Tag: ai-workflow
All the articles with the tag "ai-workflow".
-
Precedents and Draft Slips: How to Turn Daily AI Decisions into a Simple Nod
Working with an AI assistant all day shouldn't drain your attention on tiny, repeated choices. Borrow common-law precedent and Ming dynasty draft slips so your AI logs past decisions and brings a recommendation every time it asks.
-
Why AI Writing Always Sounds Like a Machine: The Fix That Got It Right on the First Pass
Fed the exact same source material to write a video voiceover, the first AI draft was so defensive and preachy I rejected the whole batch. Changing how I briefed the task and switching writing models got it approved on the first pass in ninety seconds. Here is what changed—and four moves you can try right away.
-
Make Yourself a 'Human System Card': Have AI Read Your Personality Before It Talks to You
Have Claude read your past chat logs and write a 'human system card' covering your personality, decision logic, and communication preferences. Includes an excerpt of my own card and a four-step prompt to make yours.
-
A Weekly Checklist Run by AI Only Ever Grows, So I Added a Subtraction Step
When one person or a small team has an AI run routine work from a checklist, the list only grows. Why that happens, and the monthly subtraction review I added.
-
Turning Years of Teaching into a Knowledge Base AI Can Look Up: Catching AI's Fake Quotes with Code, and Settling My Own Contradictions
I gave AI over two hundred transcripts of recorded student interviews and had it build a teaching knowledge base it looks up when preparing lessons. The AI said every quote was exact; a small program found 6 of 44 did not match. This post covers how I caught the errors, how I settle it when my own advice contradicts itself, and a starter prompt you can paste straight to an AI.
-
Turning Lesson Transcripts into a Teaching Spec: One AI Drafts, Another Finds Faults, I Only Decide
My one-on-one lessons ran 51% over schedule. I went back to the lesson transcripts, had one AI write up my teaching rules and another hunt for faults, and only made decisions on a single checklist myself. The method, the numbers, what I actually told the AI, and a prompt you can paste.
-
I Built an Exam From My Own Chat Logs and Retake It With Every New Model
I turned the work I hand to AI every day into a private exam, then used it over three weeks on Claude at different effort levels, Gemini, Codex and open models. How the questions are made, how each round runs, how scores become routing rules, and prompts you can copy.
-
How a Teacher Gives Spoken Instructions to AI: Notes From 30 Classes and 751 Commands
I went through 30 transcripts of one-on-one and company classes plus 751 commands I typed to AI in my own work, to see how I actually open a request, steer midway and close it. Includes 8 original lines and a starter prompt you can paste to an AI.
- Updated:
Having Claude Dig Through a Month of My AI Chats: Habits, Mods, and Auto Mode Rules
I asked Claude Code to sift through over 300 chat logs from the past month to extract four collaboration habits, turn my most frequent catchphrases into switchable modes, and refine auto-review rules using real rejection cases.
-
Switching Your AI's Working Mode with One Command: Building work-mode and a Week of Testing
I built work-mode, a Claude Code plugin with autonomous, delegate and wrap-up modes plus desktop/phone reply formats. The pain points, how it evolved, numbers from 136 sessions, and prompts you can copy.
-
Measuring Again Three Months Later: From AI Adoption L2.5 to L3
In July I rated myself L2.5 on Boris's AI adoption table. Three months later I measured again: Claude can reach my knowledge base and old chats, code goes through Codex review first, schedules run everything, and 430 sessions in two weeks were started by code.
-
Burning and Saving AI Quota: How I Audited, Allocated, and Spent My Compute
An audit of seven AI quota pools: burning expiring credits on self-verifiable tasks while using surplus compute to build long-term token savings. Combines a terminal dashboard and routing scripts to dispatch tasks dynamically and refine rules from logs. Includes complete tables and reusable prompts.
-
I Had a Second AI Blind-Solve My Entire Question Bank
My question bank is AI-generated, so I did not let the same AI check it. A second AI re-solved every sampled question without seeing the answer key, and people judged whatever did not match.
-
I Asked My AI "Now What?" 41 Times in Two Weeks
Letting an AI run long jobs in the background is easy. Knowing where it got to when you come back is not. I counted two weeks of my own messages and found I was missing a status board, not more monitoring.
-
Read the System Card Before Managing a Model: Personalities and Playbooks for Opus, Sonnet, Haiku, and Fable
Read the personality evaluations in the system card before using a new model so you can manage it like a teammate. A breakdown of Opus, Sonnet, Haiku 5.5, and Fable 5.2—their workplace personas, dispatch logic, and concrete communication playbooks.
