THE LEAFLET

June 20 2025

boredom and risk, LLMs for hiring, pattern trackers

BOREDOM, RISK, AND MISSION

You may be following the common advice to “start with the why” or “return to the why” for your people. You might find that this is not inspiring them. It’s having little effect, especially on tasks that are not fun to do. If your mission statement and your values and your breathless history of your organization are well-written, they may not offer an intuitive link to many of the week-to-week tasks that your people take on. 

A thing that’s worth coming back to, that’s within your “why,” that’s within your mission is “what is at risk in this situation or in this task?” Risk can be frightening and anxiety-inducing. The friendlier side of those negative emotions is suspense, intrigue. Risky work is interesting. It has a plot. Things could turn out for better or for worse.

If you find that, in fact, there is nothing at risk in the task or the work these folks are doing, consider deleting that task. Or, assign them the job of automating or eliminating it. Then, what is at risk — the thing that they can win for the organization — is a happier, less boring, more interesting future for themselves and the rest of the team. Now, instead of just doing a boring compliance-oriented thing, they are heroes of the story who are freeing up time, attention, and dollars for themselves and the rest of the team to truly chase that inspiring mission - that why - that might not have motivated them if you had just repeated it in their faces.

-eric

PS:  This kicked me right in the shins as a high school history teacher. There were inevitably lessons in the curriculum each year that even I – the teacher, the resident nerd-for-this-stuff – found boring in prospect and in delivery. In some cases, I was able to make those lessons my favorite, and the kids’ favorite, of the year. The path to that was digging into the characters and the story hidden behind the flashcard vocabulary kids would need to retain for a state test. Briefly put, I had to find what was at risk in this lesson. I had to find the drama. “Late 19th century monetary policy” is a phrase that might put you to sleep before you even get to the end of it, but when you realize that is the dull mask on a life-or-death nationwide battle between farmers and bankers with a three-time presidential candidate criss-crossing the country on a train, screaming himself hoarse about Jesus, it starts to get more interesting.

Read the rest here.

LLMs for HIRING

Around here, we’re believers in using a hiring process to give as much info as possible to the candidate. It’s really challenging to get good, credible signal from candidates in traditional 1:1 interviews. Smooth talkers outnumber smooth operators. And it’s easy to believe that all those cognitive biases that beset others don’t dog you, too. Ironically, you might be even more at the mercy of those biases when you’re aware of them. 

I’ve found it helpful to use LLMs in hiring processes as one more “voice” and “perspective” that can help you check your own biases and develop a holistic view of candidates. Here are a few places in a process where you can bring them in:

• Generating follow-up questions to ask in subsequent interviews.

• Sample prompt: Upload the job description and interview notes from a screener or first interview then ask “Based on what you see here, what are 5 questions we should ask this candidate in the next round to give us the most complete understanding of their qualifications and mindset?”

• Creating rubrics 

• This is one of those tasks that can take an hour or more for a person to do but maybe only requires 10 minutes for a person to edit when an LLM has done a rough draft.

• Sample prompt: “Here’s the job description and list of interview questions we have for this role. Please create a rubric that will enable us to rate candidates on a scale of 1-7 in five different areas, based on their performance in interviews and a performance task. Please make the rubric a spreadsheet that we can easily copy into the workbook we’re using to track candidates.” 

• Design and editing of a performance task or work trial

• One way to sort smooth talkers from smooth operators is a timed, scenario-based performance task that is then anonymized before grading. Ideally this presents a candidate with some true-to-life situations they have to address in writing. 

• Sample prompt: “Here’s the job description and some context on where we hope the team and organization are headed in the next year plus. Please generate three prompts for candidates to respond to in 90 minutes total that will a) give them a rich sense of what the job is really like and b) gives us a way to evaluate their skills, decision-making, and values”

• Grading/reviewing performance tasks and work trials

• As with interviews, there’s real value in having more than one perspective on the performance task. I like to have multiple human graders and an LLM grader as well. You can decide if you want the LLM’s scores to actually “count” in the evaluation of the candidate or if you just want them there for reference.

• Sample prompt: “Here’s the rubric we’re using and here are the anonymized performance tasks of the candidates. Please grade each task according to the rubric and output a spreadsheet with the results.”

• Checking your bias and intuition on things that don’t show up in the rubric

• Sample prompt: “I saw a candidate do x during my interview with them and it made me wonder or suspect y. What do you make of this? How should I follow up on this intuition, if at all?”

• Nb: Nothing here is legal advice and it’s important that you and your team are clear on the do’s and don’ts in the employment law of your state (especially if your organization is based in California :D

-eric

Read the rest here.

FINDING PATTERNS WITH LITTLE NEAR-TERM TRACKERS

For the last several years, I have enjoyed doing Tim Ferriss’ past year review some time in late December or early January. Ferriss has you take a retrospective look at your calendar from the prior year and identify your highlights and low lights week by week. Then you rank those highlights and lowlights, looking for the ones that recur most often and the ones that are truly exceptional. 

Then — and this is key — you take your new understanding of the patterns of your past year and use it to a) protect and b) promote your well-being in the year to come. That is, you pre-book versions of your peak or highlight experiences and you eliminate or minimize the presence of the lowlights. This helps set an elevated baseline for your year ahead. Not only are you likelier to do things that lift you - you get the zest of looking forward to them, too. 

A thing I have found challenging about this is looking back over the course of an entire year. Sometimes my calendar isn’t a complete or faithful account of what I did or what I enjoyed. I also forget what even happened back in, i dunno, April. 

So I am finding increasingly that it’s useful to run smaller versions of this exercise during the year. You can apply the simple tracking approach to things that are not just favorite and least favorite moments. If you like, you can then have an LLM analyze the data you’ve collected on yourself. Often the AI will find patterns or implications in your data that aren’t obvious to you. Or they are obvious, but you are biased against them and try to avoid them :D . 

Here are a few other things you might track for a few days or a few months, then bring to Claude or GPT and ask what they make of It:

• aliveness tracker. When did I feel most alive during the day altogether or at work in particular? (Most alive might not be the moment that was most fun or enjoyable - often it’s a moment that has stakes or risk of some kind)

• negative self talk tracker. When did I think critically about myself during the day? What was the thought? What happened immediately before or immediately after?

• our very favorite around here: recognition frequency tracker. When did you acknowledge someone for taking values aligned action? Who was it? What was the action?

I like these three because they can enrich your understanding of how things are going with more data and less reliance on vibes.

-eric

Read the rest here.

COMPELLING QUOTES

Sufi prophetess Rabi’a al-i’Adawiyya on priorities:

My love of God leaves me no time to hate the Devil..

Op-ed writer David Brooks on lenses:

Your mind creates a world, with beauty and ugliness, excitement, tedium, friends, and enemies, and you live within that construction. People don’t see the world with their eyes; they see it with their entire life.

Writer Adam Mastroianni on getting to the point:

The Wadsworth Constant says that you can safely skip the first 30% of anything you see online. (It was meant for YouTube videos, but it applies just as well to writing). This is one of those annoying pieces of advice that remains applicable even after you know it. Somehow, whenever I finish a draft, my first few paragraphs almost always contain ideas that were necessary for writing the rest of the piece, but that aren’t necessary for understanding it. It’s like I’m giving someone a tour of my hometown and I start by showing them all the dead ends.

Keep going, keep growing,

Ben & Eric