeting & Hearing #NandKishoreChaudhary at @PeopleMatters2 #TechHRIN, great and humble person!
1
Great start of the day #TechHRIN @Ester_Matters @PeopleMatters2 #PeopleMatters exciting couple of days ahead!
1
If we want people to talk to us more, we should start by listening to them more.
58
594
38
3,401
How will the jobs market of tomorrow look? A 2022 report looks at how post-pandemic employment can boost economic activity, create new opportunities and generate multiplier effects in the form of more inclusive economies and societies. wef.ch/3lKX5eQ
12
34
I completed three months recently working in an amazing open-source startup 💜 These are the Three Main Learning I want to share with everyone🧵
2
10
49
One of the truly dark tech startups in India is an app called MyGate. They bypass end-user consent by colluding with resident welfare associations. Users need it for “approving” entry for delivery services to their flat. 🧵
1