~/beer-and-code
▪ Clã Beer and Code the largest AI Engineering community in Brazil · live, every week join the Clã ›
~ / tag / #contexto $ grep

#Contexto

9 posts
01 #ai-agents · #harness
Dreaming: what Anthropic found about AI agent memory (and what it changes in your harness)

Anthropic measured what actually works in AI agent memory: four layers, telling the agent what memory is for instead of rules, and dreaming, an offline step where the agent rereads transcripts and fixes its own memory. CL-Bench, Pokémon and wiki vs search numbers, plus Dreams API code and how to apply it in Claude Code.

11 Nov · 15 min ›
02 #laravel · #php
Filesystem as agent memory: progress file, feature list and git log in practice

An agent that runs across several context windows forgets everything each session. The pattern Anthropic, Manus and LangChain converged on: move state out of the window and into files. A JSON feature list that only accepts status changes, a progress log, a session start ritual and offloading large results with a restorable pointer, all with PHP code.

06 Nov · 5 min ›
03 #php · #ai-agents
Subagents: use them to isolate context, not to build an agent team

A subagent isn't a job title, it's a context window. When to use subagents (and when one agent is enough), the difference between isolated and fork modes, the numbers from Anthropic and Cognition, and how to implement both in a PHP harness straight on the Claude API, no framework.

06 Nov · 11 min ›
04 #ai-agents · #harness
Minimalist harness: why new models need fewer rules, fewer tools and less prompt

The harness that saved your agent last year is the one getting in its way now. Every model generation turns the previous harness's crutches into noise: ALL-CAPS rules, redundant tools, giant few-shot blocks, rigid orchestration. What the official Anthropic and OpenAI guides tell you to remove, Rich Sutton's lesson applied to harnesses, and how to prove with evals that removing things didn't make anything worse.

29 Oct · 14 min ›
05 #ai-agents · #produtividade
How to use skills in Claude Code: writing the SKILL.md and when it beats MCP and CLAUDE.md

Your CLAUDE.md is 400 lines long and Claude ignores half of it. A tutorial on how to use skills in Claude Code: folder structure, SKILL.md frontmatter, progressive loading, scripts and references inside the skill, how to test whether the agent triggers it, and the decision matrix between skill, MCP, CLAUDE.md, slash command and subagent. Built on the real skills that run this blog's pipeline.

28 Oct · 19 min ›
06 #claude · #contexto
Did Claude Opus 5 Get Worse? Better on Benchmarks, Worse to Live With

The threads say Claude Opus 5 regressed, and Google already answers yes. But the most likely explanation isn't a model nerf: Anthropic cut more than 80% of Claude Code's built-in system prompt for the Claude 5 generation. The restraint defaults are gone, and the responsibility moved to your CLAUDE.md. What you can measure, what's perception, and how to tame it without switching vendors.

01 Sep · 7 min ›
07 #ia · #llm
What Is an LLM: The Explanation for People Who Build, Not People Who Post

The operational fundamentals of LLMs with no parrot analogy: what the model does at each token, why it's stateless, how the context window degrades long before the limit, and why temperature 0 isn't deterministic. Each concept closes with the architectural consequence it forces you to build, with the official Anthropic and OpenAI docs, the Lost in the Middle paper, and Chroma's context rot study in hand.

31 Aug · 5 min ›
08 #ia · #arquitetura-de-software
Prompt engineering is over. What came next is called context engineering

Half the prompt techniques disappeared because the model learned them on its own. The other half became API parameters. What survived, what turned into folklore, and why in a real system the problem stopped being the sentence and became what goes into the context window.

31 Aug · 13 min ›
09 #cache · #contexto
How to Save Tokens in Claude Code, Codex, and Cursor: Stop Breaking the Cache

You send a one-line question and /usage reports a whole day's worth of consumption. Saving tokens in a coding assistant has nothing to do with prompt size: it's about prefix caching. How it works in Claude Code, Codex, and Cursor, the seven actions that invalidate it without you noticing, how to measure it with cache_read vs cache_creation, and eight levers to stretch the session.

06 Aug · 16 min ›
Meet the Clã Beer and Code
playing