This is not just for writing long form articles, but even for stuff like writing threads about your work and ideas on twitter.
PROMPT ENGINEERING
-

Context Engineering: Key Patterns for Agent Building with LangGraph
By
–
Context Engineering "Context engineering" is a key part of agent building. We review a few popular patterns for context engineering + explain how to use them w/ LangGraph. Blog: https://
blog.langchain.com/context-engine
ering-for-agents/
… Video: https://
youtu.be/4GiqzUHD5AA -

LangGraph Assistants: Configure and Deploy Specialized Agent Versions
By
–
Define your agent logic once, then configure and deploy specialized versions on the fly with LangGraph Assistants. In this video tutorial, you'll learn how to use LangGraph Assistants to: Turn static agents into flexible, runtime-configurable systems Build and manage
-
AI-Generated Adidas Ad Using Midjourney ElevenLabs and More
By
–
Cette pub Adidas réalisé 100% par IA
— VISION IA (@vision_ia) 2 juillet 2025
• Pinterest – pour les références de style
• Claude AI – pour la création de prompts
• Midjourney – pour la génération d’images
• Higgsfield – pour l’animation
• ElevenLabs – pour la voix off
• After Effects – pour le montage https://t.co/tkkMFesm7E pic.twitter.com/v0O2uYoqbpThis Adidas ad made 100% by AI • Pinterest – for style references
• Claude AI – for prompt creation
• Midjourney – for image generation
• Higgsfield – for animation
• ElevenLabs – for voice over
• After Effects – for editing -

Strange Cities: Style Curation in Generative Image Models
By
–
More strange cities.
— Ethan Mollick (@emollick) 1 juillet 2025
(Roughly similar prompts, but the ability to radically alter style makes curation and selection much more important) pic.twitter.com/1mTGMX2MkUMore strange cities. (Roughly similar prompts, but the ability to radically alter style makes curation and selection much more important)
-

From Instant Knowledge to Prompt Engineering: The New Literacy
By
–
We no longer learn to know. We learn to speak well to machines. Knowledge has become instant. What matters is the ability to formulate. Prompt engineering is the new Latin.
Not teaching it condemns us to digital illiteracy. My latest article -
Academic AI Benchmarks: Realism, Rankings, and Methodology Critique
By
–
Many of the academic papers shared on X are benchmarking papers, which are made so that current AIs will fail often (or it isn't a benchmark for future progress) You should pay attention to the realism of the benchmark, relative rankings, and the prompts & tools given to the AI.
-

Slash Commands: Execute Bash, Mention Files, Enable Extended Thinking
By
–
As a reminder, slash commands let you store custom prompts as Markdown files and invoke them with /your-command. With this update, you can now:
– Execute bash commands from slash commands
– @ mention files for context
– Enable extended thinking with keywords within commands -
Better Tools and Prompting for Human-like AI Behavior
By
–
We don't know what a human would do, and I suspect better tools and prompting would help.
-

Multi-modal Researcher with Gemini 2.5 and LangGraph
By
–
Multi-modal researcher with Gemini 2.5 Generate reports + custom podcasts on any topic w/ LangGraph + Gemini 2.5: • YouTube video processing
• Real-time Google Search integration
• Multi-speaker text-to-speech Repository:
https://github.com/langchain-ai/multi-modal-researcher Video:
https://youtu.be/6Ww5uyS0tXw