Insights for AI builders
Tutorials, product updates, and ideas to help you build and ship AI applications faster.
Subscribe via RSS
Loop Engineering vs Prompt Engineering: What's the Difference and Which Do You Need?
Loop engineering replaces you as the person who prompts the agent. Learn how it differs from prompt engineering and when each approach makes sense.
Memarch vs Hermes vs GBrain: Which AI Memory System Should You Use?
Memarch offers semantic search, Hermes injects frozen snapshots, and GBrain cites sources with team scoping. Here's how to choose the right memory system.
Multi-Model AI Agent Councils: Do Multiple LLMs Give Better Answers Than One?
Running GPT, Claude, and Gemini in parallel with blind peer review and a chairman synthesizer can beat any single model—but only for the right tasks.
How to Use OpenRouter to Run GLM 5.2 in Claude Code for Cheaper Agentic Workflows
GLM 5.2 via OpenRouter costs $1.40 per million input tokens vs Claude Fable's $10. Here's how to set it up in Claude Code in under 5 minutes.
What Is the Pew Research AI Paradox? Why More People Use AI but Trust It Less
49% of US adults now use AI chatbots, up from 33% in 2024—yet more Americans predict AI will have a negative impact on society. Here's what the data shows.
How to Build a Production Error Sweep Loop: Nightly AI Bug Detection and Auto-Fix
A production error sweep loop reviews logs nightly, traces bugs to root causes, opens PRs, and pings you in Slack—all without manual intervention.
Prompt Bloat vs Skill Systems: Why Giant System Prompts Make AI Agents Worse
Stuffing every rule into a system prompt causes agents to lose focus. Learn how modular skill systems solve prompt bloat and reduce the re-explanation tax.
What Is Real-Time AI Video Generation? Happy Oyster and MaineCoon Explained
Happy Oyster and MaineCoon are real-time directable AI video generators that stream video as you prompt. Here's how they work and where they're headed.
Seedance 2.0 Mini vs Flagship: When to Use the Cheaper Model for AI Video
Seedance 2.0 Mini costs half as much as the flagship and works well for simple shots and prompt testing. Here's when to use each model in your video workflow.
What Is Semantic Memory Injection for AI Agents? The Frozen Snapshot Pattern
The frozen snapshot pattern injects a capped set of recent context into every agent session automatically. Here's how Hermes uses it and how to build your own.
What Is the Session-to-Skill Extractor? How to Turn Agent Conversations Into Reusable Procedures
The session-to-skill extractor reviews agent sessions for recurring non-obvious procedures worth preserving as skills. Here's how it works and when to use it.
What Is the Three-Layer AI Memory Architecture? Storage, Injection, and Recall Explained
Every AI memory system answers three questions: where to store, what to inject at session start, and how to recall by meaning. Here's how to design each layer.
What Is an Agentic Loop? How to Design AI Agents That Work Without You
An agentic loop is a trigger, action, and stop condition that lets AI agents work autonomously. Learn the core pattern and when to use it in your workflows.
What Is Sub-Quadratic Sparse Attention? How SubQ's 12M Token Context Works
SubQ's SSA architecture focuses attention only on relevant word relationships, cutting compute by 64x at 1M tokens. Here's what it means for AI agent workflows.
12 Million Token Context Windows: What SubQ Means for AI Agent Workflows
SubQ's 12M token context window lets agents process entire codebases, legal contracts, and financial filings at once—at 5% the cost of Claude Opus.
What Is the Harness Maintenance Checklist? 5 Questions to Ask Before Every Model Update
Before updating your AI agent's model, audit what it reads, what it can touch, what its job is, what proof it provides, and whether it still delivers value.
AI Agent Harness Maintenance: Why Agents Break When Models Get Better
Agents can fail not because the model degraded but because it improved. Learn why harness maintenance is the most underrated skill in agentic AI development.
How to Use AI for Deep Research Reports: Local Models, Web Search, and Visual Output
Tools like Odysseus can run multi-round deep research using local models and produce formatted HTML reports with table of contents—entirely offline.
How to Use Claude Code /goal and Auto Mode Together for Fully Autonomous Workflows
Combine Claude Code's Auto Mode and /goal command to run tasks end-to-end without approvals or early stops. Here's the setup and when to use it.
Claude Code Ultra Code Mode Explained: When to Use /effort Max vs Dynamic Workflows
Ultra Code spawns parallel sub-agents for massive tasks while /effort max deepens single-agent reasoning. Learn which to use and when for best results.
How to Build an Expert AI Coding Workflow: Skills, Automations, Loops, and Cloud Agents
Top agentic coders use skills, automations, loops, and cloud agents to ship code 24/7. Here's the full workflow from beginner prompting to expert automation.
How to Use GLM 5.2 in Claude Code: Cheaper Agentic Workflows Without Sacrificing Quality
GLM 5.2 plugs into Claude Code via OpenRouter or Z.AI, cutting costs 5x vs Opus. Here's how to set it up and when to use it over frontier models.
How to Use a Multi-Model AI Coding Workflow: Fable for Planning, Composer for Execution, GPT for Review
Using different models for planning, implementation, and review cuts costs and speeds up delivery. Here's how to build a multi-model skill in Claude Code.
How to Use Recraft V4.1 for Brand Design: Logos, Icons, and Editable Vector Assets
Recraft V4.1 Vector generates SVG files you can open in Figma or Illustrator. Here's how to use it for logos, icons, and brand identity work.