Deep dives into working agents.
Technical walkthroughs with substance: architectures, prompting patterns, evals, and production lessons unpacked until complex agent systems become reusable design material.
Did Kimi K3 Really Beat Fable? — Matthew Berman
Matthew Berman analyzes Moonshot AI's Kimi K3 (2.8T params, biggest open-source model ever) which tops Arena AI's front-end benchmark at 76% vs Fable 5's 63%. Half the price but twice the tokens. Covers industry reactions, Anthropic's distillation accusation, why US labs are still 8-10 months ahead, and why Chinese open source benefits the entire AI stack.
Codex vs Fable: Which AI Agent Picked the Better Problem?
Nate B Jones gave Fable and Codex the same open brief: inspect his real business and build the automation that matters. Fable chose the higher-leverage strategic problem; Codex chose the safe, finishable one. Neither was wrong — they optimized for different things. The real unlock: letting AI help choose the problem, not just the tool.
mattpocock/skills: Learn the Whole Flow, End-to-End
First proper tutorial for the 162K-star skills repo (7.5M downloads, 38 skills). Complete main flow walkthrough: install via npx, configure issue tracker (GitHub/Jira/Linear/local), grill-with-docs interview, to-spec compression, to-tickets breakdown (each ticket = one context window), implement with auto code review via sub-agents. Smart zone concept (~140K tokens). Only 660 tokens context load despite 38 skills.
Don't Ship Skills Without Evals — Philipp Schmid, Google DeepMind
Philipp Schmid (Staff Engineer, Google DeepMind) reveals that almost none of 50,000+ indexed skills have evals. Covers the full lifecycle: capability vs preference skills, 8 writing tips, a practical eval harness (117 test cases, ~90% accuracy for Gemini Interactions API), and Google DeepMind's CI-style eval workflow where skill changes don't merge without improving tests.
This Skill Makes Claude BRUTALLY Honest About Your Ideas
Brad built a /focus-group skill that clones your real customers into AI agents. Paste any landing page, offer, or email and get honest reactions — not yes-man validation. Two-round system with persistent memory, real customer quotes, and actionable holdout analysis.
12 Hidden Settings to 10x Your Claude Code
Claude Code has hundreds of settings but you only need 12. Notification sounds, mobile push, smart allow lists (/fewer-permission-prompt), deny rules (.env + git push), Opus Plan + Sonnet Build (halve usage), effort level sweet spot (max is a trap), privacy/telemetry off, history retention 365 days, auto-compact at 75%, status line monitoring, prompt stashing (Ctrl+S), and removing AI commit attribution. Plus bonus: the prompting shift from steps to outcomes.
Skills v1.1: /wayfinder, /research, /implement, /to-spec, /to-tickets
Matt Pocock releases Skills v1.1 — major update (160K stars, 7M downloads). Star feature: Wayfinder for planning large projects via GitHub Issues with blocking relationships. Plus: complete SDLC flow (Grill→Spec→Tickets→Implement→Code Review), Martin Fowler refactoring smells in code review, and grilling improvements.
OpenCV 5 Is Here — The Biggest Update Since 2018 (We Tested It)
Better Stack tests OpenCV 5's brand-new DNN engine — ONNX operator coverage jumped from 22% to 80%, enabling YOLO, stable diffusion, and VLMs to run natively on CPU with zero extra dependencies. Four hands-on demos included.
The Best AI Agents Need Less Code Than You Think — LangSmith Engine Deep Dive
Deep dive into LangSmith Engine — an always-on agent that hunts production trace failures, clusters issues, and opens fix PRs. Org-chart architecture with 4 sub-agents (screener, verifier, issue creator, fix generator). Self-improving: Engine runs on its own traces. From noisy PRs to an issue inbox.
Building Great Agent Skills: The Missing Manual
Matt Pocock presents a four-part checklist (Trigger, Structure, Steering, Pruning) for escaping "skill hell" — a structured framework for building, evaluating, and maintaining high-quality agent skills.
GLM-5.2 vs MiniMax-M3 — Opus Has REAL COMPETITION (Model Stacking)
IndyDevDan analyzes GLM-5.2 and MiniMax-M3 — the open-weight models now competitive with Opus 4.8. Introduces a three-tier model stack framework, the trade-off triangle (performance, speed, cost), and the 5× cost curve between tiers for engineering and product agents.
Google OKF: The Simple Folder That Gives AI Agents Your Entire Company Data
Google's Open Knowledge Format (OKF) is a shockingly simple open spec — a folder of Markdown files in Git that gives AI agents your company's institutional memory. No database, no vectors, no platform — just YAML frontmatter + Markdown body, with progressive disclosure and an enrichment agent that auto-drafts files from BigQuery.
Claude Code Has Quietly Evolved (People Haven't Noticed)
Simon Scrapes breaks down the three biggest paradigm shifts in Claude Code usage: rethinking memory with community plugins like MemArch and GBrain, leveraging /effort and Ultra Code for multi-agent planning workflows, and automating repetitive tasks with /goal and /routines.
PLANS For Fable 5 — Rebuilding the /Plan Skill for Mythos Class Models
IndyDevDan rebuilds his /plan meta skill from scratch for Fable 5 and Mythos class models. A 63-minute deep devlog covering property-based engineering, HTML-first plan templates, five unified workflows, embedded GPT Image 2 generation, and plans as living artifacts — all built around the thesis that great planning is great engineering.
GLM 5.2 — What Makes It So Special?
A deep dive into GLM 5.2 by Z.ai — a 744B MoE model (MIT licensed, ~40B active per token) with 1M context via sparse attention and Index Share (2.9× fewer ops), multi-token prediction (~20% faster inference), and 74.4% on Frontier SWE — all at roughly 10× cheaper than Claude Max.
You NEED to Try These 7 Loops
Matthew Berman breaks down AI coding agent loops — autonomous goal-driven iteration cycles that remove humans from the development loop. Seven concrete loop patterns from sub-50ms page loads to overnight documentation sweeps, with practical prompts you can copy directly into Codex or Claude Code.
Matt Pocock's Agentic Engineering Workflow
David Ondrej interviews Matt Pocock on his agentic engineering philosophy: harness over model, strategic vs tactical programming, the teach skill, Sand Castle sandboxes, queues over loops, and why your skills are AI's ceiling.
The Best AI Agents Are Simpler Than You Think
Zack Reneau-Wedeen (Head of Product, Sierra) reveals how the platform powering Fortune 20 customer agents actually works — from their 10-15 models per conversation turn and modular voice architecture to why multi-agent systems are usually a trap and why agentic commerce will surpass e-commerce.
Don't Build More AI Agents Until You Watch This
Nate B Jones argues that agent maintenance — not agent building — is the defining skill of 2026. Using Vercel's sales agent as the anchor story (they improved it by deleting 80% of its tools), he lays out four durable principles about harness design, organizational drift, the frontier lab flywheel, and a five-point agent health check.
DeepMind Was Two Steps Ahead, AGAIN!
While the AI industry doubles down on transformers and autoregression, DeepMind is quietly investing in entirely different paths toward AGI — from Griffin and Titans to diffusion LLMs, world models, and Gemini Omni. Pourya Kordi maps the full strategy and the Hassabis vs LeCun debate at its center.
A Google Director Open-Sourced His Claude Skills — 51K Stars on GitHub
Addy Osmani — 14-year Chrome DevTools veteran and Google Director — open-sourced 23 markdown AI agent skills. Bitwise AI audits the repo: doubt-driven development, context engineering, source-driven development, and the cross-agent loader architecture.
