#contextengineering — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #contextengineering, aggregated by home.social.
-
via @dotnet : Instructions Hygiene – What Frontier Models Still Need You to Say
https://ift.tt/qPefhUp
#InstructionsHygiene #FrontierModels #AIContext #ContextEngineering #RepoInstructions #CodeRepositories #SoftwareEngineering #ModelGuidance #ContextBudget #Hig… -
via @dotnet : Instructions Hygiene – What Frontier Models Still Need You to Say
https://ift.tt/qPefhUp
#InstructionsHygiene #FrontierModels #AIContext #ContextEngineering #RepoInstructions #CodeRepositories #SoftwareEngineering #ModelGuidance #ContextBudget #Hig… -
The new rules of context engineering for Claude 5 generation models
https://claude.com/blog/the-new-rules-of-context-engineering-for-claude-5-generation-models
Comments: https://news.ycombinator.com/item?id=49051361
#HackerNews #contextengineering #Claude5 #AItechnology #machinelearning #innovation
-
The new rules of context engineering for Claude 5 generation models
https://claude.com/blog/the-new-rules-of-context-engineering-for-claude-5-generation-models
Comments: https://news.ycombinator.com/item?id=49051361
#HackerNews #contextengineering #Claude5 #AItechnology #machinelearning #innovation
-
⚠️ Takeaway: the theory is promising, the practice is immature. Image handling is not optimized yet, so token savings get eaten by wall-clock time. It depends on the use case — run your own tests instead of trusting the hype.
https://youtube.com/watch?v=Bbt8cEyzsTk #AI #contextengineering
DeepSeek-OCR: Contexts Optical Compression (Haoran Wei, Yaofeng Sun, Yukun Li — DeepSeek-AI)
Paper: https://arxiv.org/abs/2510.18234
PDF: https://arxiv.org/pdf/2510.18234 -
⚠️ Takeaway: the theory is promising, the practice is immature. Image handling is not optimized yet, so token savings get eaten by wall-clock time. It depends on the use case — run your own tests instead of trusting the hype.
https://youtube.com/watch?v=Bbt8cEyzsTk #AI #contextengineering
DeepSeek-OCR: Contexts Optical Compression (Haoran Wei, Yaofeng Sun, Yukun Li — DeepSeek-AI)
Paper: https://arxiv.org/abs/2510.18234
PDF: https://arxiv.org/pdf/2510.18234 -
🖼️ Can images replace text as LLM context? A #DeepSeek paper claims one image token carries ~10 text tokens of information at close to 100% accuracy, with 59-70% cost reduction reported by PixelPipe. ThePrimeagen put it to the test. #AI #LLM #contextengineering 🧵👇
-
🖼️ Can images replace text as LLM context? A #DeepSeek paper claims one image token carries ~10 text tokens of information at close to 100% accuracy, with 59-70% cost reduction reported by PixelPipe. ThePrimeagen put it to the test. #AI #LLM #contextengineering 🧵👇
-
Could your AI know you as well as your notes do? I explored what happens when you let it try. https://www.ctnet.co.uk/ai-pkm-integration/ #AI #PKM #ContextEngineering
-
Could your AI know you as well as your notes do? I explored what happens when you let it try. https://www.ctnet.co.uk/ai-pkm-integration/ #AI #PKM #ContextEngineering
-
AI agents need product memory, but it must be structured properly to be easily accessible and supportable by both humans and AI. https://hackernoon.com/the-practical-case-for-context-engineering-in-software-teams #contextengineering
-
AI agents need product memory, but it must be structured properly to be easily accessible and supportable by both humans and AI. https://hackernoon.com/the-practical-case-for-context-engineering-in-software-teams #contextengineering
-
AI‑агенты в проде: 6 архитектурных ошибок, из‑за которых они не доживают до запуска
На демо AI‑агент может выглядеть надёжным: вызвать инструменты, собрать ответ и отчитаться об успехе. Но в продакшене быстро всплывают пустые ответы, петли, потеря контекста, ограничения бюджета и проблемы с правами. Разберём шесть архитектурных ошибок, из‑за которых агент работает в тестовом сценарии, но ломается в реальной системе.
