Hi, I’m Allen Pike. I’m currently building Powerplant, hosting It Shipped That Way, and writing monthly about what I’m learning.
November 18, 2026
Powerplant, our tool for improving AI dev workflows using coding agents’ session traces, is now open without an invite:
Today we’re excited to announce that Powerplant is now available to all, and is free for teams under 25 seats.
Modern dev teams need to be able to leverage their coding agent sessions. These traces help make PRs more reviewable, improve in-repo skills and instructions, and can even explain why you’re spending a face-melting amount of money on Claude Enterprise. But developers shouldn’t need to push every agent session irrevocably to git to get this benefit.
If that sounds appealing to you, try Powerplant. Let me know how it could be better for your team, and we’ll donate $50 to Rewiring America or Let’s Encrypt. ⚡️
October 31, 2026
On making your team’s agents better.
One problem with AI is that it’s pretty stupid. I mean, sure, the current models are wildly useful. But out of the box, they overcomplicate, take undue shortcuts, and compound deficiencies to the moon. To get from default Claude or ChatGPT to a fast, affordable software loop – one that...
8 min read →
September 30, 2026
Breaking down the parties vying for Vancouver Mayor and Council.
Updated through Mon Oct 12, with new polling and updates based on feedback. Every four years, certain odd traditions happen. The Olympics. Leap Days. Vancouverites attempting to pick their top 10 Council candidates out of 56 randomly sorted names, 20 of whom are for parties that never previously existed. Yes,...
17 min read →
August 31, 2026
Simple steps toward a company brain.
One of the many problems computers have blessed us with is an abundance of information. Software has long been great at storing, retrieving, and sharing a company’s knowledge. This is most SaaS apps, from Slack to GitHub to Notion. But as easy as it is to store information, it’s hard...
7 min read →
July 31, 2026
On the economics of doing great work.
Most of us want to do great work. Building things of exceptional quality – work that’s beautiful, lovable, fast – is one of life’s great joys. However, the story goes, capitalism doesn’t value quality. Businesses don’t fund software that is lovable. Thus, you need to make a career choice: do...
5 min read →
July 10, 2026
This week’s discussion of the ChatGPT app and its move to Electron merits a link to my evergreen article The Persistent Gravity of Cross Platform:
At the highest level, cross-platform UI technologies prioritize coordinated featurefulness over polished simplicity.
I’ve added a coda to that article about how coding agents actually strengthen the argument for Electron on large teams, at least for now.
The initial release of the new ChatGPT app has been clumsy – there’s a lot of work to do to get Electron ChatGPT (née Codex) as polished as it should be. But, like it or not, cross-platform code is the least-bad way to coordinate a massive team on a rapidly changing product.
June 30, 2026
On too much of a good thing.
Word on the street is that the cost of building software is going to zero. Zero? Sounds like a good deal! Over the last year, my co-founder and I have iteratively automated our coding loops. Each time better tools revealed a bottleneck, we’d address it. Agents would sometimes break things...
8 min read →
June 29, 2026
This week’s AI Engineering World’s Fair just posted my talk on the agony and ecstasy of voice in, visuals out agents. It’s a challenge to get model responses that feel immediate, but when it works, it feels magical.
June 9, 2026
My turn writing for the Powerplant blog:
Now typically, when you try a SaaS product for free without a credit card, and you hit the limit, you get cut off. Also known as “disruption to your service”. Instead, we were invoiced $1000, which was immediately overdue.
Genuinely curious how common this practice is. Just because I was surprised by it, doesn’t mean it’s unheard of.
June 8, 2026
Forestwalk’s CTO Jenn Cooper shares what she’s been learning about tests, after a couple years of increasingly coding with agents:
Most discussions about AI-native development jump from this problem – agents’ tendency to accumulate tech debt – directly to tests. … Tests verify that code does what it did before.
Whether what it did was even the right way to do it is a separate question.
She argues that while agents make it easy to have rigorous traditional test coverage, at best unit tests maintain local code cohesion. At worst, they can actually make it harder to improve what agents are worst at: the wider coherence of the entire codebase.
So far I’ve been impressed with how effective the broader automated checks she describes can be to guard against agentic nonsense.
May 31, 2026
Flashes of brilliance, and the tyranny of latency.
Recently, Andrej Karpathy argued that the ideal interaction pattern for AI models is voice in, visuals out: Audio is the human-preferred input to AIs, but vision is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision; it is the 10-lane...
7 min read →
April 30, 2026
On getting uncomfortable.
Years ago, back when I was leading a mobile dev team, my friend had an idea for a business. You see, back then the most frustrating thing about mobile dev was the final step: getting your app on actual phones. Builds, provisioning, and code signing made for a harrowing trial,...
3 min read →