-
How I use herdr: three workspaces for standing, today and long-term
After Opus 5.5 analyzed 30 days of my session logs, I split herdr into standing, today and long-term workspaces. Four status lights keep the standing agent aware, and Opus can jump into the next pane to rescue a task.
-
Can Haiku 5.5 Take Over Sonnet's Work? I Tested It on My Own Tasks
Instead of official benchmarks, I built a test from 761 sub-agent jobs I actually delegated over 45 days. On seven checking tasks Haiku 5.5 matched Sonnet and Opus at about a tenth of the cost; long transcript extraction is still not complete enough.
-
Why GPT 6 Sol / Luna Feel So Dumb
A small job, transcribing consulting videos: the smart model builds a pipeline, the dumb one does every step by hand. After Opus 5.5 took over Codex's mess, it found four failure modes in 6 Sol / Luna, and why Cost per Task now needs a time variable.
-
Opus Commands, Sonnet Implements, Fable Advises: How I Split the Work Across Three Models
With Opus 5.5, Sonnet 5.5 and Fable 5.1 all out, my split is: Opus leads, verifies and deploys, Sonnet implements as a subagent, and Fable gets called in now and then as an advisor.
- Updated:
Do Not Grade AI by Its Own Summary
I hit the same failure in several forms this week: an agent denied changing files, a commit message overstated the diff, and a transcript reassigned a speaker ID halfway through. A later batch added checks that never ran and still reported clean.
-
Auditing Workflows After a Model Upgrade: How to Rethink and Trim Your AI Skills
When a smarter model lands, how should you prune the bloated skills written to babysit older ones? Through video editing and cross-language translation tests, here's how to run zero-skill baseline tests, cut obsolete guardrails, and turn core rules into clean specs.
- Updated:
Most of the Gains From AI Adoption Have Little to Do with AI
In practice, most of what an organization gains from adopting AI comes from fixing permissions, data governance, buy-in, and bloated processes along the way, not the AI itself.
-
Running 5+ Claude Code/Codex at Once: My Five Fixes for the Attention Bottleneck
Once I have more than 5 Claude Code/Codex windows going, I hit an attention bottleneck — constant context switching is genuinely exhausting. Five things that get me past it: a good multi-window manager, voice input, an overnight schedule, a reviewable skill, and regular pruning.
-
Before Career Coaching: Have AI Grill You First
Before meeting with a career coach or making a major move, have AI grill your updates into a focused cheat sheet. Let your coach target your blind spots during the session, then use AI to turn those takeaways into concrete next steps.
- Updated:
Letting an Agent Tune a Local Video Model Overnight: My Three Gates
Three things I learned from letting an agent run local video-model parameter research overnight: hard constraints in CLAUDE.md, a gate script watching SSD writes, and a 30-minute check-in loop.
- Updated:
When to Call In Fable: Three Moments, and Don't Turn On ultracode
The most expensive model is not meant to run the whole way. Three moments where calling in Fable feels right to me, plus why I cap Opus 5 at med, and the weekly cycle I fell into: efficiency king Monday to Thursday, Fable mode Friday to Sunday.
- Updated:
Why Obsidian is something special to me, and why I only made this video now
I'd been wanting to make this video for a long time, but kept putting it off. Obsidian's flexibility is so high that it grows into a different shape in every person's hands. The payoff isn't immediate either—it's only after the vault has grown for a while that you realize you can't go back.
-
Why Client Conversations Drift
Notes from a client diagnosis: three root causes, four prescriptions, plus the main/sub agent pairing run backwards and the rambling only a hook can cure.
- Updated:
My Client's Chat Blew Up: Three Questions in One Prompt, and Claude Just Drifted Along With Him
Asking about revenue, metrics, and decisions in a single prompt, or never persisting conclusions after brainstorming. Two real-world cases of client drift with AI, and the fieldwork of using /explain, /first-principles, Grill-me, and checkpoint to rein their workflows back in.
- Updated:
More Subagents Won't Make You Faster
From wanting 13 subagents to chat for me, to one person running 1000, to agents arguing across a table — the real bottleneck is the human main agent, and the fix is deduping before you dispatch.
- Updated:
AI Tool Philosophy — Pick a Mindset, Not a Side
After making nearly thirty tutorial videos: tools change, thinking doesn't. Don't dismiss others' tool choices. What matters is the orchestration logic — task decomposition, validation planning, responsibility assignment.
