Prompt and context engineering
Read the Portuguese translation →
The synthesis for this topic is available in Portuguese.
Videos in this topic
Section titled “Videos in this topic”- Stop Sounding Like AI. (Give Claude These 5 Files Instead)
- Claude & ChatGPT’s NEW Upgrades Change EVERYTHING! (Intelligent UI, Managed Agents & More)
- V7 cuts costs 78% while boosting accuracy with GPT‑5.6 Luna
- Teaching LLMs to Speak Spotify — Yves Raimond & Jacqueline Wood, Spotify
- Introducing the Agents API
- Como utilizar a Skill Grill Me Para Criar a Base de Projetos com IA
- How I Keep Up with AI Without Drowning in It (Free Skill)
- Skills are just fancy prompts. Here’s why that matters.
- Structured Output in the browser with Transformers.js 4.3
- Give Your Agent a Map to Manage Context | Harness Engineering 101
- DeepSeek Solved AI’s Memory Problem
- You’re Prompting Opus 5.5 Wrong (Anthropic’s Guide to Mastering Opus 5.5)
- JEV vs LLM Memory | How AI Agents Build Better Memory | Rakesh Gohel
- Stop Telling Agents How — Dan Barrett, Raymond Weitekamp & Jose Montes de Oca, OpenProse
- Stop Telling Claude to “Think Carefully.” Do This Instead.
- O Claude Code esquece tudo. O Akita resolveu criando o AI Memory
- Teach AI how your business actually runs
- Claude Code 3.0 is CRAZY!
- Anthropic Just Revealed How Their Engineers Use Claude Code
- How to Make Insane Motion Animations with Claude!
- Agent Memory Is Solved. Agent Learning Isn’t. — Karthik Ranganathan, Yugabyte
- Como Tranformar Referências em Design System
- Context Language Models: Your Agent Doesn’t Need Compaction
- Learn to build better AI Agents through better context
- 12 Segredos do Opus 5.5 Revelados Pela Anthropic (Mais Rápido e Barato)
- Tencent’s Memory Model “Beats Claude Opus 5”. I Rented a GPU to Check
- Why Bigger Context Windows Won’t Save Your Agent — Elizabeth Fuentes Leone, AWS
- GrokBot + Dots = Insane Agentic OS
- 7 Insane Claude Mods You Need To Try Right Now
- Solve AI Data Navigation: Lovelace & Gemini Enterprise
- How To Build A Harness With Jev | A LangChain x TypeSafe Conversation
- Two Mods To Improve Claude Code Performance
- Pinecone 2.0 — Edo Liberty, Pinecone
- Transformers.js v4.3: Structured Output in the browser
- I Tested Anthropic’s Opus 5.5 Prompting Guide (36 Real Runs)
- Gemini 4 Argon: What’s new and what’s next
- Coloquei o Jev nos mods do Claude Code e é ABSURDO! (entreguei os prompts)
- Your agents can get smarter over time with Hindsight. The most powerful AI memory system.
- The Data Context Layer for Agents — Yoni Michael & Brandon Callender, Typedef
- Memory-Aware Agent Harnesses for Anti-Money Laundering — Nacho Martinez, Oracle
- Edge0 35B Tested: 0 Tokens on a 4090, 187 tok/s the Normal Way
- Claude Code Mods: 8 You Should Install Today (Free)
- Claude Projects Just Got Rebuilt (Full Guide)
- Beating RL With Reflection: GEPA and Optimize Anything — Lakshya A. Agrawal, GEPA
- Your AI Forgets Everything. This Free Tool Fixes It (Hindsight, Tested)
- Por que todo mundo fala tanto de Agent Skills? Guia completo
- Building the Document Context Layer for AI Agents — Jerry Liu, LlamaIndex
- System 1 vs System 2 Explained
- Suas notas agora podem entrar na mente do NotebookLM
- The Model Swap Workshop: GPT-5.5 vs Kimi vs DeepSeek vs Mistral
- How Deep Agents Manages Context: Offloading and Summarization
- Meet the Data Agent in ChatGPT Work
- Vast-10M Hands-On: Does 10 Million Tokens of Context Hold Up?
