Working notes from a Claude-first practice.

mcpcomplianceclaude-codeworkflow

The Lethal Trifecta Has Three Legs. Least Privilege Covers One.

Least privilege shrinks your AI agent blast radius but leaves the egress and untrusted-input paths ungoverned. Here is how to close both gaps in production.

June 16, 2026 ·12 min read

claude-apiai-strategy

Model Availability Is a Production Dependency: Build the Fallback Ladder Before the Next Model Vanishes

Claude Fable 5 was pulled worldwide three days after launch. Model availability is a production dependency, not a vendor guarantee. Build the fallback ladder first.

June 15, 2026 ·7 min read

mcpcomplianceclaude-codeworkflow

MCP Authorization Scope: Least Privilege Before You Connect

MCP server permissions are an architecture decision, not connector plumbing. Scope your Jira, GitHub, and Confluence access before you connect, not after the incident.

June 14, 2026 ·12 min read

workflowclaude-codesubagents

When to Trust an LLM Judge (and When to Pull It Off the Gate)

Uncalibrated LLM-as-a-judge verdicts share the generator's blind spots. A practitioner's guide to judge failure modes, calibration, and when a judge earns gate authority.

June 13, 2026 ·13 min read

claude-codeleadershipworkflow

The Approval Budget: A Model for Spending Human Attention in Agentic Workflows

Approval fatigue in agentic AI turns every permission prompt into a rubber stamp. The fix is a budget: spend human attention where judgment is irreplaceable and push the rest into deterministic allow and deny layers.

June 12, 2026 ·15 min read

subagentscustom-skillstutorial

Claude Code Subagents vs Skills: One Teaches the Session, the Other Staffs It

Claude Code subagents vs skills is a context architecture decision, not a capability one. Learn when to define a .claude/agents file vs. a SKILL.md.

June 11, 2026 ·14 min read

subagentsclaude-codeworkflow

The Changelog Says 5 Levels. My Probe Went 9 Deep. Inside Claude Code's Nested Subagents.

Claude Code subagents can now spawn their own subagents. Here's what the depth limit actually does, what every delegation level costs, and the few trees worth growing.

June 11, 2026 ·14 min read

June 10, 2026 ·10 min read

Claude Fable 5's Silent Degradation: The Safety Tier You Couldn't See, Log, or Turn Off

Claude Fable 5 shipped a silent-degradation tier with no stop_reason, no notice, and no opt-out, then reversed it in 48 hours. A field map of the three safety tiers and what to instrument now.

June 9, 2026 ·10 min read

Claude Fable 5 Is 'Mostly Drop-In.' The Word Doing the Work Is 'Mostly.'

Migrating from Opus 4.8 to Claude Fable 5? Adaptive thinking costs, a new refusal API, and ZDR incompatibility mean it's not just a model-name swap.

complianceai-strategy

Claude Data Retention Isn't a Mystery. Your Approval Process Is.

Before your security review stalls: Claude's enterprise data retention policy, ZDR, SOC 2, and HIPAA commitments are all public. Four questions close it.

June 8, 2026 ·9 min read

hooksclaude-codeworkflow

Claude Code Hooks, Visualized: The Lifecycle Map, the Deny Gate, and the Enforcement Ladder

Claude Code hooks, visualized: the session lifecycle map, the PreToolUse allow/ask/deny gate, payload anatomy, and the enforcement ladder vs CLAUDE.md.

June 7, 2026 ·8 min read

June 6, 2026 ·12 min read

claude-codeworkflow

I Ran Seven Claude Code Sessions on One Repo. Three Spiraled. Git Worktrees Were Only Half the Fix.

Running parallel Claude Code sessions safely requires git worktrees, not just extra tabs. Here's the structural isolation model every practitioner needs.

claude-codeclaude-apiai-strategy

Opus 4.8 vs 4.7, One Week Later: The Upgrade Call I Couldn't Make on Day One

Opus 4.8 launched as the honesty release, then misreported its own tools in launch week. A week on: the changelog fix, whether the honesty held, and the 4.7 upgrade call.

