I’ve been making an attempt to know one of many newest AI coding buzzword: Spec-driven improvement (SDD). I checked out three of the instruments that label themselves as SDD instruments and tried to untangle what it means, as of now.
Definition
Like with many rising phrases on this fast-paced house, the definition of “spec-driven improvement” (SDD) continues to be in flux. Right here’s what I can collect from how I’ve seen it used to date: Spec-driven improvement means writing a “spec” earlier than writing code with AI (“documentation first”). The spec turns into the supply of reality for the human and the AI.
GitHub: “On this new world, sustaining software program means evolving specs. […] The lingua franca of improvement strikes to a better stage, and code is the last-mile method.”
Tessl: “A improvement method the place specs — not code — are the first artifact. Specs describe intent in structured, testable language, and brokers generate code to match them.”
After trying over the usages of the time period, and a number of the instruments that declare to be implementing SDD, it appears to me that in actuality, there are a number of implementation ranges to it:
- Spec-first: A effectively thought-out spec is written first, after which used within the AI-assisted improvement workflow for the duty at hand.
- Spec-anchored: The spec is stored even after the duty is full, to proceed utilizing it for evolution and upkeep of the respective characteristic.
- Spec-as-source: The spec is the principle supply file over time, and solely the spec is edited by the human, the human by no means touches the code.
All SDD approaches and definitions I’ve discovered are spec-first, however not all attempt to be spec-anchored or spec-as-source. And sometimes it’s left imprecise or completely open what the spec upkeep technique over time is supposed to be.
What’s a spec?
The important thing query by way of definitions in fact is: What’s a spec? There doesn’t appear to be a basic definition, the closest I’ve seen to a constant definition is the comparability of a spec to a “Product Necessities Doc”.
The time period is kind of overloaded in the meanwhile, right here is my try at defining what a spec is:
A spec is a structured, behavior-oriented artifact – or a set of associated artifacts – written in pure language that expresses software program performance and serves as steerage to AI coding brokers. Every variant of spec-driven improvement defines their method to a spec’s construction, stage of element, and the way these artifacts are organized inside a venture.
There’s a helpful distinction to be made I feel between specs and the extra basic context paperwork for a codebase. That basic context are issues like guidelines information, or excessive stage descriptions of the product and the codebase. Some instruments name this context a reminiscence financial institution, in order that’s what I’ll use right here. These information are related throughout all AI coding periods within the codebase, whereas specs solely related to the duties that really create or change that specific performance.
It seems to be fairly time-consuming to judge SDD instruments and approaches in a method that will get near actual utilization. You would need to strive them out with completely different sizes of issues, greenfield, brownfield, and actually take the time to evaluate and revise the intermediate artifacts with greater than only a cursory look. As a result of as GitHub’s weblog submit about spec-kit says: “Crucially, your function isn’t simply to steer. It’s to confirm. At every section, you mirror and refine.”
For 2 of the three instruments I attempted it additionally appears to be much more work to introduce them into an current codebase, due to this fact making it even more durable to judge their usefulness for brownfield codebases. Till I hear utilization stories from individuals utilizing them for a time period on a “actual” codebase, I nonetheless have a number of open questions on how this works in actual life.
That being stated – let’s get into three of those instruments. I’ll share an outline of how they work first (or slightly how I feel they work), and can preserve my observations and questions for the top. Observe that these instruments are very quick evolving, so they could have already modified since I used them in September.
Kiro
Kiro is the best (or most light-weight) one of many three I attempted. It appears to be largely spec-first, all of the examples I’ve discovered use it for a process, or a consumer story, with no point out of find out how to use the necessities doc in a spec-anchored method over time, throughout a number of duties.
Workflow: Necessities → Design → Duties
Every workflow step is represented by one markdown doc, and Kiro guides you thru these 3 workflow steps inside its VS Code primarily based distribution.