- Updated:
7 Practical Tips for Talking to Claude 5: Less Drift, Less Chatter, Less Slacking, Less Nagging
Some practical tips I have been sharing with friends lately on talking to the Claude 5 generation of models: a home-made explain skill for alien-speak, answering everything in one pass instead of letting the conversation drift, voice-input setups, first-principles pruning, a hook that treats slacking, a minimal CLAUDE.md, and a fix for the phantom pushback habit.
- Updated:
Two Worlds of Web-Based Claude Code Setup
Web Claude Code has two completely different runtimes — cloud VM and remote-control. Here is what I learned setting up both, the small bugs I hit, and why some user-level configs simply cannot be lifted to the cloud as-is.
- Updated:
The More Rules You Add, the Less Claude Listens: Trimming 36% of Baseline Context with an AI Fleet
Piling on rules makes LLMs miss what actually matters. When a 1M context window gets clogged with noise, you need an overhaul. Here is how an automated team of subagents trimmed my baseline harness by 36% by stripping out narrative fluff and conflicting constraints.
-
ABC Legal's Agent Fleet: Turning AI Experiments Into a Governed Production System
Six cards summarizing Anthropic's ABC Legal case study: 50+ production agents, agents managed as software in git, a steering committee with no software developers on it, and the principle that trust comes before automation.
-
Once It Ships, It's Gone: Three Times an Agent Misfired on an External System
Calendar invites, replies, and the internal notes on a hold event are all one-way doors. I got each of them wrong once this month, so here are the shapes of the accidents and the checks that catch them.
-
My Context Window Is More Fragile Than Today's Frontier Models: I Open-Sourced a Document Review SKILL
Working with an agent drains my attention, so I worked out a review loop: he writes the full proposal, I review it by voice, he revises, I go eat and exercise, then v2 shows up.
-
The Alignment Gap Is Closing. Next Comes Taste and Verification
The gap between AI and human intent is closing fast, so what separates good output moves toward taste and verification — and verification is where human responsibility stays.
-
Other People Fly to Korea for Cosmetic Surgery. I Had Codex Do Mine.
Someone on Twitter chained Codex, Hyperframes, IndexTTS2 and HeyGen into a one-person media pipeline. I pulled the repo, tried it, played with a local TTS model, then rebuilt a video days later on Claude Code.
-
Fewer Prompts Is Not Less Control
Claude 5 and GPT-5.6 official guidance is converging on the same thing — retiring old-style prompt stacking. But trimming is not letting go; control just moves. And the payoff of maintaining that layering is switching tools without losing a step.
-
Porting Old Prompts to Opus 5: A Nine-Card Migration Guide
Nine cards I made after reading Anthropic's official Opus 5 prompting guide: response length, agent narration, task boundaries, subagent delegation, self-correction, and what happens when you turn thinking off.
-
Two Voice Prompting Modes: Push-to-Talk for Chores, Long Audio for Deep Thinking
When working with Claude Code or Codex, use push-to-talk for quick prompts and full recordings for deep thinking. Here is a zero-setup browser trick and a headless CLI setup for agents to transcribe audio.
-
I'm Stuck at Stage 2.5 of AI Adoption
After watching Boris Cherny break down the stages of AI adoption, it hit home: I'm stuck at stage 2.5, where limited attention plus low trust becomes a vicious cycle. This week I used late-night schedules, a morning dashboard, and herdr auto-spawning sessions to cut a 4-5 hour workflow down to 1-2 hours.
-
Picking a Brand Look as a Non-Designer: AI Made Prototypes Cheap, So Taste Became the Hard Part
I am not a designer, but I spent this week iterating on a visual system for AgentCrew Academy with Fable, GPT-image-2, and GPT-5.6-sol. Here are the four rejected directions and the final spec applied to the website, slides, and documents.
-
Claude Code To-Do Tiering: Auto / Review / Collaborate / Manual
A small discovery from using Claude Code: sort to-dos by repo, then into four tiers — auto, review, collaborate, manual. Stuff that used to drag on all day now finishes in an hour.
-
A Proposal Is Not a Deployment: Why One Quick Win Sat Dead for Five Weeks
I had an SEO weekly report running on autopilot for five weeks, and one page's Quick Win just kept sitting there doing nothing. The root cause wasn't a wrong optimization — it was that the nice optimization proposal was never actually deployed.
