tech
Software Development Roles: Lead versus Manager, Revisited
I first wrote about the lead vs manager distinction in software development in 2016. A decade later the line is blurrier than ever--and GenAI is part of why.
The original distinction was simple: if you spend half or more of your time writing code, you're a lead, regardless of what's on your business card. If significantly less, you're a manager. Organizations that keep those roles separate consistently ship better software and grow better engineers.
That's still true today. But GenAI has given companies a new reason to collapse these roles--and a new set of risks when they do.
Here's what's changed for each role:
For the Tech Lead:
GenAI raises the productivity floor for individual contributors dramatically. A skilled lead with strong AI tooling can produce what used to require a small team. Companies have noticed--and some are using this to justify asking leads to absorb management responsibilities. Don't be fooled by the productivity argument. Reviewing AI-generated code at scale, governing how your team uses these tools, and maintaining architectural integrity are already expanding the lead's cognitive load. Adding people leadership on top of that isn't a productivity gain. It's a recipe for the same burnout the hybrid role produced before GenAI existed.
For the Engineering Manager:
GenAI doesn't eliminate the core of the management role--it shifts it. The administrative overhead (status updates, reporting, some forms of performance documentation) should get easier. What doesn't go away: removing blockers, developing people, judgment calls about team direction, and now--understanding AI-assisted output well enough to hold your team accountable for it. AI-assisted--not generated--because people need to remain accountable for any and all software that ships. No blaming the AI for outcomes. Managers who stay deliberately close to how their teams are using AI will have a real edge over those who don't.
The job-search advice from a decade ago still holds: scrutinize the description, ask how the role is scoped, and look at the manager's span of control. What you find will tell you whether the company has thought clearly about these roles — or is using a familiar title to describe an unfamiliar burden.
Navigating the Great Delayering, Revisited
It’s been less than a year since I wrote this piece about engineering leadership inside a delayered organization. Here’s what I’ve learned since then.
When your rollup goes from 7 to 14 to 21 (or more) direct reports in short order, something has to give. What gives first is actually developing the people who report to you.
Delayering isn’t just a management inconvenience. It breaks the leadership pipeline.
In a healthy organization, people leadership starts small—a handful of reports, room to make mistakes—and learn from them, space to coach and be coached. Delayering eliminates that entirely. In my last organization, people leadership now starts with responsibility for two engineering teams. There is no shallow end of the pool anymore.
The way my last organization implemented delayering, team leads were turned into individual contributors with little warning beyond rumors on Blind. Imagine the whiplash of being promoted to lead a team in January only to be converted to a lead IC just a few months later. Nearly a year after implementation, there are still no clear growth paths or guidance to the next level for dozens of people in my line of business alone who went from being team leads with responsibilities for helping their direct reports shape their careers to individual contributors.
The ripple effects of delayering are real:
* 1:1 time shrinks. Feedback gets less tactically useful because the manager is too far from the work.
* aspiring leaders never get to test whether leadership is for them before being thrown into the deep end.
* senior ICs have to absorb mentoring responsibilities that aren’t formally recognized or rewarded.
* existing leaders get stretched until they break—and the institutional knowledge walks out with them.
The companies that leaned first and hardest into delayering (Meta in 2023, Amazon from 2024 to the present) have not obviously improved their products. In Amazon’s case, the combination of delayering, layoffs, and ramped-up GenAI usage has led directly to more frequent and severe production incidents. The already-fleeting margin improvements of delayering may yet turn into losses as a result.
When I evaluate my next role, among my first questions will be whether the professional growth of direct reports is a genuine leadership priority—not a talking point.
How I Created My First LinkedIn Carousel Post with Claude and Canva
A friend recommended I post more original content on LinkedIn as I enter the job market this year. Here’s how I used Claude, Canva, and other tools to create my first LinkedIn carousel post. First, I prompted Claude to look at my blog archive and curate the best 20 posts with career advice. Next, I asked Claude to convert one of the recommended posts into a LinkedIn carousel. After manually editing the HTML to update the content for the present, I opened up Canva and added screenshots of the HTML slides to a LinkedIn carousel template. After downloading the carousel in PDF format, I attached it as a document to a post and shared it with my network.