https://habr.com/ru/companies/otus/articles/1047062/
#AI #AIагенты #LLM #архитектура #production #contextengineering #observability #мультиагентныесистемы #надёжность
-
2023 - #PromptEngineering - Writing better instructions
2024 - #ContextEngineering - Feeding the model better information
2025 - #HarnessEngineering - Building infrastructure around the model
2026 - #LoopEngineering - Letting the model repeatedly call itself until a goal is reached
- AI bros discovering automation -
#AI #Automation #Prompt #Context #Harness #Loop #OSS #OpenSource
-
2023 - #PromptEngineering - Writing better instructions
2024 - #ContextEngineering - Feeding the model better information
2025 - #HarnessEngineering - Building infrastructure around the model
2026 - #LoopEngineering - Letting the model repeatedly call itself until a goal is reached
- AI bros discovering automation -
#AI #Automation #Prompt #Context #Harness #Loop #OSS #OpenSource
-
Токен-оптимизация агентов: на что уходит контекстное окно MCP
Чем больше задач берёт на себя агент, тем чаще он упирается не в качество модели, а в контекстное окно: туда нужно уместить инструкции, историю диалога, схемы инструментов и всё, что эти инструменты возвращают. Я считаю, что токен-оптимизация агентов — то, как мы расходуем это окно — станет одним из ключевых направлений ближайших лет, наравне с выбором модели и качеством промпта.
https://habr.com/ru/articles/1046203/
#mcp #claude #anthropic #llm #aiагенты #opensource #contextengineering #ai #claudecode #tokens
-
What if writing the perfect prompt is actually the least important part of working with AI? I've been exploring context engineering — and it's changed how I think about using these tools entirely. https://www.ctnet.co.uk/context-engineering-vs-prompt-engineering/ #ContextEngineering #PromptEngineering #AI
-
What if writing the perfect prompt is actually the least important part of working with AI? I've been exploring context engineering — and it's changed how I think about using these tools entirely. https://www.ctnet.co.uk/context-engineering-vs-prompt-engineering/ #ContextEngineering #PromptEngineering #AI
-
CW: Talking about AI/LLM Context Engineering.
Last year I spent a lot of time discussing the virtues and faults of "Prompt Engineering", but with time I realized there were more faults than virtues. So at some point I started moving towards writing more pre-cooked instructions, skills and other artifacts that pre-load a lot of knowledge upfront, saving time so that the agent doesn't need to go look for information that is mostly static (procedures, rules, URLs to docs, etc).
So yeah, for the past few months I have been investing a lot of effort into "Context Engineering", and all the work on that is saving me a lot of time. Don't ask me if I'm saving tokens, which I'm probably not, but I can tell you for sure that I'm saving a lot of time and sanity, because I don't have to fight the agent when "you should already know that". 😄
If "garbage in/garbage out" is a concern you have, and typing less when prompting, then you also need to start tailoring your context better. And no: AGENTS.md is not enough. You need more than that.
#LLM #Agents #PromptEngineering #ContextEngineering #GitHub #Copilot #Claude
https://github.blog/ai-and-ml/generative-ai/want-better-ai-outputs-try-context-engineering/
-
CW: Talking about AI/LLM Context Engineering.
Last year I spent a lot of time discussing the virtues and faults of "Prompt Engineering", but with time I realized there were more faults than virtues. So at some point I started moving towards writing more pre-cooked instructions, skills and other artifacts that pre-load a lot of knowledge upfront, saving time so that the agent doesn't need to go look for information that is mostly static (procedures, rules, URLs to docs, etc).
