AI engineering, in practice.

Technical guides for teams building reliable systems with language models and agents.

Browse all guides
A long token stream splitting into full-length and bounded rolling cache paths

Sliding-Window Prefix Caches Need Physical Proof

Compare the agent ecosystem

Explore actively maintained frameworks, their focus areas, and the signals behind their adoption.

LLM Framework Leaderboard

DynamiqDynamiq
1k+
Cloudflare AI SDKCloudflare AI SDK
1k+
mirascopemirascope
2k+
SymbolicAISymbolicAI
2k+
AgentStackAgentStack
2k+

Latest writing

Notes, comparisons, and implementation guides for building AI-powered software.

View all
Branching speculative paths meeting a luminous commit boundary

Speculative Agents Need a Commit Boundary

Speculative execution cuts agent latency only when prediction and commitment are separate operations.

Read

Abstract interlocking loops for harness engineering

Loop / Harness Engineering

Agent loops turn prompts into one part of a production harness: tools, state, checks, approvals, and exit conditions.

Read

Plain-Text Context Files for LLMs

Plain-Text Context Files for LLMs

Plain-text context files are the git-native, zero-ops way to steer AI agents.

Read

How to Build an MCP Server

How to Build an MCP Server

A guide to building an MCP server for Markdown note taking

Read