Kotlin creator's new language: talk to LLMs in specs, not English

Rehashing my comment from before:

I use Kiro IDE (≠ Kiro CLI) primarily as a spec generator. In my experience, it's high-quality for creating and iterating on specs. Tools like Cursor are optimized for human-driven vibing -- they have great autocomplete, etc. Kiro, by contrast, is optimized around spec, which ironically has been the most effective approach I've found for driving agents.

I'd argue that Cursor, Antigravity, and similar tools are optimized for human steering, which explains their popularity, while Kiro is optimized for agent harnesses. That's also why it’s underused: it's quite opinionated, but very effective. Vibe-coding culture isn't sold on spec driven development (they think it's waterfall and summarily dismiss it -- even Yegge has this bias), so people tend to underrate it.

Kiro writes specs using structured formats like EARS and INCOSE (which is the spc format used in places like Boeing for engineering reqs). It performs automated reasoning to check for consistency, then generates a design document and task list from the spec -- similar to what Beads does. I usually spend a significant amount of time pressure-testing the spec before implementing (often hours to days), and it pays off. Writing a good, consistent spec is essentially the computer equivalent of "writing as a tool of thought" in practice.

Once the spec is tight, implementation tends to follow it closely. Kiro also generates property-based tests (PBTs) using Hypothesis in Python, inspired by Haskell's QuickCheck. These tests sweep the input domain and, when combined with traditional scenario-based unit tests, tend to produce code that adheres closely to the spec. I also add a small instruction "do red/green TDD" (I learned this from Simon Willison) and that one line alone improved the quality of all my tests. Kiro can technically implement the task list itself, but this is where agents come in. With the spec in hand, I use multiple headless CLI agents in tmux (e.g., Kiro CLI, Claude Code) for implementation. The results have been very good. With a solid Kiro spec and task list, agents usually implement everything end-to-end without stopping -- I haven’t found a need for Ralph loops. (agents sometimes tend to stop mid way on Claude plans, but I've never had that happen with Kiro, not sure why, maybe it's the checklist, which includes PBT tests as gates).

didn't have the strongest start, but the Kiro IDE is one of the best spec generators I've used, and it integrates extremely well with agent-driven workflows.

Validating programs against a formal spec is very, very hard for foundational computational complexity reasons. There's a reason why the largest programs whose code was fully verified against a formal spec, and at an enormous cost, were ~10KLOC. If you want to do it using proofs, then lines of proof outnumber lines of code 10-1000 to 1, and the work is far harder than for proofs in mathematics (that are typically much shorter). There are less absolute ways of checking spec conformance at some useful level of confidence, and they can be worthwhile, but they require expertise and care (I'm very much in favour of using them, but the thought that AI can "just" prove conformance to a formal spec ignores the computational complexity results in that field).

> but proving correctness is one of those basically impossible tasks.

To aim for a meeting of the minds... Would you help me out and unpack what you mean so there is less ambiguity? This might be minor terminological confusion. It is possible we have different takes, though -- that's what I'm trying to figure out.

There are at least two senses of 'correctness' that people sometimes mean: (a) correctness relative to a formal spec: this is expensive but doable*; (b) confidence that a spec matches human intent: IMO, usually a messy decision involving governance, organizational priorities, and resource constraints.

Sometimes people refer to software correctness problems in a very general sense, but I find it hard to parse those. I'm familiar with particular theoretical results such as Rice's theorem and the halting problem that pertain to arbitrary programs.

* With tools like {Lean, Dafny, Verus, Coq} and in projects like {CompCert, sel4}.

The next step is to use AI to edit the spec... /s

All my self-hosted inference has temperature zero and no randomness.

It is absolutely workable, current inference engines are just lazy and dumb.

(I use a Zobrist hash to track and prune loops.)