So yeah, for the past few months I have been investing a lot of effort into "Context Engineering", and all the work on that is saving me a lot of time. Don't ask me if I'm saving tokens, which I'm probably not, but I can tell you for sure that I'm saving a lot of time and sanity, because I don't have to fight the agent when "you should already know that". 😄
If "garbage in/garbage out" is a concern you have, and typing less when prompting, then you also need to start tailoring your context better. And no: AGENTS.md is not enough. You need more than that.
#LLM #Agents #PromptEngineering #ContextEngineering #GitHub #Copilot #Claude
https://github.blog/ai-and-ml/generative-ai/want-better-ai-outputs-try-context-engineering/
-
"Using MCP, agents can fetch structured data contextually relevant to the task at hand. According to Edgar Kussberg, group product manager at Sonar, MCP accelerates the knowledge-hunting engineers must routinely perform on a daily basis.
“When an engineer needs to answer a question, they do not rely on memory alone,” says Kussberg. “They navigate code repositories, dashboards, CI systems, documentation, and security reports, pulling information from each system as needed. MCP gives AI agents that same capability.”
Many of the most popular MCP servers retrieve contextual information to improve agentic coding. For example, an MCP server from Context7 provides up-to-date documentation, while another from Filesystem pulls from any directory on a local machine. An MCP server from Sentry accesses production issues and errors, a server from SonarQube exposes security issues, and a server from Multiplayer returns user session data.
The great thing about using MCP for these situations is that it avoids the need to put large code chunks in every prompt. Instead, coding context like relevant methods, dependencies, or recent changes can be called at runtime, says Venugopal Jidigam, head of agentic platform engineering at WaveMaker, an agentic development platform. “The MCP server assembles and returns scoped, structured context, which the model then uses to reason and respond accurately,” he says.
Another common context-gathering example is retrieving institutional knowledge. “Instead of hardcoding that knowledge into the model, the agent uses MCP to retrieve relevant documents or data at runtime,” says Ebrahim Alareqi, principal machine learning engineer at Incorta, a data and analytics platform provider. “This keeps the agent lightweight while still giving it access to enterprise-specific context when needed.”"
https://www.infoworld.com/article/4175336/the-role-of-mcp-in-context-engineering.html
#AI #GenerativeAI #LLMs #MCP #ContextEngineering #Documentation #SoftwareDocumentation #AIAgents #AgenticAI
-
"Using MCP, agents can fetch structured data contextually relevant to the task at hand. According to Edgar Kussberg, group product manager at Sonar, MCP accelerates the knowledge-hunting engineers must routinely perform on a daily basis.
“When an engineer needs to answer a question, they do not rely on memory alone,” says Kussberg. “They navigate code repositories, dashboards, CI systems, documentation, and security reports, pulling information from each system as needed. MCP gives AI agents that same capability.”
Many of the most popular MCP servers retrieve contextual information to improve agentic coding. For example, an MCP server from Context7 provides up-to-date documentation, while another from Filesystem pulls from any directory on a local machine. An MCP server from Sentry accesses production issues and errors, a server from SonarQube exposes security issues, and a server from Multiplayer returns user session data.
The great thing about using MCP for these situations is that it avoids the need to put large code chunks in every prompt. Instead, coding context like relevant methods, dependencies, or recent changes can be called at runtime, says Venugopal Jidigam, head of agentic platform engineering at WaveMaker, an agentic development platform. “The MCP server assembles and returns scoped, structured context, which the model then uses to reason and respond accurately,” he says.
Another common context-gathering example is retrieving institutional knowledge. “Instead of hardcoding that knowledge into the model, the agent uses MCP to retrieve relevant documents or data at runtime,” says Ebrahim Alareqi, principal machine learning engineer at Incorta, a data and analytics platform provider. “This keeps the agent lightweight while still giving it access to enterprise-specific context when needed.”"
