How to Build an AI Agent Workflow That Produces Useful Work

    Start with the artifact, define the boundary, then add autonomy.

    Sep 5, 2026
    9 min
    44

    AI Agents for Business Operations: Start With a Verified Handoff

    A practical guide to choosing one bounded workflow, defining its evidence, and keeping a human in control.

    Sep 5, 2026
    9 min
    31

    AI Agent Examples: 7 Workflows That Produce Real Artifacts

    Seven operating workflows from my repository, with the artifact, verifier, failure state, and exact point where automation stops.

    Sep 5, 2026
    21 min
    47

    AI Agent Evaluation: How to Test Agent Skills

    A practical guide to cases, controls, graders and release gates

    Aug 18, 2026
    8 min
    93

    ChatGPT Work and Codex for Operators: 7 Workflows to Run This Week

    Practical workflows for founders, consultants, PMs, and operators after the July 2026 ChatGPT Work launch.

    Jul 10, 2026
    6 min
    110

    AI Content Repurposing: One Idea, Every Channel (2026)

    One source asset, a week of posts

    Jul 9, 2026
    11 min
    78

    The personal AI operating system (2026)

    The stack that runs your work

    Jul 7, 2026
    15 min
    696

    Claude Fable 5 Skills: Keep the Rigor After July 7

    6 free skills, blind-tested on Opus 4.8. Receipts included

    Jul 3, 2026
    8 min
    8,254

    Claude Code Skills by Fable 5: They Run in Codex Too

    The smart model writes. Your daily model keeps it.

    Jul 3, 2026
    9 min
    2,597

    Context Engineering Research: 2026 Papers and Benchmarks

    What ContextBench, SWE-contextbench, AGENTS.md, and long-context studies actually test.

    Jun 23, 2026
    11 min
    919

    Loop Engineering Is Easy. Deciding What "Done" Means Is the Whole Job.

    Prompt engineering taught us to ask. Context engineering taught us what to feed the model. Loop engineering is the next rung, and the hard part was never the loop. It is deciding what "done" means.

    Jun 16, 2026
    8 min
    163

    The Consultant's Moat Is Now a File

    Why the prompt isn't the unit of work anymore

    May 20, 2026
    8 min
    67

    Context Engineering Research: What I Found After You Shared That Paper

    A software engineer's memo on 20+ papers about AGENTS.md, context files, and AI agent productivity

    Feb 17, 2026
    5 min
    355

    Context Engineering with MCP: A Practitioner's Guide to the Model Context Protocol

    Five production patterns from running 12 MCP servers daily across 72 client deployments

    Feb 11, 2026
    11 min
    157

    From Prompt Engineer to Context Architect: The Job Nobody Trained You For

    The most valuable skill of 2026 isn't prompting—it's designing the information ecosystem around AI.

    Feb 1, 2026
    11 min
    246