June 5, 2026 ·6 min read

team-enablementroileadership

Is Your AI Rollout Actually Working? The Metrics That Matter at Month 3

AI coding tool adoption metrics that matter: why seat activation is a vanity metric, and what to measure at the three-month mark instead.

June 3, 2026 ·7 min read

June 2, 2026 ·14 min read

claude-codeworkflowroi

How to Control Claude Code Token Spend Without Sacrificing Output

Claude Code token optimization is a quality problem, not just a cost one. The structural levers that govern both: model and effort, the shape of your context, and how wide you fan out.

claude-codeworkflowclaude-api

How to Instrument Observability for Production Claude Agents

Agent View shipped this spring atop older CLI telemetry, and together they cover a lot. Here is the slice you still instrument yourself, and the principle that outlasts any dashboard.

June 1, 2026 ·12 min read

claude-codeclaude-apiai-strategy

Claude Opus 4.8 in Claude Code: I Couldn't Trust What It Said About Its Own Tools.

Opus 4.8 is the honesty release, but in my Claude Code loops I could not trust what it reported about its own tool calls. The measurement, the mechanism, and how to catch it.

May 31, 2026 ·12 min read

May 29, 2026 ·15 min read

I Read the Files Claude Code Wrote About Me: How Auto-Memory Actually Works

Claude Code auto-memory writes Markdown files about your project. Where they live, what triggers a save, and how to read, steer, and govern what Claude writes.

May 29, 2026 ·13 min read

The Most Important Number in Claude Opus 4.8 Isn't a Benchmark

Claude Opus 4.8's headline improvement is honesty, not raw capability. Why a model that flags its own uncertainty changes the economics of autonomous agents.

claude-codesubagentsworkflow

Claude Code Can Run a Thousand Subagents. The Verification Contract Is the Part You Design First.

Claude Code dynamic workflows fan out up to 1,000 subagents. At that scale no human reads every diff, so the verification contract is what you design first.

May 28, 2026 ·14 min read

claude-codeworkflowleadership

Claude Code in GitHub Actions: A Containment Checklist for CI Agents

Running Claude Code in GitHub Actions is a containment problem first. A production checklist for secrets, isolation, permission scoping, and merge ownership.

May 27, 2026 ·10 min read

May 26, 2026 ·12 min read

mcptutorialclaude-code

Build Your First MCP Server: The Hard Part Isn't the Code

Build your first MCP server step by step. Purpose-built beats a stretched connector, and tool-description design is where it counts.

claude-codesubagentsworkflow

When to Orchestrate Claude Code Subagents: A Four-Gate Decision Map

A visual decision guide to Claude Code subagent orchestration: the scope-of-work test, context blast radius, and write-safety gates that decide whether to split a task and which pattern to use.

May 24, 2026 ·6 min read

May 23, 2026 ·16 min read

Claude Code /advisor: When to Call It and Where It's Blind

Claude Code's /advisor sends your full conversation to Opus mid-task. After 159 calls in 17 days, here's the rule that beats the official guidance.

ai-strategyleadershiproiclaude-codecustom-skills

IDE-Optional Is Earned, Not Granted: Who Owns the Verification Loop

Gartner says enterprise AI coding agents make IDEs optional by 2027. That's the wrong headline. The decision that matters is who owns the verification loop.

May 22, 2026 ·12 min read

ai-strategyleadershiproi

The AI Productivity Paradox: What the 2026 Data Shows

The AI productivity paradox: why developers feel 20% faster but measure 19% slower, and the workflow layer that closes the gap.

May 20, 2026 ·6 min read

ai-strategyroileadershipgeo

GEO Is Two Jobs, and Your Marketing Team Can Only Do One

Most GEO advice sells schema and llms.txt. The evidence says they barely move AI citation. Here is the two-layer model, and the engineering layer marketing can't fix.

May 19, 2026 ·12 min read

claude-apiroiai-strategyclaude-code

Claude's New Agent SDK Credit Pool Isn't a Price Hike for Most of You

Anthropic's Claude Agent SDK credit pool is a budget signal, not a price hike. How to audit what your agent workloads burn and spend the new pool right.

