jbdamask

I'm running an experiment with a team of Claude agents to build a decision support app for biotech investors. Regardless of the results, the agents simply do too much for me to monitor what's going on. Standard updates to Slack are ok but that format lends itself to short-and-sweet posts.

Podcasts turn out to be a pretty good way to keep track of progress. At the end of a unit of work, the agent writes a script from the agent chat history (including my interjections) and generates the audio with voices from Eleven Labs.

A funny example came from an episode where I learned about the team's plan to run a large test suite. Instead of going through my Claude plan the team thought it was a good idea to use API calls. Estimated cost: $730.

I didn't get banned but you can imagine my mature, productive response when I hopped into the chat to stop the test.

Really fun model! Thanks for opening up access as quickly as you are.

Appreciate you trying it and commenting. And I'm sorry that you hit this bug on first contact. My goal is to have a dead-simple UX, not waste your time trying to get it working. Heck, the whole point of Rocky Surf is convenience.

I've filed this as a bug.

Per your comment about the documentation - I agree that the docs aren't great for humans. In fact, they're meant to be read by agents, not humans. But I don't make this clear anywhere.

During this build, my development agents were instructed to be verbose with documentation. I find that this improves code quality and architectural consistency across multiple agent sessions - Rocky Surf was built over hundreds of agent sessions. The trade-off is that there's too much for humans to read.

As I got closer to release, I read, edited, and pruned a considerable amount of verbiage, but stopped short of making concise docs a release requirement. But the fact that you noticed that a particular doc was 40 pages tells me that I didn't value your time as much as I should have. Duly noted.

Development and new releases will continue since I use Rocky Surf all the time. In fact, I recently found that it pairs nicely with Herdr https://x.com/jbdamask/status/2099110104037494963?s=20

Thanks again for trying it and commenting. You didn't have to give me feedback but you did, and that's really nice.

An associated plugin, https://github.com/jbdamask/modern-software-engineering-in-a..., is available to audit codebases against the principles.

I find the perspective is a useful complement to standard code reviews.

pfft...I'm way past understanding

Not sure why this is surprising. Language is a communication protocol

Enterprises need a solution like Lovable or Replit if only for the one-touch deployments. Unfortunately, neither tool is there.

I don't know what's taking Anthropic, OpenAI, Google, Microsoft, even AWS to build deployments themselves. There are only a handful of reference architectures for vibe-coded apps.

I use AI explainers a lot in my own projects and have skills that give outputs I like. I'll even pipe the output into NotebookLM to make a video sometimes. This is actually a decent way to grok complex subsystems (YMMV).

What I don't care for is the pretty-yet-verbose HTML outputs that I see from some teams. They can be way too long and it's often the case that the engineer who made it didn't read the whole thing.

Any linkedin devs here? Would be interesting to hear about the algos

Flowise was cool. I used to to help build an enterprise employee search tool with it a few years back. https://medium.com/better-programming/employee-search-with-o...

The fact is, there's not as much need for drag-n-drop low code tools anymore. At least I don't have much need.

Building while vacationing

sure, but just look at that butter cow!

The bigger a system gets, the tougher it is to grok. I used to spend oodles of heartbeats writing explainers for managers and other engineers but rarely do that w/out AI now.

I like NotebookLM's video creation abilities for certain things. To make this one, I:

1. Chatted with Claude about a particular part of my app. It read the code and docs for grounding and we iterated. 2. When happy w/ to scope and level of detail, I asked for an explainer doc. 3. Uploaded to NotebookLM. 4. Clicked 'Video Overview'.

I can't tell if this thread is real or not.

But, uh, I have All Clad pots and pans and still like them. The bottoms warped on a couple so I replaced them with other brands.

In general they hold up well when hand-washed.

The handles are terrible though. Maybe it's a UX nudge to always use a pot holder?

Classic case of a CEO finally understanding why engineers are needed

Agentic Engineer: "How'd you solve the icing problem?" Vibe Coder: "Icing problem?"

Steve's mega-project this past year has been Gas Town. It's a way to manage umpteen coding agents doing your bidding. It allows humans to delegate more to AI while not sacrificing quality. I finally found a day to dig into it and, even though it did some amazing stuff, I was confused.

Gas Town has its own vocabulary since Steve got to name everything. There's the Mayor, Rigs, Polecats, Witnesses...zoiks. He blogged a lot about Gas Town but it's still the kind of thing you need to use in order to grasp.

To make learning Gas Town a bit easier, I wrote a post called A Random Walk Through Gas Town. Well, I didn't actually write it. I indexed the codebase then had Claude pull out interesting features and write about them from the Mayor's quirky perspective.

