Healthy AI First (English)

Miriam's department head wants a number by the end of the month: how much faster is the team with AI? Instead of one big shiny number, we follow Miriam, the team lead, with Daniel and Jonas for 4 weeks like a diary. Week one: only watching. Weeks two and three: one person works with the new rule, the other with the old one, and they swap after a week. Week four: looking at the results. They measure with a car dashboard of 3 gauges. Along the way, we meet Goodhart's law, a broken Thursday that a summary written by AI hides in the median, and a single page for the budget meeting. And one last time: your number.

Chapters
00:00 Opening
01:04 Welcome
01:54 The First Temptation
03:08 The Dashboard
04:09 Fuel Gauge and Warning Light
05:37 Week One: Just Watching
07:22 A word from us
08:14 Switching Sides
09:48 Week Two
10:57 Week Three
12:24 Week Four: The Smooth Summary
13:50 One Page for the Budget Meeting
15:29 What Nobody Knows Yet
16:25 Your Number

All sources, studies and the companion document for this episode:
https://clnwork.com/podcast/healthy-ai-first/en/episode-08

Miriam, Daniel, Jonas and the department head are fictional. In episode 1, Daniel stood in for the participants of the METR study; from episode 2 on, he is a fictional colleague on Miriam's team and did not take part in the study. The course and results of Miriam's experiment (the hard week two, the broken Thursday, Daniel's understanding check) are made up too; they show one possible interpretation of a pilot, not measured or typical values. A real experiment may also show no improvement or a deterioration.

Healthy AI First is AI-researched and AI-generated, narrated in Björn's voice, recreated with AI, and reviewed by him.

A quick word from us: CLN Work
Björn is one of the founders of CLN Work. CLN Work helps companies adopt AI in small, verifiable steps: finding where real capacity is, which processes can be automated, and how to use AI interactively. The decisions stay with you.

Book a free, no-obligation 30-minute conversation: https://clnwork.com/book
More about the approach: https://clnwork.com

We rewind Jonas's Tuesday and tell it again: one single change, an appointment reminder with a daylight saving trap, from sizing up the task to exploring, a 4-line contract, Daniel's review and a careful rollout. Alongside it, Miriam's day with a calendar that is only half hers, and what of all this still works for juniors and people on call. The workflow is a proposal to try out, not a proven optimal work cycle.

Chapters
00:00 Opening
00:56 Welcome
01:37 The Image: a Mountain Hike
02:32 Before You Set Out
04:02 Miriam's Tuesday
05:07 Exploring, and Sometimes a Map
06:18 A word from us
07:10 The Short Contract
08:37 Letting It Run
09:45 Cairns
11:11 A Second Pair of Eyes
12:40 The Whole Day
14:08 Logging Off
15:38 Energy at Night

All sources, studies and the companion document for this episode:
https://clnwork.com/podcast/healthy-ai-first/en/episode-07

Healthy AI First is AI-researched and AI-generated, narrated in Björn's voice, recreated with AI, and reviewed by him. Jonas, Daniel and Miriam are fictional characters.

A quick word from us: CLN Work
Björn is one of the founders of CLN Work. CLN Work helps companies adopt AI in small, verifiable steps: finding where real capacity is, which processes can be automated, and how to use AI interactively. The decisions stay with you.

Book a free, no-obligation 30-minute conversation: https://clnwork.com/book
More about the approach: https://clnwork.com

An agent reports "all checks passed", and everything is green. This episode asks what each check really proves, why an agent can bend its own tests, and why a second AI model as reviewer can share the same blind spot. Also: how to protect test files from the agent, mutation testing for changed lines only, risk classes as a team agreement, the ironies of automation, and the explain-back check.

Chapters
00:00 Cold Open
01:03 Welcome
01:47 What a Check Mark Says
02:45 Miriam's Proposal
03:53 The Bent Test
05:17 A Lock for the Tests
06:31 A word from us
07:23 A Cone in the Blind Spot
08:56 The Second Mirror
10:12 The Overeager Reviewer
11:35 Where Humans Look
13:20 Why Good Tools Lull Us to Sleep
14:49 Keeping Judgment Awake
16:43 Green That Means Something

All sources, studies and the companion document for this episode:
https://clnwork.com/podcast/healthy-ai-first/en/episode-06

Healthy AI First is AI-researched and AI-generated, narrated in Björn's voice, recreated with AI, and reviewed by him. Jonas, Daniel and Miriam are fictional characters.