- Inside Managed Deep Agents: mda CLI, Context Hub, and Harbor Evals | Interrupt London
- Grep or Embeddings? Agentic Search Over Company Documents — George He, LlamaIndex
- Como a atualização do Claude e ChatGPT muda o seu prompt
- Jev Just Got Eyes. It Beat GPT-6.1: 9× Faster, 20× Cheaper (1,000 Photos)
- Stop Chatting With Claude. (Use This 1% Blueprint Instead)
- The Cost of Accessibility in AI — Jemima Abu, CAIS
- 😮 Isso Custaria uma FORTUNA para Filmar! EU Fiz com IA! Teste prático! Pollo AI!
- Why AI Writing Still Reads Like Slop — Louis-François Bouchard, Towards AI
- Stop Renting Your AI’s Memory — Dylan Couzon, Qdrant
- 16 dicas OFICIAIS que deixam o Opus 5.5 MUITO melhor (testei num projeto real)
- I Built JARVIS with GPT-6 Astra… It’s Insane
- What is a Skill?
- Why Your Company Needs a Context Graph (and How to Build It) — Gil Feig, Merge
- Opus 5.5 OFFICIAL Super Mode: So, ANTHROPIC JUST REVEALED HOW TO MAKE Opus WAY BETTER!
- The first API built for Dictation: AssemblyAI’s Dictation API
- Agora o Jev decide se o Claude Code pode rodar o comando. É bizarro!
- How to Write Your First AI Eval - SallyAnn DeLucia, Arize AI
- Claude 5.5 Model Mistakes you may still be making (23 Tips and Fixes)
- Full Course: Spec-Driven Development with Coding Agents
- 25 Hidden Settings That You Need In Your Claude Code Setup
- GRÁTIS: AULA COMPLETA 2 HORAS SOBRE FINE-TUNING
- Why We Deleted Our MCP Server and Rebuilt It — Abhi Arya, Reducto
- ChatGPT’s New Changes are MIND BLOWING! (New Extension, Voice Mode & More)
- Claude Code Skills, Explained Simply.
- Qwen Image 2.1 - Low VRAM 7B All-in-One Model | Local Install, Tests & Prompt Guide
- Google Antigravity Livestream: Behind the Product and Gemini 4 Argon
- Anthropic Made an Official Claude Certification — Everything on the Exam (CCA-F)
- The SDLC You Build Yourself — Andy Wong, Andrei Bocan & Shane Wolf, Atlassian
- MCP Doesn’t Suck. Your Agent Does. — Jan Čurn, Apify
- Harness² Explained: Self-Improving Agents Without Training
- From Vibes to Production: Evaluating and Shipping AI Agents That Work 101 — Laurie Voss, Arize AI
- Jev + Claude Code — When you give Voice Control of My Browser to an AI
- Gemini Cloud Agent Interview: One Memory Across Your Full Stack
- How Stripe Built Kai
- Germany’s New 78B Open Model (Kolibri-1) Runs at 126 Tokens/Sec on ONE GPU (I Tested It Hard)
- Beyond RAG: Build a Relational Context Engine from Scratch — Peter Werry, Unblocked
- Your Agent Isn’t Dumb. Your Context Is Broken.
- Sonnet 5.5 ou Opus 5.5? O guia oficial da Anthropic
- Paving the Road to Production: Governed Enterprise AI Agents — Harish Gaggar, Credit Karma
- Building AI Assistants with On-Device Memory
- These 9 Claude Mods Make Claude Code Feel Brand New (Install Guide Included)
- Stop Prompting AI. Use Karpathy’s Method Instead.
- Introducing Agent Memory on Databricks
- Microsoft Work IQ could cut AI token usage by 80%
- My Self Training Claude Code Setup: I Made Claude Code TRAIN ITSELF!
- Configurei um projeto no Claude do zero para implementar uma feature completa
- Qwen 3.8 in DeepSeek Harness: Free, Local, One Catch
- Total Recall: Agent Memory and Harness Engineering — Ignacio Martinez, Oracle
- How to Build Agents That Improve Over Time: Model, Harness, Context | Interrupt London
- O que vai acontecer com a engenharia de prompt em 2027
- Peguei as regras vazadas do Claude Code e colei num modelo de 15 centavos (RESULTADO ABSURDO!)
- Using Jev In Your Agent Harness
- ChatGPT, Google Gemini & Claude’s BIGGEST Updates From This Week! (AI News Update)