Skip to main content
Watch: Grok Bot Built My AI Video Arena While I Tested 8 Models

ARCHITECTURE

10 items

10 posts

Blog
DeepSeek Super-Agent: The Always-On Router and Worker Design

DeepSeek open-sourced dsh-superagent, an always-on coding agent built on a router and worker split. What the design says, what the code ships, and the safety debate.

Blog
How OpenAI Built GPT-Live: Full-Duplex Voice, WARP, and the Death of the Turn Detector

How OpenAI built GPT-Live: a full-duplex voice model with no turn detector, Go on the media path, stateful handoffs, and the new WARP WebRTC transport.

Blog
MCP vs Agent Skills: When to Use Which (and Why You Need Both)

MCP vs Agent Skills: MCP gives agents live access to tools and data, Skills give them packaged procedure. The decision rule for when to use which, or both.

Blog
The Log Is the Agent: Event Sourcing Comes to AI Systems

Event sourcing for AI agents: a new paper makes the append-only log the source of truth for agent state. What it enables, and whether HN thinks it is just CQRS.

Blog
There Are No Instances in ATProto - Dan Abramov Explains the Architecture

There are no instances in ATProto: Dan Abramov explains how Bluesky's protocol separates hosting from apps, what Hacker News pushed back on, and why it matters.

Blog
Agent Architecture: Building Multi-Step AI Workflows That Survive Production

Agent architecture for multi-step Claude workflows: loop patterns, state management, error recovery, and the production gotchas that break agents at scale.

Blog
The Agent Reliability Cliff: Why Your 10-Step Chain Only Succeeds 20% of the Time

The agent reliability cliff: 85% per-step success compounds to about 20% over 10 steps. Why long chains collapse, and six patterns that fight the decay.

Blog
Intent Debt: The AI-Era Debt Nobody Is Tracking

Intent debt is the third layer of AI-era debt Martin Fowler describes, after technical and cognitive debt. What it is and how to diagnose it in your project.

Blog
7 AI Agent Orchestration Patterns Developers Should Know

Seven AI agent orchestration patterns for production, from single-agent baselines to multi-level hierarchies, each with a decision rule, sketch and tradeoffs.

Blog
Progressive Disclosure: How Claude Code Cut Token Usage by 98%

Progressive disclosure lets agents load tools only when needed. How Cloudflare, Anthropic and Cursor cut token usage, and how to do it in Claude Code.

AI Development Stack

Get Smarter About AI Dev

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.

One email per weekReal code, not theoryFree forever