I’ve been blogging off-and-on for over 20 years, not always about my career, but enough that I expected there would be enough posts I could use as a starting point to share original content on a consistent basis. Here’s an outline of my initial Claude prompt that could be adapted and applied to any LLM:
<blog archive URL>
Review the provided URL and generate a table with the top <number of posts> links best suited to repurposed as LinkedIn posts. Each row should have the following columns: link to the blog post, <number of> items of key career advice the post contains, recommendation on whether significant rewriting is needed to make it relevant to the present day.
While I didn’t provide a persona in my prompt, I did provide details on how the response should be structured. Here is some of Claude’s “thinking” as it built a response to my prompt:
Now let me fetch the key career and leadership posts to understand their content before building the table.
I now have enough content from the key posts to build a comprehensive table. Let me compile this into a document.
Now I have enough content to build the full table. Let me create a nicely formatted HTML file with the table.
Here's your LinkedIn repurposing table with all 20 posts ranked and analyzed. A few highlights worth calling out:
Ready to post with minimal editing (5 posts): "Navigating the Great Delayering," "Tell Me About Yourself — Engineering Leader Edition," "Software Development Roles: Lead vs. Manager," "Idolatry of Innovators," and "The Problem with Exit Interviews" are all essentially evergreen and could go up this week with only length trimming.
...
Format tip: Several of these (especially #2, #11, and #13) would convert naturally into LinkedIn carousels — the structured advice translates well to a slide-per-point format.
Claude’s response was a nicely-formatted HTML table. The column with blog post links included the date of the blog post. The “rewriting needed?” column provided unexpected depth regarding the degree of rewriting needed, recommendations of specific updates to be made, even advice on the best time of year to share a particular post. The format tip which came just before the HTML table is what sent me down a bit of a rabbit hole to try and create a LinkedIn carousel instead of a traditional post.
Building on the output of the first prompt, and advice I read elsewhere regarding LinkedIn carousels, my next prompt was this:
As a LinkedIn content specialist, turn the contents of post #2 into a LinkedIn carousel of 5-15 slides in length.
Unlike my initial prompt, I did provide a persona. The range of slides gave Claude enought flexibility to size the content to a sensible number rather than stretching or cramming it into too many or too few slides.
The HTML version of the carousel looks great—I’ll definitely make future carousels I publish available in that format as well as in LinkedIn. The main goal was posting on LinkedIn though, so I pressed forward. On my Mac mini, I used Cmd-Shift-4 to screenshot each HTML slide as a image. Then I dragged and dropped it into the template pages and resized the images to fit. After downloading as a PDF (a few times as my final walkthrough of the output revealed some things I wanted to tweak), I uploaded and published the post to my LinkedIn network. In the future, I’ll make the posts open beyond my LinkedIn network for broader reach.
Navigating the Great Delayering as a Senior Manager or Individual Contributor
The recent Wall Street Journal piece titled Your Boss Doesn’t Have Time to Talk to You describes the past year-and-a-half of my life as a senior manager on the software side in a financial institution very well. My “roll up”–the number of people who report to me directly–is 14 today, but has been as high as 21 within the past month or two. The delayering happening across corporate America is making workplaces worse for managers, for individual contributors (ICs), for the products companies put out, and ultimately for consumers.
The push from Wall Street to turn management into a job where you just “push the work forward”, as Beth Steinberg says in the WSJ piece, is short-sighted. Leaders must also be about helping their directs become more effective in their roles and leveling up to be capable of taking on more scope successfully. This is how a smart organization builds the next generations of leaders from within. One of the ways I tell people I mentor to judge hiring managers is by whether or not it seems clear that the professional growth of their direct reports is a top tier priority. Delayering is causing that answer to be “no” for a growing number of leaders.
A corporate America that already does a substandard job of training leaders has further broken the leadership growth ladder with delayering. In my organization, that means people leadership doesn’t start until you become a senior manager—with responsibilities for 2 separate engineering teams. Gone are the opportunities to create stretch roles managing a small number of direct reports or contractors and coaching aspiring leaders through successes and setbacks. Gone also are the opportunities for an IC to test out if leadership is for them on a small scale, and to change career tracks if they have a good experience. Failing to develop new leaders internally while stretching and burning out existing leaders with additional responsibilities heaped on them will contribute to poor decision making, organizations losing direction, perhaps even negative P&L outcomes until the leadership gaps are filled.