Necessities: Structured as a listing of necessities, the place every requirement represents a “Consumer Story” (in “As a…” format) with acceptance standards (in “GIVEN… WHEN… THEN…” format)
Design: In my try, the design doc consisted of the sections seen within the screenshot beneath. I solely have the outcomes of one in every of my makes an attempt nonetheless, so I’m undecided if it is a constant construction, or if it adjustments relying on the duty.
Duties: A listing of duties that hint again to the requirement numbers, and that get some further UI parts to run duties one after the other, and evaluate adjustments per process.
Kiro additionally has the idea of a reminiscence financial institution, they name it “steering”. Its contents are versatile, and their workflow doesn’t appear to depend on any particular information being there (I made my utilization makes an attempt earlier than I even found the steering part). The default topology created by Kiro while you ask it to generate steering paperwork is product.md, construction.md, tech.md.
Spec-kit
Spec-kit is GitHub’s model of SDD. It’s distributed as a CLI that may create workspace setups for a variety of frequent coding assistants. As soon as that construction is about up, you work together with spec-kit through slash instructions in your coding assistant. As a result of all of its artifacts are put proper into your workspace, that is probably the most customizable one of many three instruments mentioned right here.
Workflow: Structure → 𝄆 Specify → Plan → Duties 𝄇
Spec-kit’s reminiscence financial institution idea is a prerequisite for the spec-driven method. They name it a structure. The structure is meant to include the excessive stage ideas which might be “immutable” and may at all times be utilized, to each change. It’s principally a really highly effective guidelines file that’s closely utilized by the workflow.
In every of the workflow steps (specify, plan, duties), spec-kit instantiates a set of information and prompts with the assistance of a bash script and a few templates. The workflow then makes heavy use of checklists inside the information, to trace needed consumer clarifications, structure violations, analysis duties, and many others. They’re like a “definition of achieved” for every workflow step (although interpreted by AI, so there is no such thing as a 100% assure that they are going to be revered).
Under is an outline for example the file topology I noticed in spec-kit. Observe how one spec is made up of many information.
At first look, GitHub appears to be aspiring to a spec-anchored method (“That’s why we’re rethinking specs — not as static paperwork, however as residing, executable artifacts that evolve with the venture. Specs change into the shared supply of reality. When one thing doesn’t make sense, you return to the spec; when a venture grows advanced, you refine it; when duties really feel too massive, you break them down.”) Nonetheless, spec-kit creates a department for each spec that will get created, which appears to point that they see a spec as a residing artifact for the lifetime of a change request, not the lifetime of a characteristic. This group dialogue is speaking about this confusion. It makes me assume that spec-kit continues to be what I’d name spec-first solely, not spec-anchored over time.
Tessl Framework
(Nonetheless in non-public beta)
Like spec-kit, the Tessl Framework is distributed as a CLI that may create all of the workspace and config construction for a wide range of coding assistants. The CLI command additionally doubles as an MCP server.
Tessl is the one one in every of these three instruments that explicitly aspires to a spec-anchored method, and is even exploring the spec-as-source stage of SDD. A Tessl spec can function the principle artifact that’s being maintained and edited, with the code even marked with a remark on the prime saying // GENERATED FROM SPEC - DO NOT EDIT. That is presently a 1:1 mapping between spec and code information, i.e. one spec interprets into one file within the codebase. However Tessl continues to be in beta and they’re experimenting with completely different variations of this, so I can think about that this method may be taken on a stage the place one spec maps to a code part with a number of information. It stays to be seen what the alpha product will help. (The Tessl crew themselves see their framework as one thing that’s extra sooner or later than their present public product, the Tessl Registry.)
Right here is an instance of a spec that I had the Tessl CLI reverse engineer (tessl doc --code ...js) from a JavaScript file in an current codebase:
Tags like @generate or @take a look at appear to inform Tessl what to generate. The API part exhibits the concept of defining not less than the interfaces that get uncovered to different elements of the codebase within the spec, presumably to ensure that these extra essential elements of the generated part are absolutely below the management of the maintainer. Working tessl construct for this spec generates the corresponding JavaScript code file.
