CodeGraph turns any project folder into a local, queryable Knowledge Graph 1️⃣ Parses 20+ languages locally 2️⃣ Uses a local model to find hidden relationships. 3️⃣ Exposes the graph via an MCP medium.com/agentic-builders/…? #CodeGraph #AIAgents #SoftwareEngineering #MCP #Claude #Cursor

Protecting AI Agents: How Claw Patrol Safeguards Your Systems from Accidental Damage and Attacks #ai #safety #agentic medium.com/agentic-builders/…

The AI puzzle: As AI talks more like us, are we starting to think more like it? Discover #LLMorphism – the mistaken belief that human thinking is like an LLM. #AI #Cognition #Psychology #HumanAI medium.com/@anna.bildea/llmo…

The best enterprise agents in 2026 use a 3-layer stack: 1️⃣ Skills (Domain Knowledge) 2️⃣ MCP (Secure Connectivity) 3️⃣ CLI (Token-Efficient Execution) Stop overloading your LLM. Read the full architecture breakdown here: medium.com/agentic-builders/…

Amazing. No words to describe this tune. Emotional and to the point. New Iranian LEGO movie : We Share the Same Pain 💔 😭🥹 via Brick Beat Battalion

First systematic map of "AI Agent Traps" adversarial web content engineered to hijack autonomous agents. 6 attack classes targeting every layer of an agent's operating cycle: How to Defend Against AI Agent Traps: #ai #agents #Security medium.com/agentic-builders/…

Agent Design Patterns for Long-Running AI Agents medium.com/agentic-builders/… #ai #agents #llm #production #google

How to Use Graphify: Turn Any Folder Into a Knowledge Graph medium.com/agentic-builders/… #aiagents #graph #knowledgegraph #ai

How much budget did you actually approve for your Agentic AI strategy? Not the roadmap. Not the slide deck. The actual signed check. That number tells you everything. #AIStrategy #EnterpriseAI #AgenticAI #AI #Leader

i just published a short article on building applications w/ Claude. captures a few lessons from my own work and many discussions with others at Anthropic. claude.com/blog/harnessing-c…

LiteLLM Attack: How a Security Scanner Backdoored AI medium.com/agentic-builders/…

An AI Broke Into McKinsey’s Platform. Here’s What We Should All Learn From It.“ #ai #genai #security #aiagents #ops medium.com/agentic-builders/…

PI planning in agentic times ..#ai #agile #funny linkedin.com/posts/anabildea…

"Mixture-of-Depths Attention" This paper teaches a Transformer to attend not just across tokens, but also to depth KV from its earlier layers. That helps recover shallow-layer signals that standard residual stacking tends to dilute, improving performance with only a small extra compute cost. Similar idea to Kimi’s Attention Residuals, but MoDA modifies the attention module itself, while AttnRes changes the residual/depth aggregation path.