How This Post Was Made
Prompt: “Write 7+ in-depth blog posts documenting real engineering patterns from helloweather/web. These posts go deeper than the existing ‘Skills and Scripts’ overview, showing specific implementations.”
Generated by Claude (Opus 4.5) using the blog-post-generator skill. Credit: @ioquatix for the Ruby async ecosystem. Sources: falcon.rb, app/models/api/async_http.rb, scripts/benchmark/
Rewrite (2026-09-01): Part of an archive-wide rewrite. The owner asked, “with Fable 5.1, supposedly the writing quality is much better, I’m wondering if we should do a pass on all of the blog posts we have so far to improve them. should we start with the latest one?” and, after a pilot on the worktrees post, “I like the rewrite in any case and we have a lot of Fable capacity at the moment, should we go for it and dispatch an initial round of research to improve our skills, agents.md, etc and then dispatch sub-agents to rewrite each post? this could be done in a single PR, I think.” Four Claude Fable 5.1 agents surveyed the archive to settle the voice and structure rules now in the blog-post-generator skill, and one agent rewrote this post under them. The post now opens on the 800ms p50 and the waiting behind it, the “key points” list after the client code became one paragraph, the two “when fibers help” lists folded into a single boundary paragraph, and the generic lessons were replaced by three rules that transfer. Code blocks, dates, numbers, links, and headings are unchanged, and no facts were added.
Fact check (2026-09-01): The owner asked, “1) dispatch research into the ~/Code/helloweather repos to validate the posts’ content, for example checking the StoreKit code we shared is correct. 2) fix the “Pre-existing oddities” using your judgement, and feel free to make “judgment calls” as you see fit – this is a blog meant to be authored by AI and is expected to lean on AI model judgement calls, advancements in model capabilities may prompt future editing/rewriting sessions, and for each one I’ll want them to be driven autonomously.” One Claude Fable 5.1 agent checked this post’s code excerpts, numbers, dates, and quoted rules against the source repositories. The falcon.rb excerpt gained the request-line-length override added in July 2026; the client excerpt was replaced with the real class minus logging and CDN header checks, adding the parse: option, per-host error messages, 204 handling, and the Response class it referenced; the illustrative fetch_all_sources fan-out was replaced with the real preload_each barrier pattern. The benchmark section now says the scripts date from February 2026 and were not used for the Puma comparison, with timestamped result filenames; the results table is dated to February 2026 because the September 2021 switch left no recorded benchmark; “almost none of the work is computation” became past tense because the app is CPU-bound today.
Fact check (2026-09-01): The owner asked, “did we have a post about our major CPU savings work we did a while back? IIRC we cut our Heroku bill by a huge amount w/ Claude doing local benchmarks and finding hotspots” and then, “kick off a post in a PR for that, then let’s kick off another more comprehensive round of digging into the web and ios code looking for more good stuff to post. to start I’d like to find more stuff I can share for falcon/async/async-http users. the author of async is asking if I’ve done any writing about out cost savings, so this is a great start, but I’d love to find more to share.” Writing the new post surfaced that the Results table here described the February 2026 CPU pass, not the 2021 Falcon switch: the source repository’s January 22, 2026 cost analysis records the 40-dyno fleet at about $2,025 a month, and the February 25, 2026 closeout records the 40-to-8 reduction as about $1,600 a month saved, while no plan, benchmark, or commit records any latency, cost, or Apdex figure from the Puma-to-Falcon migration. The cost row is now attributed to the CPU pass with a link to the new post, the p50, p95, and Apdex rows and the 800ms figure in the opening were removed as unsourced, the summary no longer credits Falcon with the savings, and one sentence in the Benchmarking section points to the new post. Code blocks and headings are unchanged.