A quick word from us: CLN Work
Björn is one of the founders of CLN Work. CLN Work helps companies adopt AI in small, verifiable steps: finding where real capacity is, which processes can be automated, and how to use AI interactively. The decisions stay with you.

Book a free, no-obligation 30-minute conversation: https://clnwork.com/book
More about the approach: https://clnwork.com

Miriam, the team lead, read a 12-page AI-written concept twice and still can't find the answer when Daniel asks in a meeting what happens if a payment notification arrives twice. This episode is about why a small diagram sometimes clarifies more than many pages of text, when duplicate explanations and voice help or hurt, and why explaining something to the AI yourself does more than just listening to it. With a rubber duck that asks back, a prompt to take away, and an experiment for developers and office work.

Chapters
00:00 Cold Open
01:15 Welcome
01:58 Ten Thousand Words
03:12 Map, Directions, Stranger
04:33 A Picture for Your Ears
06:09 When Pictures Hurt
07:23 A word from us
08:15 Double and Spoken
09:46 Rereading Feels Good
11:01 The Rubber Duck
12:15 A Duck That Asks Back
13:44 Miriam's Second Try
15:10 One Picture Instead of Twelve Pages
16:09 Your Experiment

All sources, studies and the companion document for this episode:
https://clnwork.com/podcast/healthy-ai-first/en/episode-05

Healthy AI First is AI-researched and AI-generated, narrated in Björn's voice, recreated with AI, and reviewed by him. Miriam, Daniel and Jonas are fictional characters.

A quick word from us: CLN Work
Björn is one of the founders of CLN Work. CLN Work helps companies adopt AI in small, verifiable steps: finding where real capacity is, which processes can be automated, and how to use AI interactively. The decisions stay with you.

Book a free, no-obligation 30-minute conversation: https://clnwork.com/book
More about the approach: https://clnwork.com

At 10:40 in the morning, 3 of Jonas's 4 agents reach for him at the same time, and a couple of rooms away, Miriam loses track of her own quarterly plan across 3 AI chats. This episode explains attention residue, takes apart the myth of the "23 minutes", and uses Little's Law to show why more agents with the same review capacity mostly mean longer waits. Plus a tool tip on separate git worktrees, a resumption point for every switch, and a suggestion to try out, for developers and for the office.

Fictional characters: Jonas (junior developer), Daniel (senior developer), Miriam (team lead for Daniel and Jonas). The Little's Law calculation is an illustration, not a measurement.

Chapters
00:00 Cold Open
01:24 Welcome
02:05 The Juggler
03:11 Miriam's Morning
04:13 What Stays Behind
05:27 The 23 Minutes
06:53 A word from us
07:44 Small Portions
09:10 The Queue at the Pass
10:42 How Many Balls
12:16 Separate Working Copies
13:53 The Resumption Point
15:16 A Limit for the Team
16:18 Until Next Time

All sources, studies and the companion document for this episode:
https://clnwork.com/podcast/healthy-ai-first/en/episode-04

Healthy AI First is AI-researched and AI-generated, narrated in Björn's voice, recreated with AI, and reviewed by him.

A quick word from us: CLN Work
Björn is one of the founders of CLN Work. CLN Work helps companies adopt AI in small, verifiable steps: finding where real capacity is, which processes can be automated, and how to use AI interactively. The decisions stay with you.

Book a free, no-obligation 30-minute conversation: https://clnwork.com/book
More about the approach: https://clnwork.com

A ticket made of a single sentence, an agent that builds a clean account deletion feature in 20 minutes, and a question from Jonas that reveals what the agent quietly decided along the way. Meanwhile, the AI writes a delivery date into Miriam's client proposal that nobody ever committed to. This episode is about which decisions have to stay with people and which ones the agent can safely make: load-bearing walls, one-way doors, locks instead of notes in the prompt, a lost Mars probe, and how much planning is really needed.