Delayering doesn’t only worsen life for ICs by reducing the amount of 1:1 time with their leader for feedback, it makes that feedback less-likely to be tactically useful because that leader’s broader scope necessarily puts them further from the tactical work. When I led one team of engineers, my scope was narrow enough to review PRs and provide comments to help subsequent work improve. I could question individual design choices and shape them for the better. I could work individually on helping my directs communicate more effectively. 14 directs is too many people for one manager to coach and guide directly that will yield significant professional growth.
Delayering may have improved the profitability and stock prices of most FAANG companies (and Microsoft) in the near term, but the trend has not improved these companies’ products at all in my experience. Google Search results are noticeably worse. Meta’s product newest product offerings still look very similar to features pioneered by much smaller companies and platforms. Their GenAI advances also appear to have stalled relative to their competitors.
How does a people leader who still wants to prioritize the growth of his direct reports mitigate the downsides of delayering? Three approaches I’ve been taking are: (1) 1:1s every 2 weeks instead of weekly, (2) requesting weekly reports wins, planned work, & risks, (3) delegating more tactical mentoring to my most senior ICs. Approach 1 just accepts the reality of a limited number of hours in a day and a limited number of days in the week. My burning out would serve no one’s interest. I still maintain a weekly cadence for ICs where I have performance concerns, but a longer cadence for consistent strong performers still gives us both enough touch points beyond the usual scrum ceremonies for now. Approach 2 (not the stupid and deservedly panned “5 things” emails demanded of federal employees by Elon Musk) has enabled me to see and respond to risks more quickly—-and escalate them to my director if and when needed. They will also provide a great resource for performance management when it’s time to talk about the accomplishments of my directs in future review cycles. Approach 3 expands the scope of responsibilities for senior ICs from just an owner of technical scope, to an exemplar for less-senior teammates.
ICs in these delayered workplaces must consistently look beyond their managers to mitigate the downsides of this flatter organizational model. I’ve worked in tech long enough to remember very infrequent 1:1 time with my manager and having to make the case in writing for conferences I wanted to attend and training I wanted to take. Those relatively new to the tech industry will have to exercise the muscles of owning their professional development early and often now.
Whether we like it or not, the delayering of corporate America is changing the workplace in ways we don’t control. We still control our effort, and must mitigate the downsides of delayering so we can further grow ourselves professionally and those we work with. Regardless of the organizational design fads of the present, people matter. Professionalism matters. Treating people like they matter and being professional will outlast every trend.
My First YouTube Video
I made the tutorial you see above entirely with the following tools:
- QuickTime Player
- iMovie
- Zoom
The reason I made it was a recent struggle one of the presenters of our weekly Zoom Bible study had to get their sound shared along with their screen for the music and videos that were part of the presentation.
As long as I’ve owned Macs, it wasn’t until trying to figure out how to capture what I was doing in Zoom that I learned the QuickTime Player also has a screen recording feature. So with that new (to me) information, I wrote myself a little script and followed it to record my demo.
Once I captured the demo (and the Zoom recording of the brief solo meeting I used to demonstrate screen and sound sharing), then it was time to combine them into a single video. This is where iMovie comes in.
First I pulled in the two clips and trimmed them to the desired places. Next I threw in a cross-dissolve between them. I also tried adding a voiceover to clarify that the video after the cross-dissolve was the Zoom recording created during the first part of the video but I didn’t get that voiceover audio to come through.
Still, not bad for a first effort—and it helped the very small audience for which it was intended.
The [Tech Bro CEO] Strikes Back
What Elon Musk is doing to Twitter right now is what happens when someone with the same ideology and worldview as James Damore has enough power and money to be in charge of a company instead of just a worker. When I first wrote about Damore a little over 5 years ago, I wrote about the ways in which the ideas in his muddled, poorly-written manifesto were easily disproven. Subsequent years have demonstrated that Damore's worldview has plenty of representation not merely within the rank-and-file of tech companies, but at the very top as well. While Damore did not use this term in his manifesto, with today's perspective it's clearly recognizable as an a long accusation about the ways in which the Google in 2017 was too "woke". His manifesto is still available online, along with much of the criticism of it, but for the purposes of this piece I will summarize the tech bro worldview this way:
- The status quo composition of our companies, with its relative lack of women, black people, brown people, etc is the “natural order” of things
- Diversity initiatives require a “lowering of standards” and are therefore not meritocratic
The tech bro worldview bears enough similarities to the worldview of those who lead businesses outside of tech, hold political office, lead certain of our religious institutions, and those who populate newsrooms and shape popular opinion that Damore's manifesto even found a defender on the opinion page of the New York Times. Despite Brooks' call for Google CEO Sundar Pichai to resign, the National Labor Relations Board found the company acted lawfully in terminating Damore's employment for violating the company's code of conduct (an unsurprising outcome in my view, given the way at-will employment works).