https://www.infoworld.com/article/4175336/the-role-of-mcp-in-context-engineering.html
#AI #GenerativeAI #LLMs #MCP #ContextEngineering #Documentation #SoftwareDocumentation #AIAgents #AgenticAI
-
Self-Evolving Knowledge: Как взрастить senior агента
Привет! Я не AI-инженер, у меня нет ML образования. Я проджект-менеджер со старым бекграундом в качестве веб-разработчика и с опытом более 10 лет в управлении командами разработки ПО. И с приходом полноценных AI-агентов я стал по выходным заниматься экспериментами на своих пет-проектах. Один из таких проектов - мобильное приложение для запоминания карточек/слов: я учу японский язык и не нашёл ни одного сервиса, в котором добавлять новые слова в словарь было бы не мучительно, поэтому решил сделать своё, для себя. Что ж, для этого у меня не было GPU-кластера и команды, но был MacBook, свободное воскресенье и конкретная проблема, которую я хотел решить. Ниже я опишу свои наблюдения с точки простого PM'a, и вытекающую идею и концепт.
https://habr.com/ru/articles/1041612/
#aiagent #ai #project_management #development #product_management #contextengineering
-
The smartest thing I've done for my AI coding workflow is build a local knowledge base every agent reads and writes to. Claude Code, Codex, and Copilot all hit the same wiki. Claude's work becomes Codex's knowledge.
It's just markdown and git. Every session writes raw transcripts to ~/kb/raw. A nightly cron turns GBs of those into single-digit MBs of curated markdown that every agent checks first. Another cron does GC. That's it.
#Claude #Codex #ClaudeCode #ContextEngineering #DeveloperTools
-
#SoftwareSpecifications can now serve as a dynamic source of truth, as LLM-based reasoning agents become better at interpreting human ambiguity.
The catch? #LLMs are stochastic and must be constrained.
Enter #ContextEngineering - a structured discipline focused on providing clear intent and missing instructions to AI models.
It relies heavily on context artifacts, including: ⇨ Skills ⇨ Rules ⇨ Scripts ⇨ Feedback loops ⇨ Evaluation metrics
🎧 Hear more insights on the #InfoQ #podcast with Baruch Sadogursky: https://bit.ly/49dArFj
📄 #transcript included
#SoftwareArchitecture #SpecDrivenDevelopment #Testing #AI #SoftwareEngineering
-
#SoftwareSpecifications can now serve as a dynamic source of truth, as LLM-based reasoning agents become better at interpreting human ambiguity.
The catch? #LLMs are stochastic and must be constrained.
Enter #ContextEngineering - a structured discipline focused on providing clear intent and missing instructions to AI models.
It relies heavily on context artifacts, including: ⇨ Skills ⇨ Rules ⇨ Scripts ⇨ Feedback loops ⇨ Evaluation metrics
🎧 Hear more insights on the #InfoQ #podcast with Baruch Sadogursky: https://bit.ly/49dArFj
📄 #transcript included
#SoftwareArchitecture #SpecDrivenDevelopment #Testing #AI #SoftwareEngineering
-
The new 10x Engineer with AI
The idea of the “10x engineer” has always been a bit controversial. Some people see it as a myth. Some people see it as a harmful label that creates hero culture. Some people have worked with engineers who clearly create much more impact than others, and believe the idea is real. I sit somewhere in the middle. I don’t think a 10x engineer means someone who writes 10x more code than everyone else. That version of the idea was never useful to me. Writing more code is not the same as […]https://codeaholicguy.com/2026/05/13/the-new-10x-engineer-with-ai/
-
The new 10x Engineer with AI
The idea of the “10x engineer” has always been a bit controversial. Some people see it as a myth. Some people see it as a harmful label that creates hero culture. Some people have worked with engineers who clearly create much more impact than others, and believe the idea is real. I sit somewhere in the middle. I don’t think a 10x engineer means someone who writes 10x more code than everyone else. That version of the idea was never useful to me. Writing more code is not the same as […]https://codeaholicguy.com/2026/05/13/the-new-10x-engineer-with-ai/
-
Your AI agent doesn’t need more context. It needs cleaner context: refreshed often, kept minimal, and not treated like memory. https://hackernoon.com/the-only-context-rule-your-ai-agents-actually-need #contextengineering