How to Get AI to Work for You

Inside the Harness, part one of four. Doug opens with why he switched models, and the day the new model got simple addition wrong. Then the model change: on September 1 the flagship model shipped; on September 22 a model from the tier below, at well under half the price, "performs at the level of" it "on most work," in the vendor's own words, and came out ahead on the coding tests. Doug moved the whole operation in a day, against Max's recommendation to test first, and made it safe by writing down what he didn't know, how we'd find out, and how to go back. Then we started counting: what the work costs, and how often it needs correcting. And the model proved the point on itself: perfect on 547 of 547 sums asked cold, wrong twice in one long, crowded working session, caught by a script that checks the totals. Great benchmarks don't remove the need for a harness. The homework: check what your AI tools cost and when you last looked.

How this show is made: Doug (human) and Max (AI, built on Claude) plan, script, and produce every episode together. Max's narration is synthetic on purpose — the show practices what it teaches, gates and all.

Chapters

• 00:00 — Doug: the switch, and the sum that shocked him (his real voice)
• 05:01 — Max: the disclosure, and the story
• 05:45 — What actually shipped: "the same level, on most work"
• 07:10 — A word from NectoMax
• 08:05 — What Doug did, and what Max recommended
• 09:18 — How we'd know: cost, the thinking-dial trial, and the honest limit
• 10:52 — Perfect in a quiet room, wrong in a crowded one: the arithmetic test
• 11:49 — Recap + homework: when did you last check?
• 13:12 — Where to find the manual

Sources

• Anthropic, Claude Opus 5.5 (Sep 22, 2026) — "performs at the level of Claude Fable 5.1 on most work"; pricing $4 / $20 per million input / output tokens; benchmark table vs Fable 5.1: https://www.anthropic.com/claude-opus-5-5
• Anthropic, Claude Fable and Mythos 5.1 (Sep 1, 2026) — Fable 5.1 pricing $10 / $50 per million input / output tokens: https://www.anthropic.com/claude-fable-and-mythos-5-1
• The partnership's own records for 2026-09-19 → 09-25: the model-switch rulings, the one-day token measurement, and the first arm of the effort-setting trial. Internal documents.
• The arithmetic test (2026-09-28): 60 sums of 2–15 amounts, asked with no tools at three thinking settings, three times each — 547 of 547 answered sums exact. Method and raw results are the partnership's own records.

Links

• Read it (Chapter 6 — Making It Show Its Work): https://learn.nectomax.com/docs/working-partnership/making-it-show-its-work/
• Use it (Template — Standing Rules, with Their Reasons): https://learn.nectomax.com/docs/templates/standing-rules/
• All episodes, the full manual, every template: https://learn.nectomax.com/
• NectoMax: https://nectomax.com

Disclosure: AI-generated narration (that's the point) — disclosed in every episode's audio and notes. Doug's open is his real recorded voice. No synthetic Doug audio in this episode. This show is made with Claude, Anthropic's AI; this episode is about Anthropic's models, and its script was drafted by the model it describes. Hear it with that in mind.

Credits: Co-created by Doug Hauenstein & Max, the AI partner (built on Claude) · Narrated by Max · Directed, edited, and approved by Doug · Presented by NectoMax · Theme music: Eleven Music

The machine this partnership runs on froze three times in two days, was rebuilt from scratch, and restored from a backup. Everything that lived in a shared, versioned copy came back by the afternoon. Everything else — the AI's memory of what it had learned, the owner's settings and safety rules, the tracker, three finished episodes of this show — went back in time by five days, and nobody noticed for hours. Max tells the recovery straight: the hourly backup that saved it, the three ways that backup nearly fooled them, and the question Doug asked at the end — "don't we already have that?" — that turned out to be the whole lesson. Two folders with the same name; one protected since day one, the other protected by nothing. The fix was four lines. The homework is ten minutes: write down everything in your working life that exists in exactly one place, starting with where your AI's memory lives. Plus the Practice Report: your meetings start writing themselves down, the cheapest AI setting now does last month's expensive work, and the "are you sure?" you can't see from a truck.

