Aaron Wirick @awirick.com · 23/09/2026Flying to NYC today for Evolve. Looking forward to seeing some of our customers IRL 000
Aaron Wirick @awirick.com · 22/08/2026I wrote a thing on my company's engineering blog about building an agentic system and specifically how I think about Trust. This really represents the v0 model for the system and we definitely need more optimizations/improvements. It's a solid start though. builders.cortex.io/blog/trustwo...builders.cortex.ioBuilding trustworthy agents for Operational Excellence reviewsHow and why we built an agent to drive an engineering process 010
Aaron Wirick @awirick.com · 30/06/2026Thanks for publishing this. I'm definitely more Claude centered in my dev workflow but I've really enjoyed looking at both your kata skills and arcaneum for inspiration! 101
Aaron Wirick @awirick.com · 13/06/2026I actually really admire Anthropic overall but I'm deeply concerned about sovereignty when running a frontier model in the US. This whole Fable drama is the realization of the risks that I and a lot of other people have expressed over market consolidation on US AI labs. Gonna get worse I think. 000
Aaron Wirick @awirick.com · 13/06/2026Man... The USG can be kinda dumb sometimes. It's not like we haven't seen a clear path towards progressively stronger AI models for the last 8+ years. It's moving fast... but nationalistic reactions are dumb. 000
Aaron Wirick @awirick.com · 20/05/2026Reminded today that duckdb is great when you need some random interconnect between random DBs on a bastion. 010
Aaron Wirick @awirick.com · 20/05/2026Also pretty clear that there's a LOT of software out there with incredibly thin moats nowadays. "Oh I really like Foo but I don't want to deal with Java... Maybe I should just rewrite it in Rust/TS/whatever" 000
Aaron Wirick @awirick.com · 20/05/2026On my third side project in as many months and I definitely feel like it's a pretty cool time to be a builder. Undoubtedly pros and cons of AI, but it's made me more ambitious about silly projects and that is just fun. 110
Aaron Wirick @awirick.com · 13/05/2026Vendor lock in is obviously going to be a thing in agentic coding and systems. You can have your own harness or adapter layer but it's hard to say no to a fixed cost subscription. CostMaxing is gonna replace TokenMaxing 000
Aaron Wirick @awirick.com · 06/05/2026I used to work with a compliance officer who would say this all the time and have otherwise never heard it used in any conversation until Claude. Kinda makes me chuckle since Claude is kinda the opposite of a compliance officer. 010
Aaron Wirick @awirick.com · 03/05/2026So I am left again simultaneously optimistic and pessimistic about what the future of my industry could look like. If we listen to our better angels, it's going to be a wildly fun time to be an engineer and tackle wild, audacious projects. 000
Aaron Wirick @awirick.com · 03/05/2026Access to investment favors a certain type of engineer and a certain type of person if I'm being honest. If you don't NEED deep pockets to take big risks then we are going to see some awesome, audacious projects in the next couple years driven by small teams of highly motivated engineers. 100
Aaron Wirick @awirick.com · 03/05/2026This all gets derailed if access to agents calls for higher premiums. We are in this weird phase right now where $200 per month gets you crazy access to frontier models. If that sharply increases, engineers are going to need strong backers to take big risks. 100
Aaron Wirick @awirick.com · 03/05/2026On the whole, I think there's both good and bad things that come from this. Smaller teams sharpen a vision considerably, but miss out on diversity of input. Another problem here is that it means we are going to drown in possibilities. App stores were already flooded with near clones. 100
Aaron Wirick @awirick.com · 03/05/2026We've seen this story before in the industry. Individual engineers shipping packages or tools that go on to become industry standards (linux, redis, clojure, sqlite). It's not unrealistic to think that we will see even more of it as individual engineers gain increasingly greater leverage. 110
Aaron Wirick @awirick.com · 03/05/2026If that conjecture holds, I don't think you need big engineering teams (defined by anyone's definition of big). Five highly aligned and motivated people can ship a LOT at very high quality with process and agents filling in a lot of the gaps. 110
Aaron Wirick @awirick.com · 03/05/2026This means that an individual engineer can ship faster and more safely because the guard rails are technical not managerial. You obviously need the conviction to put the guard rails in place. 100
Aaron Wirick @awirick.com · 03/05/2026You _also_ need a lot of supporting apparatus and people around the engineering teams to clear the path so that the engineers can keep building. That doesn't necessarily go away but supporting a team of 5 engineers is a lot easier than supporting a team of 25. 100
Aaron Wirick @awirick.com · 03/05/2026You need to include things like "another engineer must review every PR" because of trust issues and because humans inherently make a lot of mistakes (missing checks, bad test cases, etc.). My honest to god take is that a lot of that goes away when you can build good process with agents. 110
Aaron Wirick @awirick.com · 03/05/2026I really do wonder about the future of engineering teams and how dramatically we will see a scale down in their size. A lot of the friction we have in place right now is generally because scaling the number of _people_ working on a project means you have to create human-friendly guard rails. 110
Aaron Wirick @awirick.com · 29/04/2026Not to pile on, but the decline of GitHub is really sad to me. It's not like there was no more room to innovate in the space? Such a great brand completely run into the ground by a corporate overlord. 000
