Skip to content
All tags

#context-engineering

24 posts
ai deep-dive

Letta and MemGPT Complete Guide: Memory Inside a Stateful Agent Runtime

Letta extends MemGPT's operating-system analogy but is not a standalone memory API. The runtime persists agent state, editable in-context blocks, conversation history, and external archival memory, while the model can actively curate memory through tools.

ai deep-dive

OpenViking: Agent Memory as a Virtual Filesystem

Volcano Engine's open-source OpenViking stores agent memory, knowledge, and skills as a viking:// virtual filesystem — browsable with ls, tree, and find. Three-tier loading (L0/L1/L2) averages just 550 tokens per retrieval, boosting LoCoMo memory accuracy from 24–57% to 80–83%.

ai debug

How to Write a Claude Code Skill That Doesn't Eat Context: Entry Point, Thresholds, Cost, Sources

I turned Anthropic's session-cost advice into a global skill, and the first version made the very mistakes it was meant to prevent: a description stuffed with trigger keywords, hard thresholds based on file counts and minutes, and 'protect the main context' conflated with 'spend fewer tokens overall'. Three rounds later the entry point is one page, details live in references, numeric thresholds became four judgment dimensions, and every claim from a draft post was checked against official docs.

ai deep-dive

Seven Answers to a Full Context Window, and No Consensus

Chroma's controlled study shows that even when it fits, a full context degrades performance. Coding agent vendors have landed on seven different responses: compact, hand off, prune, defer loading, isolate, train it into the model, or change the unit of work. Amp removed /compact outright, Atlassian argues summarization should be a last resort, and Cursor's A/B test measured a 46.9% token reduction. The three real disagreements come down to what each team is measuring.

How Ten Certifications Actually Test Prompting: Exam Framing vs. Practice

Most people assume GenAI certifications are built around prompt writing. CCAO-F gives Prompting 14% while Output Evaluation gets 21%; CCDV-F gives Prompt and Context Engineering 11.0%. What actually gets tested is structured output, injection-resistant prompting, dynamic context injection, context compression and caching, prompt lifecycle governance, and proving a prompt change helped — closer to context engineering and software engineering than to writing craft. None of the ten asks you to write a prompt on the spot; they are all multiple choice, so explaining why beats having a feel for it. The single most useful line comes from CCAR-F: when business logic must be guaranteed, 'change the prompt first' is usually the wrong answer.

AI Agent GitHub Digest — 2026-08-18

headroom compresses tool output, logs, and RAG chunks locally before sending them to the LLM, reaching 66K stars in 7 months. agentmemory gives Claude Code, Cursor, Codex CLI and a dozen other coding agents a shared cross-session memory store, hitting 27K stars in half a year. Andrew Ng's team releases OpenWorker, a desktop agent targeting knowledge workers beyond engineers. NVIDIA's labs-OO-Agents reimagines agent abstractions with object-oriented design. Mastra 1.59.0 renames CostGuardProcessor to TokenCostControl (breaking). browser-use 0.13.8 adds first-party OpenClaw skill support.

ai deep-dive

The 45 Rules of microsoft/AI-Engineering-Coach: An Opinion About Agentic Engineering, Written as Executable Thresholds

A VS Code extension open-sourced by Microsoft employees that reads your local Claude Code / Codex / OpenCode session logs. The real payload is 45 Markdown rules: prompts under 30 characters, sending the next message within 15 seconds of receiving 20 lines of AI code, instruction files over 4,000 bytes — turning 'context engineering' into numbers you can argue with.

CS146S Week 4: What Goes in CLAUDE.md, What Hooks Should Block, Where Subagents Cut

The course lists four techniques for directing agents: instruction files, hooks, commands, subagents. The instruction file is the only one loaded in full every startup, making it config rather than memory; hooks cover what instructions can't, because a rule can be ignored and a hook cannot; commands are the only one a human triggers. The course also marks just one and a half of seven task steps as human work.

CS146S Week 3: An Agent Skill Is a Folder — the Hard Part Is Two Lines of Description

The Agent Skills spec fits in a sentence: a directory containing a SKILL.md. The real design is three levels of progressive disclosure — only name and description load at startup, the body loads on a match, bundled files load on demand. This site's own repo carries 35 skills and 7,893 lines of SKILL.md, and startup still costs only those 35 metadata pairs.

CS146S Week 2: Context Engineering, RePPIT, and MCP's 98.7% Cut

Fall 2026 compresses a full week of prompting into one bullet here and adds RePPIT (Research, Propose, Plan, Implement, Test) and MCP. Two RePPIT rules are worth stealing outright: always ask for exactly two proposals, and never let the instance that wrote the code review it. On the MCP side, Anthropic measured turning tools into code calls dropping 150,000 tokens to 2,000.

Stanford CS146S, Two Syllabi Side by Side: What Changed in a Year

Stanford CS146S's Fall 2026 syllabus compresses prompting from a full week into a single bullet, drops the terminal and UI-generation weeks, and adds Agent Skills, Agent-Ready Codebases, Background Agents, and AI-Native Team. Grading moved too: the final project fell from 80% to 50%, with 30% now on open source contributions. This series reads all ten weeks.