-
The Blind Spot in AI Self-Verification — Why You Need an Uninformed Agent to Audit
AI is great at "looking done." To catch its blind spots, you can't rely on it checking its own work — you bring in an auditor that knows nothing, inherits no context, and gets only the rules and the output.
-
The Claude Code Ecosystem: Skills, Hooks, and Agents in Practice
Claude Code has grown well past a basic terminal CLI into a system powered by skills, hooks, and agent orchestration. Here is how those pieces connect to keep daily workflows dependable.
-
Turning Street Smarts into an AI Skill — When the Numbers Are Clear, You Stop Flinching
After turning Norm Brodsky's Street Smarts into a Claude Code Skill, every partnership opportunity gets a margin analysis first. Many appealing deals turn out to be money losers. When you know the numbers, you stop flinching.
-
Cross-Model Review: Stop Letting AI Grade Its Own Work
When an AI reviews its own output, blind spots are inevitable. Bringing in Codex for an independent pass or running a three-model expert panel with Review Council offers a practical fix.
-
Three moves to firepower-demo Agentic AI at your company—desktop cleanup, conflicting meeting notes, multi-version emails
If you want to make your manager or coworkers feel Agentic AI in one second—and then open the door to an internal training engagement—my three go-to moves are cleaning up messy desktops, reconciling conflicting meeting notes and emails, and producing multi-version drafts for different recipients. These three hit office workers right in the pain.
-
Covey's time management matrix, now with Claude Code—how each quadrant shifts
Covey's time management matrix from The 7 Habits of Highly Effective People splits time on two axes: important × urgent. Drop Claude Code into the picture and each quadrant's time allocation shifts. The long-term compounding from AI isn't in Q1, it's in Q2.
-
1M context isn't about holding more — it's about managing better
Claude Code's context window grew from 200k to 1M. The instinct is to put more in. That instinct is wrong. Five session management operations, four strategy rules, and the two most common ways to break your own context.
-
See the Outside, Think the Inside: Two Claude Skills That Pair
I saw a competitor selling well and my first reaction was anxiety. But before letting anxiety win, I wanted to actually understand what it was. Lately I have been pairing two Claude Skills for this — H/V analysis to see the outside, first-principles to see the inside.
-
My Claude Code Automation Stack: /loop, Monitor Tool, the Skill System, Obsidian Reflection Reviews
From /loop clocking in for me at ERP, to Monitor Tool as a background event gatekeeper, to Google Map MCP saving browser clicks, to Obsidian + Mirror framework for weekly reflection. Here's my six-month Claude Code automation stack, plus a clarification of how commands and skills actually split.
-
Six Months with Claude Code: From First Affection to Hesitation, From Overtime to Detox, From Mandarin Circles to the Thai Community
From January to April, my state of mind with Claude Code went from "that PTT-generation affection for the CLI" to "20x hesitation" to "AI detox" to "practicing Thai at a Bangkok meetup." Here's the six-month arc, along with the nights agents worked overtime for me until 5 AM.
-
Two Months of Claude Code Harness Ops: Crashes, Zombies, Cache Misses, and Plan Mode Edges
From March to April, running Claude Code as a long-running harness surfaced a bunch of issues. Survival tactics during the outage, my hook for cleaning up zombie processes, the silent memory bloat fixed in 2.1.86, the resume cache-miss fix in 2.1.90, and the Plan-Mode-question-density problem after 4.7.
-
Practical Claude Code Setup: Slimming CLAUDE.md, Quota Control, and Automated Workflows
When CLAUDE.md swells past a thousand lines, instructions get dropped, and rate limits hit within minutes, your harness needs an overhaul. A practical guide to splitting Rules, Memory, and Hooks, delegating to Haiku subagents, caching rules, Ghostty click fixes, and an automated video pipeline.
-
Mirror System: Weekly Reviews Without the Comfort
Normal weekly reviews let you make excuses for yourself. Mirror System doesn't offer reassurance — just feed your daily notes to Claude and watch it surface the patterns you've been avoiding.
-
Turning Books into Claude Skills: From Textbooks to Atomic Habits, the World Is Already On It
Turning books, frameworks, and methodologies into Claude Skills — making knowledge executable as interactive coaches. A roundup of popular examples and practical lessons.
-
My AI Workflow: Convergence and Divergence
Distilling my AI collaboration philosophy into two modes -- convergence and divergence. Plus how I build a personal knowledge base, and my day-to-day practice of running multiple agents in parallel.