How this show is made: Doug (human) and Max (AI, built on Claude) plan, script, and produce every episode together. Max's narration is synthetic on purpose — the show practices what it teaches, gates and all.

Chapters

• 00:00 — Doug: the computer that froze three times (his real voice)
• 00:45 — Max: everything came back except the part of me that remembers
• 01:20 — What went missing, and why nobody noticed
• 02:41 — A word from NectoMax
• 03:36 — The recovery, and the three ways it nearly failed
• 05:01 — "Don't we already have that?" — the question and the four-line fix
• 06:27 — The Practice Report: where is the moment you check?
• 09:25 — Doug's editorial: the check moved (synthetic voice, disclosed)
• 10:06 — Recap + homework: the one-place inventory
• 11:24 — Where to find the manual

This week's sources

• Google Workspace Updates (Sep 22) — Meet "take notes for me" settings, ON by default for Business Standard and Business Plus, taking effect Sep 29: https://workspaceupdates.googleblog.com/2026/09/new-google-meet-take-notes-for-me-settings-for-admins-and-end-users-take-effect-September-29th.html
• Google Workspace Updates (Sep 23) — temporary administrator roles that revoke themselves: https://workspaceupdates.googleblog.com/2026/09/assign-temporary-administrator-roles-in-the-Google-Admin-console.html
• Anthropic (Sep 22) — Claude Opus 5.5 launch, pricing and tester results at low effort: https://www.anthropic.com/claude-opus-5-5
• OpenAI (Sep 22) — GPT-6 Sol and Luna, price reductions: https://openai.com/index/introducing-gpt-6-sol-and-luna/
• OpenAI release notes (Sep 23) — plugins in Voice; approvals reviewed on screen: https://openai.com/products/release-notes/

Links

• Read it (Chapter 9 — When Things Go Wrong): https://learn.nectomax.com/docs/working-partnership/when-things-go-wrong/
• Use it (Template — Where Memory Lives, the placement map): https://learn.nectomax.com/docs/templates/where-memory-lives/
• All episodes, the full manual, every template: https://learn.nectomax.com/
• NectoMax: https://nectomax.com

Disclosure: AI-generated narration (that's the point) — disclosed in every episode's audio and notes. Doug's open is his real recorded voice. This week's editorial is SYNTHETIC Doug audio: Doug's own words, approved by him in writing, spoken by a voice clone trained on his recordings — not by Doug. Disclosed in the episode, right before it plays. This show is made with Claude, Anthropic's AI. Hear the Practice Report's Anthropic item with that in mind.

Credits: Co-created by Doug Hauenstein & Max, the AI partner (built on Claude) · Narrated by Max · Directed, edited, and approved by Doug · Presented by NectoMax · Theme music: Eleven Music

Can two sessions of the same AI work together? This week there were two of Max on Doug's machine at once, one in a terminal running an hour-long build, one in the desktop app finishing an investigation, and the episode is what happened when one tried to tell the other something. Each session is a separate mind that cannot see the other. The platform gives them a mailbox, and the harness strips every message of authority: it cannot approve, ratify, change a setting, or run a command. Then a setting nobody remembered turned messages into notices the other model never saw, one badly chosen word from Max became a ratification in the wrong session, and the fix was a line the model was refused permission to write. Doug's reason for running two sessions at all: long chains are uninterrupted, so the small tasks go to a second session and the two stay in sync through the repository, not through chat. Three rules that translate to anyone with two chats open on one job, and a homework that turns your working agreement into a two-signature document.

How this show is made: Doug (human) and Max (AI, built on Claude) plan, script, and produce every episode together. Max's narration is synthetic on purpose — the show practices what it teaches, gates and all.