There is plenty of evidence to debunk both the "natural order" and "lowering of standards" assertions (to say nothing of the idea of meritocracy itself). Nor can the timing of this particular conflict realistically be separated from what was happening in our politics at the time. But let us proceed to another example of how these false assertions nevertheless shape the thinking and actions not just of rank-and-file tech bros, but of those who typically lead them.
Fast-forward to April 2021, and I've been asked to be a co-panelist for a discussion on the intersection of race and technology. This discussion occurred just a day after Jane Yang (a now former employee of Basecamp) wrote an open letter to the founders while on medical leave. Yang was responding to the decision of the CEO (Jason Fried) to ban "societal and political discussions" from the company's internal chat forums. Yang's letter painted a picture of Basecamp's leaders that looked very familiar to me from my own experience with similar people in the industry. The letter is well-worth reading in full, but here is paragraph that makes it clear Basecamp's leaders were no different than those at other companies they'd criticized for years:
from Jane Yang's open letter to Jason Fried and David Heinemeier Hansson
"But there were also some yellow flags. Whiffs of smoke that I was starting to pick up on. Your disproportionate, chilling response to a retrospective that you asked for. The whispers of how you had handled a prior company discussion when someone raised the able-ist language in the title of a recently published company book. The continued mourning years later of an executive who had centered the employees as her job, and then was summarily fired for not living up to the additional expectations of working miracles in marketing. The quiet departures of women and people of color, all of whom held their heads up high and left a better place behind than they found it."
Fried and Hansson also announced the end of committees (including a committee for diversity, equity, and inclusion) and the end of 360 reviews (among other changes). As it turned out, Fried and Hansson were dealing (quite poorly) with an internal reckoning over a long-standing company practice of maintaining a list of "funny" customer names. The founders knew about the existence of this list for years, and predictably, the names that Basecamp customer service reps found ripe for mockery included Asian and African names. Particularly because of how public and opinionated Fried and Hanson have been regarding workplace culture--to the extent of having written five books on the subject, including a New York Times bestseller--and held up their own company as an example of how to do things better, it was (and still is) quite difficult to ignore the rank hypocrisy of their choice to shut down internal discussion of a significant cultural failure that they allowed to persist for years. The company all-hands called by the co-founders to try and mitigate the blowback from their decisions instead resulted in the departure of one-third of the entire company.
Over time, marginalized groups (and some of their allies) have mastered online tools and social media and leveraged them to amplify their voices. We saw that mastery at work in the responses to Damore's manifesto. At Basecamp, marginalized people used these tools to challenge the worldview of the company founders. Fried and Hansson's attempt to squash the backlash by fiat failed miserably.
While Coinbase didn't figure prominently in our panel discussion at the time, that's one of a number of companies whose lead Basecamp was following in being "mission-focused", and supposedly apolitical. So discovering that barely two years later, CEO Brian Armstrong has decided that politics is ok when it comes to tracking the "crypto-friendliness" of politicians prior to the recent midterm elections here in the U.S. was ... interesting to say the least. People and companies advocating for cryptocurrency have been far from apolitical when it comes to targeting black and brown investors, so the same groups targeted by unscrupulous operators in the mortgage space prior to the crash of 2008 have piled into crypto in disproportionate numbers relative to other investors--and have taken disproportionate losses as cryptocurrencies have plunged in value and multiple crypto companies have gone bankrupt.