Placing the specs for spec-as-source at a fairly low abstraction stage, per code file, in all probability reduces quantity of steps and interpretations the LLM has to do, and due to this fact the prospect of errors. Even at this low abstraction stage I’ve seen the non-determinism in motion although, once I generated code a number of occasions from the identical spec. It was an attention-grabbing train to iterate on the spec and make it increasingly more particular to extend the repeatability of the code technology. That course of jogged my memory of a number of the pitfalls and challenges of writing an unambiguous and full specification.
Observations and questions
These three instruments are all labelling themselves as implementations of spec-driven improvement, however they’re fairly completely different from one another. In order that’s the very first thing to remember when speaking about SDD, it isn’t only one factor.
One workflow to suit all sizes?
Kiro and spec-kit present one opinionated workflow every, however I’m fairly positive that neither of them is appropriate for almost all of actual life coding issues. Particularly, it’s not fairly clear to me how they’d cater to sufficient completely different downside sizes to be usually relevant.
Once I requested Kiro to repair a small bug (it was the identical one I used up to now to strive Codex), it shortly grew to become clear that the workflow was like utilizing a sledgehammer to crack a nut. The necessities doc turned this small bug into 4 “consumer tales” with a complete of 16 acceptance standards, together with gems like “Consumer story: As a developer, I would like the transformation operate to deal with edge circumstances gracefully, in order that the system stays sturdy when new class codecs are launched.”
I had an identical problem once I used spec-kit, I wasn’t fairly positive what dimension of downside to make use of it for. Out there tutorials are normally primarily based on creating an software from scratch, as a result of that’s best for a tutorial. One of many use circumstances I ended up making an attempt was a characteristic that may be a 3-5 level story on one in every of my previous groups. The characteristic trusted a number of code that was already there, it was supposed to construct an outline modal that summarised a bunch of information from an current dashboard. With the quantity of steps spec-kit took, and the quantity of markdown information it created for me to evaluate, this once more felt like overkill for the dimensions of the issue. It was an even bigger downside than the one I used with Kiro, but in addition a way more elaborate workflow. I by no means even completed the total implementation, however I feel in the identical time it took me to run and evaluate the spec-kit outcomes I may have carried out the characteristic with “plain” AI-assisted coding, and I’d have felt rather more in management.
An efficient SDD device would on the very least have to offer flexibility for a couple of completely different core workflows, for various sizes and forms of adjustments.
Reviewing markdown over reviewing code?
As simply talked about, and as you’ll be able to see within the description of the device above, spec-kit created a LOT of markdown information for me to evaluate. They have been repetitive, each with one another, and with the code that already existed. Some contained code already. Total they have been simply very verbose and tedious to evaluate. In Kiro it was somewhat simpler, as you solely get 3 information, and it’s extra intuitive to know the psychological mannequin of “necessities > design > duties”. Nonetheless, as talked about, Kiro additionally was method too verbose for the small bug I used to be asking it to repair.
To be trustworthy, I’d slightly evaluate code than all these markdown information. An efficient SDD device must present an excellent spec evaluate expertise.
False sense of management?
Even with all of those information and templates and prompts and workflows and checklists, I continuously noticed the agent in the end not observe all of the directions. Sure, the context home windows at the moment are bigger, which is usually talked about as one of many enablers of spec-driven improvement. However simply because the home windows are bigger, doesn’t imply that AI will correctly decide up on every little thing that’s in there.
For instance: Spec-kit has a analysis step someplace throughout planning, and it did a number of analysis on the present code and what’s already there, which was nice as a result of I requested it so as to add a characteristic that constructed on prime of current code. However in the end the agent ignored the notes that these have been descriptions of current courses, it simply took them as a brand new specification and generated them once more, creating duplicates. However I didn’t solely see examples of ignoring directions, I additionally noticed the agent go method overboard as a result of it was too eagerly following directions (e.g. one of many structure articles).
The previous has proven that one of the simplest ways for us to remain accountable for what we’re constructing are small, iterative steps, so I’m very skeptical that a number of up-front spec design is a good suggestion, particularly when it’s overly verbose. An efficient SDD device must cater to an iterative method, however small work packages nearly appear counter to the concept of SDD.
