How This Post Was Made
Prompt 1: “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”
Prompt 2: “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.”
Generated by Claude Fable 5.1 using the blog-post-generator skill. The first prompt found that the CPU pass was mentioned in two existing posts but had none of its own. Sources: the January 2026 CPU plans and profile results, the February 12 plan that re-measured the app output path, the February 19 memoization PR and its concurrency audit, the direct-delegation and translation-cache PRs of February 23, the February 24 report that closed the track, the dyno step-down plan with its per-window log samples, the February 25 closeout summary, scripts/benchmark/weather_request_probe.rb, scripts/benchmark/derived_hotspots_probe.rb, app/models/api/concerns/lazy_attr_accessor.rb, and config/heroku/formation.yml history. Judgment calls: dollar figures recorded in the plans are expressed here as dyno counts and percentages, the product-specific output name is described rather than named, the vendor behind the 504s is not named, and the “three quarters of traffic” figure is the plan’s approximate number as of February 2026.
Rewrite (2026-09-03): Plain-register pass, pilot for issue #66, after a reader said the posts read like AI. Archive batch 3, run after batch 2 (#69) merged. Rewrote the prose from an ELI5 of the post: first person and contractions throughout, “derived attributes”, “memoize”, and “interleaved baseline” defined at first use, one name each for the dominant path, the vendors, and the fleet, and the sentences that packed three facts split into one fact each. Judgment calls: “the contract” and “the whole diff” on the accessor became “the rule” and “the accessor after the change, in full”, and “formation” became “fleet” so the dyno count has one name; code, headings, numbers, and the guardrail bullets are unchanged. 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?”