Now we're just over a month into Twitter's takeover by Elon Musk--a takeover entered only because he faced certain defeat in Delaware Chancery Court. Musk has fired half the staff in layoffs so haphazardly executed that he ended up trying to rehire those not correctly identified as critical. He undermined the company's current verification scheme by pushing the launch of a feature enabling anyone to be verified by paying $8/month, only for numerous pranksters to pay the fee and impersonate numerous brands on Twitter like Eli Lilly. Musk's ultimatum to remaining Twitter staff to be "hardcore" or be gone resulted in a wave of resignations much larger than anyone anticipated, not unlike Fried and Hansson's attempt to mitigate the damage from their attempt to squash internal dissent. The same thin-skinned reaction to criticism displayed by Fried and Hansson has been even more on display from Elon Musk. He's fired those who tried to correct his ill-informed assertions regarding the ways the tech behind Twitter actually works--and mocked the skills and intelligence of the people he fired after the fact. Musk blames "activists" for the precipitous drop in ad revenue instead of being accountable for his own poor decision-making.
The reaction in various quarters to Musk's floundering incompetence as CEO of Twitter has been very telling. According to the reporting of Casey Newton and Zoe Schiffer, some tech CEOs are hoping Musk succeeds. The same Hansson who not long ago "encouraged employees to read Between the World and Me, a memoir by Ta-Nehisi Coates, and The New Jim Crow, Michelle Alexander's exploration of the racist nature of mass incarceration", is now writing tributes to Elon Musk cheering the likely end of affirmative action in higher eduction. Hansson even touts John McWhorter's Woke Racism these days, and speaks favorably of the likes of Glenn Loury and Bill Maher. Loury and McWhorter are regularly quoted by white conservatives too cowardly to share the stereotypical views of black people they already believed anyway without a black conservative to hide behind. We're already starting to see layoffs across tech, and as economic conditions change and COVID-19 (hopefully) recedes, these CEOs almost certainly see an opportunity to re-establish their worldview within their spheres of control without having to account for marginalized people. That desire is almost certainly behind the persistent belief in some quarters that what Elon Musk is doing is on purpose.
There is plenty of criticism that can and should be leveled at Mark Zuckerberg (particularly his continued pursuit of the failed metaverse strategy and cavalier approach to customer privacy). But when it comes to how to handle layoff news, he delivered a masterclass in how to handle layoffs professionally not long after Musk's deliberately cruel and haphazard ones. Other tech CEOs rooting for the man who treats his employees the worst will definitely be a trend to keep an eye on as time progresses.
(Tech) Education Should Be Free (and Rigorous)
Free tech education is the reality being created by Quincy Larson, the founder of FreeCodeCamp. I've been seeing their posts on Twitter for years, but didn't dive deeper until I heard Larson interviewed recently on Hanselminutes. The 30-minute interview was enough to convince me to add Larson's organization to the short list of non-profits I support on a monthly basis. One of the distinctions I appreciated most in the interview was the one made between gate-keeping and rigor. Especially in the context of certifications (in an industry with an ever-growing number of them), making certifications valuable is a challenge that FreeCodeCamp solves by making them challenging to get. Having pursued a number of certifications over the course of my tech career (earning a Certified Scrum Master cert a couple of times, the AWS Certified Solution Architect Associate, and an internal certification at work for secure coding), I've seen some differences in how the organizations behind each certification attempt to strike that balance.
The key value of rigor is that the process of preparing to take a certification exam should meaningfully apply to actually doing the work the certification is intended to represent. My experience of pursuing AWS certification is that the learning did (and does) apply to design discussions. It's given me valuable depth of understanding necessary to push my teams to fully explore different services for building features. One of my direct reports used the knowledge gained from certification to build equivalent functionality out of AWS services approved for use inside our organization to approximate the functionality of an AWS service currently not approved for use (in order to integrate with a third-party vendor we were working with).
When I talk to people in different fields where certifications are available, I get the distinct sense that there are varying degrees of gate-keeping involved (a practice that tech companies are certainly no strangers to). My wife has said this often regarding HR certifications offered by SHRM. She's been an HR director for over 20 years (without that certification) but hasn't been able to pass the certification exam (despite having a master's degree in HR management).
When considering whether or not to pursue a certification, it's definitely a good idea to look at them from the additional perspective of whether they are gate-keeping--or providing rigor--not just if they will help you advance your career. If you can, find out from people who've actually earned the certification whether they feel like it helped make them better at their job. Some certifications are must-haves regardless of their rigor or utility, either because your employer requires them or because eligibility to pursue certain contracts requires them (particularly in the federal contracting space).