Context and Memory: Where Agents Actually Fail

Chroma tested 18 frontier models and all of them degrade as input grows — as a cliff, not a slope. Memory failures are usually retrieval failures in disguise. And the real cost of KV cache is bandwidth, not storage: every generated token reads the whole cache.

ai deep-dive

How to Pick the Right Tool from Hundreds: The Collapse Curve of Tool Selection and Engineering Solutions

As tools scale up, selection accuracy doesn't degrade gracefully — it collapses: 4 to 51 tools drops from 43% to 2%, 10 to 100+ drops from 78% to 13.62%. The root fix is to stop stuffing everything in at once — Anthropic's Tool Search Tool uses defer loading plus retrieval to cut 85% of tokens, pushing Opus 4.5 accuracy from 79.5% to 88.1%. Description quality has conditional payoff: negligible in simple scenarios, but correctness jumps from 44% to 50% in multi-tool chaining.

ai deep-dive

CodeGraph: Local Code Knowledge Graph, and the Truth About 'Walking the Graph to Save Money'

CodeGraph uses tree-sitter to extract a codebase into a local SQLite/FTS5 knowledge graph, letting AI coding agents query the graph instead of scanning files. The official end-to-end benchmark (7 repos, median of 4 runs) averages 35% cost savings and 70% fewer tool calls -- but only if the agent actually walks the graph. Delegating exploration to a file-reading subagent that ignores CodeGraph turns it into pure overhead.

ai deep-dive

Code Mode: Moving Tool Definitions from Context into Code

Stop stuffing all your tool descriptions into context at session start. Let the model write code, have the runtime execute it, and let tool definitions enter context only at the import line — Anthropic's GDrive→Salesforce example dropped from ~150K tokens to 2K, and Cloudflare's 2,500-endpoint schema shrank from 1.17M to 1K.

ai deep-dive

Claude Skills: Package Domain Knowledge into a Folder, Teach Once and It Remembers

A Skill is a folder with a SKILL.md. Three-layer progressive disclosure lets Claude load details only when needed, eliminating the need to re-explain preferences every conversation.

The Memory Problem in Agentic Engineering: Types, Implementation, and Ownership

Agent memory isn't a plugin — it's part of the harness itself. Pick the right memory type, estimate data volume, then decide on the technology. And finally, figure out whether you actually own that memory.

product project

quidproquo Blog Improvement Roadmap: Content, Technical Debt, RAG Design, and Harness Infrastructure

Using my own 30+ RAG/Agent posts to audit the blog itself, I identified a prioritized improvement list spanning content quality, site tech, RAG design fixes, harness infrastructure, and AI agent applications — no phases, just priorities.

ai guide

How to Use Claude Code Agent Teams? Design Patterns from 6,400+ Agents on GitHub

There are already 6,400+ .claude/agents/*.md files on GitHub. We dissected 4 representative projects — ChemistryTimes (content production pipeline), claude-sub-agent (document-driven development pipeline), agentic (Temporal.io DAG parallel execution), and vs-copilot-multi-agent (hook-enforced memory persistence) — plus ruflo's enterprise-grade swarm architecture, distilling 6 design patterns and 5 practical trends.

The Complete Guide to Agent CLIs: Design Logic, Tool Comparison, and Best Practices

Agent CLIs are not smarter autocomplete tools -- they are AI agents that can read your codebase, execute multi-step tasks, and operate in real environments. Claude Code, Codex CLI, Gemini CLI, OpenCode, Aider, Pi, Kiro, Amp, Cursor CLI... the tools keep multiplying, but they all share a common set of design principles -- understanding these principles is how you actually get good at using them.

From Prompt to Harness: The Three Evolutions of AI Engineering

AI engineering has gone through three phases: Prompt Engineering (write better instructions) → Context Engineering (feed the right information) → Harness Engineering (design the entire working environment). Each evolution doesn't replace the previous one — it operates at a higher level of abstraction.

Context Engineering: Why Your AI Agent's Problem Is Information, Not the Model

Context Engineering is the core concept that replaced Prompt Engineering in 2025: the focus shifted from 'how to ask' to 'what information to provide.' Delivering the right information at the right time into the context window is more effective than upgrading to a stronger model. This post covers the definition, four key strategies, practical techniques, and common failure modes.

ai deep-dive

Complete Guide to AI Agent Architecture Patterns: From Three Pillars to Multi-Agent Systematic Navigation

AI Agent is not a single technology -- it is an entire architecture system. This article is a systematic navigation: starting from the Agent Three Pillars (Context/Cognition/Action), through the three-stage evolution of AI engineering (Prompt -> Context -> Harness), to eight Multi-Agent design patterns and production-grade Harness infrastructure. Each topic links to a dedicated deep-dive article.

ai guide

The Three Core Pillars of AI Agents: Context, Cognition, Action

An AI agent is not a black box — it is built from three layers: what it knows (Context), how it thinks (Cognition), and what it can do (Action). Understanding these three layers is the key to grasping why agents are sometimes brilliant and sometimes go off the rails, and how to design a truly effective agent system.