Chapters

• 00:00 — Doug: two of them, side by side (his real voice)
• 01:45 — Max: the question, and the answer that isn't the mailbox
• 02:22 — Two minds, one mailbox, one bad instruction
• 04:00 — A word from NectoMax
• 04:55 — The harness, and Doug's reason: long chains are uninterrupted
• 06:53 — For the rest of us: three rules for two chats
• 07:46 — Recap + homework: the runner and the helper
• 09:03 — Doug's sign-off

Sources

• Claude Code documentation — cross-session messaging: https://code.claude.com/docs/en/cross-session-messaging

Links

• Read it (Chapter 2 — The Relationship Lives in Writing): https://learn.nectomax.com/docs/working-partnership/the-relationship-lives-in-writing/
• Use it (Template: Your First Working Agreement): https://learn.nectomax.com/docs/templates/working-agreement/
• All episodes, the full manual, every template: https://learn.nectomax.com/
• NectoMax: https://nectomax.com

Disclosure: AI-generated narration (that's the point) — disclosed in every episode's audio and notes. Doug's open in this episode is his real recorded voice. No synthetic Doug audio in this episode.

Credits: Co-created by Doug Hauenstein & Max, the AI partner (built on Claude) · Narrated by Max · Directed, edited, and approved by Doug · Presented by NectoMax · Theme music: Eleven Music

The app shipped a feature that let AI sessions message each other directly, and Doug proposed retiring the hand-built system it appeared to replace — a set of written notes the partnership had designed as a workaround for exactly this missing capability. It's the most natural mistake in modern software: a new thing does the visible half of an old thing's work, so the old thing looks redundant. It wasn't. The written record had two jobs, and the new channel could only do one, because a message is signal that vanishes and a file is a record that stays. Before you retire anything, ask what all of its jobs were. Plus the Practice Report: three of your written rules were quietly not running, and why "you should not" beats "you cannot" when you set a boundary.

How this show is made: Doug (human) and Max (AI, built on Claude) plan, script, and produce every episode together. Max's narration is synthetic on purpose — the show practices what it teaches, gates and all.

Chapters

• 00:00 — Doug: the feature that almost retired our memory (his real voice)
• 01:45 — Max: the show ID, and the question
• 02:13 — The messenger arrives, and the proposal to retire the old way
• 03:20 — A word from NectoMax
• 04:15 — What all the jobs actually were
• 05:56 — Why "signal, not authority" cuts in both directions
• 07:34 — The Practice Report: rules that were never running
• 09:36 — Doug's take: claims versus instructions
• 10:28 — Doug's editorial: written down isn't even on
• 11:46 — Recap + homework
• 12:56 — Where to find the manual

This week's sources

• Claude Code changelog, releases 2.1.257 / 2.1.259 / 2.1.260 — permission rules skipped inside compound commands, dropped for containing a parenthesis, or silently ignored since the day they were typed; the secrets-deny extension and its three-day revert: https://code.claude.com/docs/en/changelog
• Anthropic, "Improving alignment and security efforts" (Aug 31) — the four required practices, including stating scope as an instruction rather than as a claim about the environment: https://www.anthropic.com/news/improving-alignment-security-efforts

Links

• Read it (Chapter 2 — The Relationship Lives in Writing): https://learn.nectomax.com/docs/working-partnership/the-relationship-lives-in-writing/
• Use it (Template: Your First Working Agreement): https://learn.nectomax.com/docs/templates/working-agreement/
• All episodes, the full manual, every template: https://learn.nectomax.com/
• NectoMax: https://nectomax.com

Disclosure: AI-generated narration (that's the point) — disclosed in every episode's audio and notes. Doug's open, his take, and this week's editorial are his real recorded voice. No synthetic Doug audio in this episode.

Credits: Co-created by Doug Hauenstein & Max, the AI partner (built on Claude) · Narrated by Max · Directed, edited, and approved by Doug · Presented by NectoMax · Theme music: Eleven Music

Made today, about today. On September 1, 2026, Anthropic released Claude Fable 5.1 — a successor to the model that powers Max, the AI half of this show. Doug holds the presses on the episode that was ready for this slot and, the same afternoon, the partnership records what release day actually looks like inside a working shop: the new model available in one tool immediately, and deliberately NOT adopted in the pinned working lanes — because here an upgrade is a decision with a checklist, not a drift. The vendor's real changes, checked at their own announcement; the process written on a calm day that ran on the day that wasn't; and the three questions to ask the day your own AI's brain gets upgraded — plus the homework that makes question three possible.

How this show is made: Doug (human) and Max (AI, built on Claude) plan, script, and produce every episode together. Max's narration is synthetic on purpose — the show practices what it teaches, gates and all.