Fictional characters: Jonas (junior developer), Daniel (senior developer), Miriam (team lead for Daniel and Jonas). All studies and cases are real.

Chapters
00:00 Cold Open
01:08 Welcome
01:51 The List
03:10 Miriam's Proposal
04:17 Load-Bearing Walls
05:52 One-Way Doors
07:28 A word from us
08:19 The Lock on the Door
09:27 Locks in the Tool
11:01 The Connection Next Door
12:28 What Stays With Us
13:40 What the Vendors Recommend
15:33 Two Fields in the Ticket
16:47 Your Load-Bearing Wall

All sources, studies and the companion document for this episode:
https://clnwork.com/podcast/healthy-ai-first/en/episode-03

Healthy AI First is AI-researched and AI-generated, narrated in Björn's voice, recreated with AI, and reviewed by him.

A quick word from us: CLN Work
Björn is one of the founders of CLN Work. CLN Work helps companies adopt AI in small, verifiable steps: finding where real capacity is, which processes can be automated, and how to use AI interactively. The decisions stay with you.

Book a free, no-obligation 30-minute conversation: https://clnwork.com/book
More about the approach: https://clnwork.com

When AI writes the code, the work doesn't disappear. It moves: from writing to explaining, reviewing and fitting things together. This episode follows the trail of the time, shows why more code is a poor measure of success, and explains how a team can ship more every day and still make slower progress. Plus a tool tip on reading lead times from Git and GitHub.

Fictional characters in this episode: Jonas (junior developer), Daniel (senior developer; in episode 1 a stand-in for the study participants, from now on part of the team), Miriam (team lead for Daniel and Jonas), Hanna (wedding photographer, this episode's image).

Chapters
00:00 Opening
01:24 Welcome
02:34 The Whole Journey
03:59 Miriam's Status Report
05:41 The Photographer
06:56 A Sixth of the Day
08:26 A word from us
09:16 The Second Half of the Sentence
11:00 The Pile Before the Bottleneck
12:13 Almost Right
13:26 The Clock in the Tools
14:44 What Done Means
16:25 Your Time, Split Up

All sources, studies and the companion document for this episode:
https://clnwork.com/podcast/healthy-ai-first/en/episode-02

Healthy AI First is AI-researched and AI-generated, narrated in Björn's voice, recreated with AI, and reviewed by him.

A quick word from us: CLN Work
Björn is one of the founders of CLN Work. CLN Work helps companies adopt AI in small, verifiable steps: finding where real capacity is, which processes can be automated, and how to use AI interactively. The decisions stay with you.

Book a free, no-obligation 30-minute conversation: https://clnwork.com/book
More about the approach: https://clnwork.com

16 experienced developers expect AI to make them almost a quarter faster. Measured, they are slower, and afterward they still believe they were faster. The opening episode of Healthy AI First tells why our gut feeling is a poor measuring instrument when we work with AI, what other studies say against it, and where the series goes over the next 7 episodes.

Chapters
00:00 Opening
00:57 Welcome
01:44 Your Guess
02:19 The Experiment
03:32 The First Twist
04:55 The Second Twist
07:24 A word from us
08:14 The Experiment Breaks Apart
09:59 The Other Side
11:27 Three Questions for Every Headline
12:25 What It Costs
14:21 The Journey of This Series
15:53 Your Number

All sources, studies and the companion document for this episode:
https://clnwork.com/podcast/healthy-ai-first/en/episode-01

Daniel and the project manager are fictional characters used for illustration.

Healthy AI First is AI-researched and AI-generated, narrated in Björn's voice, recreated with AI, and reviewed by him.

A quick word from us: CLN Work
Björn is one of the founders of CLN Work. CLN Work helps companies adopt AI in small, verifiable steps: finding where real capacity is, which processes can be automated, and how to use AI interactively. The decisions stay with you.

Book a free, no-obligation 30-minute conversation: https://clnwork.com/book
More about the approach: https://clnwork.com