Aaron Wirick @awirick.com · 28/04/2026We recently experienced a significant merge queue corruption when the queue wasn't properly selecting the base commit. Changes were just getting silently reverted on merge. 000
Aaron Wirick @awirick.com · 24/04/2026💯 They really are. I think so many people think of AI as a coding assistant only, but that's not even where they work the best! 010
Aaron Wirick @awirick.com · 21/04/2026So... I think a lot of our assumptions about good software engineering practices are flawed. They are predicated on humans and humans ain't the only ones building software anymore. There's some things that probably DON'T matter anymore and some new things that our current practices can't handle. 110
Aaron Wirick @awirick.com · 12/04/2026This totally depends on who the human was who wrote the original code. 000
Aaron Wirick @awirick.com · 12/04/2026I've made similar statements and I think it means something different than simply "more chat". A lot of UI exists for building workflows, configuration, whatever because you need to walk a human through complex things that an agent can just intuit because it understands "how systems work". 000
Reposted by Aaron WirickJustin Garrison @justingarrison.com · 01/04/2026A picture is worth 99.9 words. How's that @github.com migration from bare metal to Azure going? via Alex on Mastodon techhub.social/@ironicbadge... 1321548
Aaron Wirick @awirick.com · 10/04/2026I have a line in my global agent instructions about no random python scripts. AI usually follows the guidance, but tries to sneak them in occasionally just to keep me on my toes. 000
Aaron Wirick @awirick.com · 09/04/2026Still worried that the benefits of AI are forever going to be locked behind a bigcorp paywall. I thought it was wild that someone wanted $200 per month for AI. Kinda feels like we aren't even close to testing the market limits for the "best". 000
Aaron Wirick @awirick.com · 18/03/2026I low-key love the unbridled optimism that only an AI can have. 010
Aaron Wirick @awirick.com · 18/03/2026Agents are incredibly good at using CLI tools and this creates a very simple extension point for adding capabilities. Much easier than MCP. 010
Aaron Wirick @awirick.com · 10/03/2026You can explore a space with an agent much more rapidly than you could on your own before. Think slow, doesn't really resonate but "spend time thinking, exploring and iterating on ideas" does. 110
Aaron Wirick @awirick.com · 23/02/2026I've read some really bad takes from some well known engineers about AI agents like Claude Code. You are lucky if you've always had 10x roles with companies that had deep pockets to hire top talent. For the rest of us, $200 / month gives you crazy leverage to be more ambitious in your work. 000
Aaron Wirick @awirick.com · 15/02/2026This is 100 percent my feeling too. I don't need to be the one typing every LOC to build good software. Also Claude is really good at giving feedback and exploring alternatives so my designs are getting better too. 010
Aaron Wirick @awirick.com · 08/02/2026It's a very exciting and scary time in software engineering. I simultaneously have a great sense of optimism and an overwhelming sense of terror at how much leverage an individual engineer has. The coin is spinning and no one REALLY knows if AI is going to end up good or bad. 000
Aaron Wirick @awirick.com · 25/11/2025I don't really dabble in psychology much anymore, but every once in a while I run into a phenomenon that reminds me why I was fascinated by the field. I just had a pretty great insight into a complex graph traversal problem that fell into place while I was brushing my teeth. Gotta love the aha. 010
Aaron Wirick @awirick.com · 25/11/2025One of my coworkers just got back from three months of parental leave. Bringing him up to speed on all the tooling changes with AI is kinda shocking. Not that it was bad three months ago but the capabilities REALLY have grown fast. I feel like a frog boiling in a pot of water. 000
Aaron Wirick @awirick.com · 19/11/2025The more time I spend in software the more I kinda wish I had a proper CS academic background. 000
Aaron Wirick @awirick.com · 10/11/2025I'm jealous of all the folks who get to go to kubecon this week. Have fun yall 000
Aaron Wirick @awirick.com · 03/11/2025It's been said before but one of the best features of LLMs are that they are more than willing to try things. It lowers the required inertia to try something novel. 000
Aaron Wirick @awirick.com · 21/10/2025Today a lot of folks found out that even though they don't personally host their stuff in AWS they are indeed indirectly an Amazon customer 000
Aaron Wirick @awirick.com · 20/09/2025I've always been of the opinion that ORMs abstract away the data model in a way that leads to short term gains and, inevitably, long term pain. Don't avoid thinking about your data model just because it takes extra work. 000
Aaron Wirick @awirick.com · 28/08/2025It low-key drives me nuts when people suggest using an LLM for something that good tools already solve well. Like linters. You don't need a language model to lint a million line codebase. You need a linter. 000
Aaron Wirick @awirick.com · 28/06/2025Momentum is absolutely a thing in engineering. The best products I've ever worked on built up a head of steam and had feedback loops that kept them pointed in the right direction. The worst products got bogged down in minutiae or, even worse, moved fast but in the totally wrong direction. 010
Aaron Wirick @awirick.com · 05/06/2025As it turned out, there WAS a small logic bug in the PR that needed to be fixed but another test that caught the issue (yay for testing) and it only took a two line change to fix. 010