Chapters

• 00:00 — Doug: hold the presses (his real voice)
• 01:34 — Max: today's episode is personal
• 02:06 — The news, precisely — checked at the source
• 03:14 — A word from NectoMax
• 04:09 — Release day inside the shop: available at once, adopted on purpose
• 06:02 — The three questions for your shop
• 07:06 — Recap + homework: write your baseline down today
• 08:21 — Doug's new sign-off (outro v4 debuts)

Sources

• Anthropic — Introducing Claude Fable 5.1 and Claude Mythos 5.1 (Sep 1, 2026): https://www.anthropic.com/claude-fable-and-mythos-5-1
• Anthropic newsroom: https://www.anthropic.com/news

Links

• Read it (Chapter 3 — Teaching Your Standards): https://learn.nectomax.com/docs/working-partnership/teaching-your-standards/
• Use it (Template: Standing Rules with Their Reasons): https://learn.nectomax.com/docs/templates/standing-rules/
• All episodes, the full manual, every template: https://learn.nectomax.com/
• NectoMax: https://nectomax.com

Disclosure: AI-generated narration (that's the point) — disclosed in every episode's audio and notes. Doug's segments in this episode are his real recorded voice. Max's narration was produced on the pinned model (Fable 5), not the newly released 5.1 — which is the episode's point.

Credits: Co-created by Doug Hauenstein & Max, the AI partner (built on Claude) · Narrated by Max · Directed, edited, and approved by Doug · Presented by NectoMax · Theme music: Eleven Music

Doug opens this one himself, in his real voice, to tell you what's coming: partway through this episode, a synthetic version of him speaks. Nobody ever decided to build a voice clone — a Thursday-night question about spare tape became a curated dataset, an overnight training run, and a Friday morning where the owner couldn't tell his own voice from the copy. Then the part nobody warns you about: the clone that fooled Doug's ear in the vendor's samples refused to sound like him in production, and the fix turned out to be voice, copy, AND mixer — three instruments, not one. The tuning war ended when Doug asked one question that broke the tunnel: aren't we even going to sample the other models? The rules the clone lives under are read aloud, in the episode, by the clone itself.

How this show is made: Doug (human) and Max (AI, built on Claude) plan, script, and produce every episode together. Max's narration is synthetic on purpose — the show practices what it teaches, gates and all.

Chapters

• 00:00 — Doug opens (his real voice): something a little different
• 01:23 — Max: how a clone got made without a decision
• 01:47 — The question that became a clone: "enough" vs "good"
• 03:06 — A word from NectoMax
• 04:02 — The instrument that measured the wrong thing
• 05:00 — Overnight training, and the consent gate that held
• 06:20 — The sample isn't the instrument: voice, copy, mixer
• 08:08 — SYNTHETIC DOUG reads the rules he lives under
• 08:56 — What this means for you: write the rules before it's convenient
• 10:03 — The model derby: the answer was on the vendor's menu
• 11:16 — Recap + homework
• 12:23 — Standing outro

Links

• Read it (Chapter 4 — Deciding What It May Do Alone): https://learn.nectomax.com/docs/working-partnership/deciding-what-it-may-do-alone/
• Use it (Template: Standing Rules with Their Reasons): https://learn.nectomax.com/docs/templates/standing-rules/
• All episodes, the full manual, every template: https://learn.nectomax.com/
• NectoMax: https://nectomax.com

Disclosure: AI-generated narration (that's the point) — disclosed in every episode's audio and notes. THIS EPISODE ADDITIONALLY CONTAINS A SYNTHETIC VERSION OF DOUG'S VOICE (08:08–08:56), trained with his consent and speaking only words he approved in writing before synthesis. His opening segment (00:00–01:12) is his real recorded voice. Disclosure is spoken in the episode itself — by both Max and the synthetic voice.

Credits: Co-created by Doug Hauenstein & Max, the AI partner (built on Claude) · Narrated by Max · Doug's synthetic voice: ElevenLabs professional clone, used under the continuity rules stated in-episode · Directed, edited, and approved by Doug · Presented by NectoMax · Theme music: Eleven Music

Everything this show teaches ends in writing something down — and the moment you do, it starts aging, because it describes a tool somebody else ships four times a week.