May 18, 2026 ·6 min read

claude-codeworkflowleadership

Claude Code Can Auto-Fix Your Pull Requests Unattended. Who Owns the Review Bar Now?

Claude Code auto-fix watches your PR, fixes CI failures, and responds to review comments overnight. Here's what that means for your merge gate.

May 17, 2026 ·11 min read

roiai-strategy

The Seat License Is the Cheapest Part of Your AI Coding Tool

The true cost of AI coding tools in 2026 runs $150–250 per developer per month for full-time agentic work, not $20. The TCO breakdown leaders miss.

May 16, 2026 ·6 min read

May 16, 2026 ·15 min read

mcpclaude-codeworkflow

How to Audit an MCP Server Before Its Upstream API Breaks It

MCP servers are a maintained production surface, not one-time plumbing. A guide to security audits, token governance, and surviving upstream API deprecation.

ai-strategyteam-enablementworkflow

How to Train AI on Your Company's Knowledge: A Field Guide for Non-Engineers

Teach your AI how your best people decide, not just what documents say. A field guide to training AI on company knowledge across eight business roles.

May 14, 2026 ·13 min read

claude-codeclaude-apileadershipworkflow

What Does 'Critical' Actually Mean in an AI Code Review?

Review automation treats Claude's severity labels as absolutes. They're local ranks inside one context. A deep-dive on AI code review severity calibration and what to do about it.

May 14, 2026 ·13 min read

ai-strategyleadershipworkflowclaude-codeclaude-apisubagents

The AI Diligence Operating System: Schema First, Subagents Second

Before you hire a Claude architect for diligence, settle the AI diligence operating system question: memo schema first, subagents second. Here's why.

May 12, 2026 ·6 min read

Claude Code iPhone: The Practitioner Playbook for Shipping Without a Laptop

Claude Code on iPhone runs production-grade personal projects, if you stop fighting the workflow. A practitioner playbook for shipping without a laptop.

May 9, 2026 ·11 min read

claude-apiclaude-codeai-strategyroi

Claude Routing Has Two Knobs, Not One: A Model x Effort Matrix for 2026

Claude model selection guide: map every task to the right (model, effort) tuple. Fable 5 through Haiku, with the cost math and ZDR gate that make routing obvious.

May 8, 2026 ·9 min read

team-enablementworkflowuse-casescustom-skills

Stop Loading UX Research Reports Into Claude One at a Time. Build a Corpus Your Whole Team Can Query.

Most UX research repository AI setups fail because the structure blocks retrieval. Here's how research teams build a corpus any LLM can query on demand.

May 6, 2026 ·11 min read

ai-strategyleadershipteam-enablement

How to Re-Engage Engineers Who Already Tried AI and Wrote It Off

Burned engineers aren't your hardest re-engagement segment. They're your easiest. The recovery playbook for engineering leaders running a second AI rollout.

May 6, 2026 ·6 min read

claude-codetutorialai-strategysubagents

When to Reach for Claude Code's /batch (and When claude-squad, Agent Teams, or Superpowers Wins)

A reference for senior engineers deciding whether to adopt Claude Code's /batch command on real work. Mechanics, suitability criteria, anti-patterns, comparison against claude-squad, Agent Teams, the Anthropic Agent SDK, and Superpowers v5, plus the failure modes the launch announcement skipped.

May 4, 2026 ·9 min read

claude-codeteam-enablementleadership

How to Onboard Engineers to Unfamiliar Codebases in Week One With Claude Code

Claude Code codebase onboarding is ending the 30-day ramp. The bottleneck was never reading speed; it was senior-engineer translation capacity. Here is what changes when new engineers hold the tool, and where the new /team-onboarding command fits.

May 3, 2026 ·15 min read

claude-codeleadershipteam-enablementai-strategyhookscustom-skills

Half Your Team Is on Opus 4.6, Half Is on 4.7. The Problem Isn't the Model.

