Manager x Builder (@managerxbuilder) header
Manager x Builder (@managerxbuilder) profile picture

One of us still manages. One went back to building. AI smashed those jobs together, so we argue in public. Weekly.

Joined August 2026
Photo by Manager x Builder (@managerxbuilder)Photo by Manager x Builder (@managerxbuilder)Photo by Manager x Builder (@managerxbuilder)Photo by Manager x Builder (@managerxbuilder)Photo by Manager x Builder (@managerxbuilder)Photo by Manager x Builder (@managerxbuilder)Photo by Manager x Builder (@managerxbuilder)Photo by Manager x Builder (@managerxbuilder)Photo by Manager x Builder (@managerxbuilder)Photo by Manager x Builder (@managerxbuilder)
Brian's personal wiki ranks sources by trust. His own words count most, then his calls, then the podcasts and newsletters he trusts. Random web results never get in.
1
28
Brian deleted all of his custom sub-agents this week. He still runs vanilla sub-agents constantly, because a test writer shouldn't know what the implementer did. managerxbuilder.substack.com…
1
36
Tomorrow on Manager Builder, Kunal and Brian debate generalized vs specialized agents. "Most of our best practices are just best practices for humans."
1
37
In planning, Claude should ask what you want to do and then stop. Once it hands you a recommended option, it's too easy to just hit Enter. managerxbuilder.substack.com…
1
45
One-shot vs progressive on the same monitoring stream. One-shot: four false pages, missed the leak, a couple of cents. Progressive: one page, no false positives, about 50 cents. managerxbuilder.substack.com…
1
63
One-shot vs progressive on the same monitoring stream. One-shot: four false pages, missed the leak, a couple of cents. Progressive: one page, no false positives, about 50 cents. managerxbuilder.substack.com…
1
41
When did you last disagree with Claude? If you can't remember, you might not be the one making the decisions anymore.
26
Asked a fast classifier to make one call per event. Four false alarms, and it missed the memory leak.
1
44
AI slop can cost you a client. Manager: keep a quality gate when models write the code. managerxbuilder.substack.com…
2
32
Why personal software matters: remove friction in your own workflow, and get a low-risk lab to try AI before work. Builder. managerxbuilder.substack.com…
1
33
RIP PRs in 2026 — or just move the review upstream? Klaus Nji joins Manager Builder: build the room, not the house.
1
1
35
Squarespace had no API, so I was the human in the loop adding zero value. One day-long side project with AI later, the site runs on Astro 5 + Cloudflare Pages. Builder take on personalized software.
1
1
1
80
Squarespace had no API, so I was the human in the loop adding zero value. One day-long side project with AI later, the site runs on Astro 5 + Cloudflare Pages. Builder take on personalized software.
1
54
Are you leading Claude, or is it leading you? Manager take: lead the bots instead of being led by them. managerxbuilder.substack.com…
2
1
32
A human avatar sending dehumanized Claude-speak in Slack isn't helpful — it feels disrespectful. Manager take on AI slop in human channels.
1
1
43
Subsidized plans are coming to an end. What's your end game strategy? We think it's shifting execution to the right into centralized, lower-cost software factories: managerxbuilder.substack.com…
Hi, Tomorrow we are re-opening the Pro $200 subscriptions to new subscribers, but together with it we are also changing how we calculate the usage for it. In effect, if you do the math, it will net out at half the dollar in API spend compared to the old Pro $200 plan. Now that it's said, let me explain why this is happening and why you will still get more work done than if you were on the Pro $200 subscription one month ago. (a) We didn't want to compromise in other ways and are committing to not reintroducing the 5h limit, so that you can fully use the weekly usage when you want. (b) On the subscription, we guarantee that over time you always get more work done and with an increasing level of quality. This means that you will continue to get more value per dollar spent as a result of models getting more efficient and us passing down the improvements in the form of API price reductions. (c) We don't want to put an incentive on ourselves to artificially inflate the API list prices to make it look like you are getting a lot (and workaround it through discounts, etc). Instead we want to continue to both rapidly reduce prices and increase capabilities of models on the API. This week we introduced GPT-6 Sol and GPT-6 Luna at 50% of their previous price. Over time, we see prices go low enough that it makes sense for most to buy usage as needed without there being a significant gap between what you get in a subscription and what you get in the API for a dollar spent. (d) Tomorrow, we are adding more things to the subscription that won't draw on the usage, I won't reveal what that is yet. I wanted to be transparent before all the big announcements tomorrow. Lots of new exciting things are coming to the subscriptions that will make it super compelling, but I wanted to make sure to share this change ahead of time so you can all understand it before we shower you with good news. Codexingly, Tibo
36
Bots reading incomplete Jira context is dangerous. 95% done in tickets ≠ done when the rest lives in someone's head. managerxbuilder.substack.com…
2
1
22
The night shift isn't just overnight agent work — it's a different operating model. managerxbuilder.substack.com…
2
1
51
Is coordination dead in the age of AI? (Manager) More POCs just means more program management — not less.
1
1
36
Functional constraints vs architectural ones — which actually breaks your agent workflow?
2
2
30