Rewrite (2026-09-03): Plain-register pass, pilot for issue #66, after a reader said the posts read like AI. Archive batch 5, the last, run after batch 4 (#72) merged. The post now says “we” and “our” throughout, replaces “lightweight cooperative coroutines” with a plain definition of a fiber, defines Async::Barrier at first use, and drops three figurative lines: “most of that overhead buys idling”, “The workload decides”, and “Falcon’s share of that result is the shape of the workload it left behind”, each restated as the plain fact it stood for. The category-plus-examples list in Why Ruby Async Works kept the examples only. The summary got the same treatment. Code blocks, headings, tables, dates, numbers, links, and the credit line are unchanged, and no facts were added. Prompts, verbatim:
Prompt 1: “we got feedback from a reader that our posts are still too AI/slop/wordy, an example and a possible skill to improve are included here, please review and let me know what you think, consider if we could do another big bang rewrite without spending too much of our Fable budget, or we could prep and schedule for when our limits are about to be reset and save in a date-triggered gh issue: I enjoy your ai posts, but man is it wordy :joy: [the reader’s quoted paragraph and a link to the SimpleEnglish skill followed; both are in issue #66]”
Prompt 2: “agreed, but lets make this into an issue, I just enabled issues, document what your plan is with a new issue, then we can kick it off with the smaller sample, maybe keep going depending on token usage, and the reader can subscribe to the gh issue to track if they like. as usual, please include this prompting in the issue so people can follow along to see “how the sausage is made” if they’re interested. oh, and sorry, I think what I’m looking for is less about word counts, and more about “ai speak” as in, here’s a bit more slack chatter about this with the reader: I’m kicking off a blog rewrite thing, not 100% sure if I want to do a big bang today tho b/c Fable budgets [10:38 AM]but I’ll report back READER [10:39 AM] I’ll be curious. Will it be “byte for byte identical” ??? :joy:”
Prompt 3: “and the density issue, the quote the reader provided is a perfect “what not to do” example, I think”
Prompt 4: “another possible thing to mix into the skill changes would be the ELI5 idea, which I generally like, I often ask AI to ELI5 after dispatching research so I get a human-readable explanation of the why, what, how etc”
Prompt 5: “go ahead and kick off the pilot PR”
Prompt 6: “perhaps the use of Opus for the writing is a source of the problem? I’m finding Opus to be a bad writer, and Fable 5.1 to be much better. the reader reports: Also I think it’s funny that the ai suggestions are still bad. “extracting from the source is what makes the slice trustworthy” Should just be “The slice is trustworthy because it’s directly extracted from the source.” – and the “Not every slice can be copied straight out of the source PR” rewrite paragraph is better, but perhaps still somewhat verbose/ai-slop-ish? I wonder if we can do just a bit better, but this does seem like a promishing direction. consider and report back with a recommendation.”
Prompt 7: “agreed except I wouldn’t worry about the word count at all. “wordy” isn’t the same thing as “word count” and I think the reader (and my) issue is more to do with the AI style of speaking, which is why we’re looking at the ELI5 and SimpleEnglish skill adaptations.”
Prompt 8: “merge it and start the first batch of ten, then I can check usage, and then we can keep going – just to check, are you saying the total spend would be ~6M tokens?”
Prompt 9: “usage looks fine, merge it and run batch 2”
Prompt 10: “usage is fine, please continue – one more thing – at the end (or perhaps with future batches?) I’d like to change the “How This Post Was Made” sections in all posts to not have the prompt in the post itself, rather, the prompts should be moved into PR body if editable, or comments, then the “How This Post Was Made” can have the last edit date and a link to the Pull Requests / Prompts – then there’s less cruft at the end for readers that just want to copy paste a post into their agent – wdyt?”
Prompt 11: “sounds good”
Prompt 12: “for the “How This Post Was Made” maybe we move the date down there as well, so it’s like first posted by MODEL on DATE, last edited by MODEL on DATE, View: PROMPTS, HISTORY or something along those lines, so it’s all in one place?”
Prompt 13: “agreed, go”
Prompt 14: “approved, go”