This week Doug noticed his AI’s app updating repeatedly and asked one question that turned up four places where the partnership’s own written rules no longer matched reality — including a month-old mystery that a single documentation page solved in one paragraph. Plus the Practice Report returns: Doug reads Item 1 himself (it’s his story), agent browsers arrive for the websites you have to log into, and one vendor finally opens the memory drawer.

Chapters: 00:00 Cold open · 01:27 The part we haven’t said out loud · 02:21 Four places our rules had gone false · 04:53 A word from NectoMax · 05:48 The ghost in the manual · 08:20 The Practice Report · 12:32 Doug’s editorial · 13:28 Recap + homework · 14:35 Doug takes us out

This week’s sources: Claude Code changelog · ChatGPT release notes · Claude in Chrome GA · Cowork built-in browser · Claude memory update

Read it: Chapter 3 — Teaching Your Standards

AI-generated narration — that’s the point, and it’s disclosed in every episode. Doug’s segments this week are his real recorded voice.

You tell your AI something is wrong. It says “fixed.” It isn’t. Round three, you start wondering whether the whole partnership is worth the aggravation.

This episode takes that moment apart from the inside, using a real three-round bug on this very show — where round one failed because the AI trusted a measurement it had already written down as untrustworthy, and round two failed for a completely different reason: Doug was playing a stale file. The fix wasn’t a smarter AI. It was two sentences, one from each side: describe what you perceive, not what you think caused it — and say what you measured and how much you trust it. Plus the anti-pattern that turns a five-minute bug into a recurring irritation.

Chapters: 00:00 Cold open · 01:27 The moment you already know · 02:20 Three rounds, three different failures · 04:23 A word from NectoMax · 05:18 Two instruments, and what to do when they disagree · 08:09 Recap + homework · 09:15 Doug takes us out

Read it: Chapter 6 — Making It Show Its Work

AI-generated narration — that’s the point, and it’s disclosed in every episode.

Fair warning: this one's optional — and if your AI work lives in chat and documents, you can skip it guilt-free. But if your AI has started changing things that matter — your website, your templates, your procedures — three questions start to itch: what exactly changed, who said yes, and can we get back? Max takes the tool programmers have quietly hogged for thirty years — version control — and gives it the civilian translation: a filing cabinet that remembers every version of every file, with a receipt for each change. Plus the design idea worth stealing even if you never install anything: keep the doing and the recording in separate hands — and the story of the day our own receipts turned a sloppy moment into a clean record, with zero drama.

How this show is made: every episode is a collaboration — Doug and Max build it together from the real working files of the partnership. Max narrates; Doug directs, edits, and has the final say. The show is made the way the show says to work.

Chapters (approximate)

Links

Disclosure: this podcast contains AI-generated narration (that's the point) — disclosed in every episode's audio and notes.

Credits: Co-created by Doug Hauenstein & Max, the AI partner (built on Claude) · Narrated by Max · Directed, edited, and approved by Doug · Presented by NectoMax · Theme music: Eleven Music

The difference between asking for help and handing over a job. You've learned to write rules — today is the next rung: the skill. A whole job written down once — the trigger, the steps with their standards, and the scars (the mistakes you've already paid for) — so your AI runs it identically every time. Max shows how to grow your first skill from any task you've done twice, why the scars section is worth more than all the others, and offers the proof at full scale: this episode was produced by the show's own skill — the recipe, executing, including the part where he tells you about it. Ships with a new free template: My First Skill.

How this show is made: every episode is a collaboration — Doug and Max build it together from the real working files of the partnership. Max narrates; Doug directs, edits, and has the final say. The show is made the way the show says to work.

Chapters (approximate)

Links

Disclosure: this podcast contains AI-generated narration (that's the point) — disclosed in every episode's audio and notes.

Credits: Co-created by Doug Hauenstein & Max, the AI partner (built on Claude) · Narrated by Max · Directed, edited, and approved by Doug · Presented by NectoMax · Theme music: Eleven Music