Half your team on Opus 4.6, half on 4.7? The issue isn't the model gap, it is CLAUDE.md drift. The EM's configuration audit guide for Claude Code teams.

May 2, 2026 ·13 min read

claude-codeworkflowleadershipteam-enablementtutorialhookscustom-skills

90 Minutes With 400 Engineers, PMs, and Ops on Claude Code: Here's What They Wanted to Know

Six questions kept recycling when I trained 400+ people on Claude Code. The taxonomy reveals more about rollout failure than the answers do.

May 2, 2026 ·14 min read

claude-codeai-strategyleadership

The AI Coding Spectrum: Vibe Coding, Agentic Development, and Who Owns the Verification Loop

AI Coding spans vibe coding to true agentic development. The diagnostic is who owns the verification loop, and the failure modes don't show up until production.

April 30, 2026 ·7 min read

claude-codetutorialworkflowcustom-skills

How to Create a Claude or Claude Code Skill: A Hands-On Guide for First-Timers and Optimizers

Skills feel like a mini-program in a new tech stack. They aren't. Here is how to create your first Claude or Claude Code skill, three creation paths from easiest to most rigorous, and how to make the same SKILL.md run in Codex, Cursor, and beyond.

April 29, 2026 ·16 min read

claude-codeclaude-apitutorialsubagentshookscustom-skills

The free Claude Code skill that audits your CLAUDE.md, hooks, and subagents for Opus 4.7 breaking changes

Your 4.6 CLAUDE.md looks fine. Opus 4.7's literal reading means it isn't. Free compatibility scanner audits hooks, settings.json, and subagents in minutes.

April 26, 2026 ·13 min read

claude-codeworkflowtutorialleadershiphookscustom-skills

Where Does That Rule Go? A Decision Tree for CLAUDE.md, Settings, Skills, and Hooks in Claude Code

Stop overloading CLAUDE.md. Learn when Claude Code directives belong in settings, rules, skills, or hooks. Includes a decision tree and worked examples.

April 26, 2026 ·10 min read

claude-designclaude-codeai-strategyleadership

Claude Design: The Handoff Is the Feature

Claude Design launched April 2026. Teams evaluating it as a Figma rival are missing the compounding benefit: the design-to-code handoff.

April 24, 2026 ·15 min read

claude-codeai-strategy

Opus 4.7 vs 4.6 in Claude Code: Where the Upgrade Shows Up, and When xhigh Is Worth the Tokens

Opus 4.7 changes how Claude Code behaves at every effort level. Here's when to use xhigh, when high is enough, and what the upgrade feels like from the CLI.

April 24, 2026 ·7 min read

claude-codeai-strategytutorialcustom-skills

Claude vs Claude Code: How to Pick the Right One (and When to Use Both)

Claude vs Claude Code: understand the core differences, when each tool is the right choice, and how the most effective users run both together.

April 20, 2026 ·15 min read

claude-codeclaude-apiworkflowsubagents

The Four Sub-Agent Orchestration Patterns That Cover 90% of Production Claude Workloads

Anthropic ships no canonical multi-agent reference architecture. Here are four Claude sub-agent orchestration patterns with production decision criteria, cost math, and failure modes.

April 18, 2026 ·17 min read

claude-apiclaude-codeai-strategyleadership

Claude Opus 4.7: Your Eval Harness Can't See What Just Changed

Claude Opus 4.7 improves long-horizon agentic work, but single-turn evals can't measure it. Rebuild your harness around traces, tool calls, and recovery.

April 17, 2026 ·22 min read

April 16, 2026 ·6 min read

Claude Opus 4.7 Is a Split, Not an Upgrade

Opus 4.7 vs Sonnet 4.6: Anthropic just split its lineup into agent operators and fast-turn assistants. Route them interchangeably and you'll pay for the mismatch.

Quick read

ai-strategyleadership

Stop Asking Which AI Tool to Buy. Ask This Instead.

95% of AI pilots fail. The reason isn't the tools. It's the question leaders ask before they buy. Here's the question that moves the needle.