The best way to successfully separate practical from technical spec?
It’s a frequent thought in SDD to be intentional in regards to the separation between practical spec and technical implementation. The underlying aspiration I assume is that in the end, we may have AI fill in all of the solutioning and particulars, and change to completely different tech stacks with the identical spec.
In actuality, once I was making an attempt spec-kit, I continuously acquired confused when to remain on the practical stage, and when it was time so as to add technical particulars. The tutorial and documentation additionally weren’t fairly per it, there appear to be completely different interpretations of what “purely practical” actually means. And once I assume again on the various, many consumer tales I’ve learn in my profession that weren’t correctly separating necessities from implementation, I don’t assume now we have a great observe report as a career to do that effectively.
Who’s the goal consumer?
Lots of the demos and tutorials for spec-driven improvement instruments embrace issues like defining product and have targets, they even incorporate phrases like “consumer story”. The concept right here may be to make use of AI as an enabler for cross-skilling, and have builders take part extra closely in necessities evaluation? Or have builders pair with product individuals after they work on this workflow? None of that is made express although, it’s offered as a given {that a} developer would do all this evaluation.
Wherein case I’d ask myself once more, what downside dimension and sort is SDD meant for? In all probability not for big options which might be nonetheless very unclear, as certainly that may require extra specialist product and necessities expertise, and plenty of different steps like analysis and stakeholder involvement?
Spec-anchored and spec-as-source: Are we studying from the previous?
Whereas many individuals draw analogies between SDD and TDD or BDD, I feel one other essential parallel to have a look at for spec-as-source particularly is MDD (model-driven improvement). I labored on a couple of initiatives at the start of my profession that closely used MDD, and I stored being reminded about that once I was making an attempt out the Tessl Framework. The fashions in MDD have been principally the specs, albeit not in pure language, however expressed in e.g. customized UML or a textual DSL. We constructed customized code turbines to show these specs into code.
Finally, MDD by no means took off for enterprise functions, it sits at a clumsy abstraction stage and simply creates an excessive amount of overhead and constraints. However LLMs take a number of the overhead and constraints of MDD away, so there’s a new hope that we are able to now lastly concentrate on writing specs and simply generate code from them. With LLMs, we’re not constrained by a predefined and parseable spec language anymore, and we don’t need to construct elaborate code turbines. The worth for that’s LLMs’ non-determinism in fact. And the parseable construction additionally had upsides that we’re shedding now: We may present the spec writer with a number of device help to jot down legitimate, full and constant specs. I’m wondering if spec-as-source, and even spec-anchoring, may find yourself with the downsides of each MDD and LLMs: Inflexibility and non-determinism.
To be clear, I’m not nostalgic about my MDD expertise up to now and saying “we’d as effectively deliver that again”. However we should always look to code-from-spec makes an attempt up to now to study from them once we discover spec-driven immediately.
Conclusions
In my private utilization of AI-assisted coding, I additionally typically spend time on rigorously crafting some type of spec first to present to the coding agent. So the final precept of spec-first is unquestionably invaluable in lots of conditions, and the completely different approaches of find out how to construction that spec are very wanted. They’re among the many prime most continuously requested questions I hear in the meanwhile from practitioners: “How do I construction my reminiscence financial institution?”, “How do I write a great specification and design doc for AI?”.
However the time period “spec-driven improvement” isn’t very effectively outlined but, and it’s already semantically subtle. I’ve even not too long ago heard individuals use “spec” principally as a synonym for “detailed immediate”.
Relating to the instruments I’ve tried, I’ve listed a lot of my questions on their actual world usefulness right here. I’m wondering if a few of them try to feed AI brokers with our current workflows too actually, in the end amplifying current challenges like evaluate overload and hallucinations. Particularly with the extra elaborate approaches that create a number of information, I can’t assist however consider the German compound phrase “Verschlimmbesserung”: Are we making one thing worse within the try of constructing it higher?
