I would say maybe 50% of software already does that.

Would you care to show some evidence, or is it a vibe?

For example 100% of Rust crates ship the docs with the code.

True, and that’s actually a point for CoDoc, not against it. Rust already does the right thing. The question is what the other 90% of the whole software ecosystem is doing.

AI will happily skip the docs and just figure things out from the source code, which is usually better anyway.

Show us the evidence. Vercel’s evals say the opposite: 100% pass rate with bundled docs vs 53% without, on APIs absent from training data. It got it wrong 47% of the time. The docs weren’t skipped… they were the difference.

Using which model? They don’t say? Huh.

Let me save you some tokens: https://nextjs.org/evals

Frontier models very rarely hallucinate anymore, and they’re actually really good at writing tests now

How does that address a frontier-model hallucinating your v5 API signatures? Would you like to find this out at runtime and burn more tokens for the corrections?

Spoiler: If you look at the Next.js evals here you will see that even GPT 6 Astra (high) benefits from bundled documentation.

Not surprised that your neighbors haven’t heard of them…

What really surprises me is your claim here: “any software engineer worth their salt has” heard of Amadeus. So the bar for being a competent software engineer is now name-recognition of a specific travel-tech company? Let me pass that to HR: “have you heard of Amadeus?” is going straight into our next interviews.

And as for your AI-generated diatribe claim, I invite you to look up the meaning of diatribe. A well articulated and thought-provoking post is not a diatribe.

• Post and comment 100% written by a human, in case you had any doubts :)

Nope, no joke. Ask your neighbors if they have ever heard of Amadeus (the company), and if they reply affirmatively, let me know.

• CoDoc (Co-packaged Documentation) is a standard advocating for colocating AI-optimized documentation next to the code installed for each software library used in your project.

• Understand-Anything is a Claude Code plugin that maps your existing codebase into a knowledge graph.

They are complementary. Software libraries following CoDoc would supply additional files and directories for each dependency in your project enriching the output of the Understand Anything plugin.

I also understand that they solve different problems. CoDoc would allow an AI agent to operate in auto-pilot mode (with less AI slop) by having all the necessary context locally for all your project’s dependencies. CoDoc enables the AI agent.

Understand Anything maps your codebase to help you navigate and understand a complex codebase (it builds a JSON graph). Understand Anything enables the human software engineer.

They will retract the statement once data-center spending dries out ;)

They will retract the statement once data-center spending dries out ;)

You called it “pure drivel” and then quoted the one line that’s a file-naming convention, not the argument… The moat in CoDoc is that the documentation ships inside the package, version-matched, offline, deterministic. Can you tell me what proportion of software libraries today ship complete AI-optimized documentation within the library’s artifact? I’ll wait.

And to your frontier-model guess, the models behind the research agents are: Opus 5.5 and Astra. So no, not slop.

As for “open weight models are nowhere near the capabilities of frontier models”: sure, on raw benchmark scores (but they always end up catching up). Vercel’s evals on Next.js 16 APIs (absent from training data) show 100% pass rate with bundled docs vs 53% without. As stated in the post, the bottleneck for a 27B local model isn’t raw intelligence, it’s context. CoDoc fixes the context for free. A 27B on your laptop with the right context can beat a frontier model that’s hallucinating your v5 API signatures.

Keep letting the Goliaths vacuum your code, your tokens, and your money. The fizzy orange drink is on them.

P.S. Post and comment 100% written by a human, in case you had any doubts :)

Be our guest 👍

The LLM provider/creator would have to disclose this. Easier said than done but you would need open-source models and not just open-weight models.

We now have more capable hardware and there are different needs and constraints for web-development.

I would recommend Qwen4-27B + CoDoc

What is CoDoc? Have a look at the recent post I published so that you have all context (no pun intended) ;)

IMO, massive costs savings ahead for those that adopt the set-up above.