April 16, 2026 ·4 min read

April 16, 2026 ·12 min read

claude-apiuse-cases

What 20-Turn Conversations Taught Me About the Claude API

Nine production Claude API agent patterns from running a 20-turn assessment tool. Effort tuning, dynamic prompts, confidence caps, and more the docs don't cover.

claude-codeleadershipteam-enablementhookscustom-skills

The Engineering Manager's Guide to Governing Agentic Development

Govern agentic development by encoding team standards into tooling, not mandating keystrokes. A framework for engineering managers adopting Claude Code at scale.

April 15, 2026 ·12 min read

April 15, 2026 ·14 min read

claude-apitutorial

Beyond the Wrapper: Five Claude API Patterns That Separate Prototypes from Production

Most Claude API integrations are wrappers around a string function. Five architectural patterns separate prototypes from production: here's how to ship them.

team-enablementai-strategy

Your Team Bought AI Licenses Three Months Ago. Why Aren't They Using Them?

AI adoption stalls after license purchase because teams default to training when they should be redesigning workflows. The research is clear on what works instead.

April 10, 2026 ·10 min read

April 9, 2026 ·7 min read

complianceai-strategy

The AI Compliance Stack: Five Layers Every Organization Faces in 2026

AI compliance requirements vary wildly by industry. This visual guide breaks down 2026 regulations for healthcare, fintech, and government with deadlines, costs, and a checklist.

claude-apiworkflow

Your Claude API Integration Is Probably a Wrapper Around a String Function

Most teams treat the Claude API as stateless text-in/text-out. The integration mistakes that follow cost money, add latency, and leave Claude's strongest features unused.

April 9, 2026 ·5 min read

April 8, 2026 ·12 min read

The Agentic Development Starter Guide: Plan, Audit, Implement, Verify

A practitioner's guide to agentic coding workflows. Learn the plan-audit-implement-verify cycle that separates disciplined AI development from vibe coding.

April 8, 2026 ·10 min read

ai-strategyroieducation

AI in the SDLC: What the Research Says About Shipping LMS Software Faster and Cheaper

Learn how AI-driven SDLC changes cut SaaS LMS development time by 30-50% and slash costs. A phase-by-phase guide with ROI data for edtech teams.

ai-strategyleadership

AI Is Not Taking Your Job. It's Rewriting the Job Description.

AI is reshaping the entry-level job market faster than anyone expected. Here is what is changing, which roles are most at risk, and five strategies new graduates can use to stay ahead.

April 5, 2026 ·5 min read

ai-strategyworkflowuse-cases

How to Turn Every Research Report into a Month of Social Content with AI

A step-by-step AI workflow for turning your research reports into LinkedIn posts, data visuals, and social content that positions you as a thought leader.

April 1, 2026 ·12 min read

April 1, 2026 ·5 min read

roiai-strategy

Is AI Worth It for Your Small Business?

Small businesses using AI save 5+ hours per week and cut costs by 20-30%. See where the savings come from, why most pilots fail, and how to start right.

ai-strategyleadership

The Three-Question Filter: A Framework for AI Tool Decisions

AI moves fast, but chasing every new tool costs more than falling behind. A practical framework to cut through AI FOMO and stay strategically focused.

April 1, 2026 ·6 min read

April 1, 2026 ·9 min read

ai-strategyworkflow

What Should a Solopreneur Automate With AI First?

Solo business, zero employees, endless tasks. Learn which AI workflows to set up first as a solopreneur, what to automate vs. keep human, and how to build a lean AI stack in 2026.

March 31, 2026 ·13 min read

ai-strategyuse-cases

AI Is Coming for Your Research Business. Here's How to Make It Work for You Instead.

The market research industry hit $153 billion in 2024. Independent researchers are losing share, not to better research, but to better visibility. Here's the playbook to fight back.

ai-strategyworkflowuse-cases

Running Post-Mortems on Disaster Scenarios with AI

Most post-mortem reports get filed and forgotten. AI changes the equation by reconstructing timelines, detecting cross-incident patterns, and turning years of incident data into strategic insights.

March 29, 2026 ·12 min read