Feeling great. It’s never been faster to bring ideas to life. If anything, I need to look at nature more

Previously: https://news.ycombinator.com/item?id=47195123 (March 2026, 136 comments)

Several months ago I posted about my little proto-app, Now I Get It! that uses LLMs to translate scientific papers into web pages that anyone can understand. The feedback and engagement from this community was terrific and helped me turn it into a real product. It's a niche, convenience product. Not a game changer. I'm comfortable with that and went into it with eyes wide open.

Regardless of whether the product does anything, building and launching this as a solopreneur was super fun and educational. It helped me hone my agentic engineering skills and also gave me a better sense of what I could truly delegate to coding agents and where I had to be involved.

In short, my experience led me to believe that the best models, harnesses, and techniques aren't yet there to fully build a cloud-native app (AWS) that is fast, cost-efficient, robust, and secure. Not to mention modular and extensible. The number of decisions a human must make is still very high. That's not a huge surprise to me since coding is just one part of engineering.

The fun part of engineering (for me at least) is putting shape to a problem and thinking at a systems level even when decomposing into tasks. It's the constant zoom-in, zoom-out interplay that first attracted me to software engineering. Yes, I rely heavily on LLMs for development but 9/10 times I would find something wrong in a plan, a design, an implementation, or a test that would have created problems if I wasn't there.

The process I followed for this build, in-a-nutshell: 1. Every feature, bug, and improvement gets its own Issue. Descriptions are sparse so the LLM can really dig into during planning. 2. Plan every issue but override Claude Code's planning mode since it tries to implement immediately after a plan is approved. Also, it's helpful to have the LLM write a user story before writing the plan so that UX stays front-and-center. I had so many issues where Claude would be like, "Oh. You mean you don't want the user to see a 403?" 3. Read the plan. 4. Decompose into Beads (Thanks Steve). 5. Open a new Claude Code session in TMUX and say, switch to a worktree for issue xyz and build it. 6. Deploy to a test AWS environment. Use Claude for Chrome to do a first-pass check for front-end stuff then I'd follow up. 7. Devlog the work. 8. Make a PR, review, merge, deploy to prod

Three things I did early on that turned out to be very useful: 1. The app was free when I first posted and people from around the world processed a lot of papers. This gave me a TON of data I could analyze to figure out a pricing structure that maintains a sustainable margin. This is important because the app is self-funded; I don't want to have to decommission it because I miscalculated my expenses.

2. Optimized architecture for low idle cost. I don't want a bunch of infrastructure burning a hole in my bank account if I can't get enough customers to sustain the app. This app relies heavily on static html pages on S3 behind CloudFront, along with Lambda, and DynamoDB. All very cost-effective.

3. In addition to my DevLog skill, I made an app-specific skill called now-i-blog-it. This reviews my DevLog for recent updates and writes short, technical blog posts. Of course, LLMs aren't great writers so I wound up with another skill called cringelinter that can be run in a Ralph loop to scrub all the mic-drops, bro-speak, and cringe words from the blogs.

The blog has over 60 entries so far covering everything from architecture, to adding an inline HTML and KaTeX editor, to my first hacker, to launch. Some of you may find it interesting. It demonstrably shows that that reports of the death of software engineering have been greatly exaggerated.

Thanks again to this community for engaging with my original post. It's been a fun build.

Nice job - I'm a fan. Makes it easy to get the big picture so I know where to dive in.

Added a waitlist to the site https://nowigetit.us

I should probably just make a new post but if anyone is still watching, I've made a couple of changes and have more coming:

1) Modes. You can now choose between Native, Non-Technical, or Kid-Friendly mode. Here are results for the same paper Native: https://test.nowigetit.us/pages/62ef3639-02f0-472b-b0a6-79f6... Non-technical: https://test.nowigetit.us/pages/eba32173-269f-4b5c-9df1-c782... Kid-friendly: https://nowigetit.us/pages/3c413c94-d843-4e84-8805-22af16021...

2) I'm working on user accounts with private galleries

3) Getting closer to opening this up with a cost-plus pricing model. Hopefully by next week but we'll see.

Some commenters have suggested turning this into a sort of graph where references are either brought into the page or new pages are made for references then linked. Is that what you're thinking about?

That's a really cool idea. Can you elaborate?

A few people uploaded the Bitcoin paper and I noticed a bug in one where the page just kind of ended halfway through. This was due to my stringent security protections against prompt injection and outside links but I was blocking some legit CDNs, like Chart.js. That's been adjusted.

Thank you. Great to hear!

Totally agree. At the same time, I find that my brain learns best when I ingest the same information in different ways. This app doesn't replace papers; it complements them. Unless you're my mom - she's not going to read arXiv anytime soon.

No. At least that's not what I intended.

I find the same thing - that sometimes less is more when it comes to prompts. Especially when the inputs are somewhat unpredictable.

Yea, I was surprised by the output myself. It's all auto-generated.

I'm considering some ways to direct the LLM but we're in this funny period where models are getting better on subjective things like look-and-feel. And if I direct too much, I may wind up over-fitting for today's models.