Almost all the points are not about what DSPy is mainly supposed to offer. What's supposedly great at is automatic optimization, for everything else... who the hell puts Python in production just to make some API calls? There are "frameworks" available in all the better languages, but the constructs behind are not that complicated. And why does DSPy even try to compete with LangChain/Graph/crap?

I don't see it at all.

> Typed I/O for every LLM call. Use Pydantic. Define what goes in and out.

Sure, not related to DSPy though, and completely tablestakes. Also not sure why the whole article assumes the only language in the world is Python.

> Separate prompts from code. Forces you to think about prompts as distinct things.

There's really no reason prompts must live in a file with a .md or .json or .txt extension rather than .py/.ts/.go/.., except if you indeed work at a company that decided it's a good idea to let random people change prod runtime behavior. If someone can think of a scenario where this is actually a good idea, feel free to elighten me. I don't see how it's any more advisable than editing code in prod while it's running.

> Composable units. Every LLM call should be testable, mockable, chainable.

> Abstract model calls. Make swapping GPT-4 for Claude a one-line change.

And LiteLLM or `ai` (Vercel), the actually most used packages, aren't? You're comparing downloads with Langchain, probably the worst package to gain popularity of the last decade. It was just first to market, then after a short while most realized it's horrifically architected, and now it's just coasting on former name recognition while everyone who needs to get shit done uses something lighter like the above two.

> Eval infrastructure early. Day one. How will you know if a change helped?

Sure, to an extent. Outside of programming, most things where LLMs deliver actual value are very nondeterministic with no right answer. That's exactly what they offer. Plenty of which an LLM can't judge the quality of. Having basic evals is useful, but you can quickly run into their development taking more time than it's worth.

But above all.. the comments on this post immediately make clear that the biggest differentiator of DSPy is the prompt optimization. Yet this article doesn't mention that at all? Weird.

> f"Extract the company name from: {text}"

I think one thing that's lost in all of the LLM tooling is that it's LLM-or-nothing and people have lost knowledge of other ML approaches that actually work just fine, like entity recognition.

I understand it's easier to just throw every problem at an LLM but there are things where off-the-shelf ML/NLP products work just as well without the latency or expense.

Loved the article because I exactly hit the stages all up till the 5th! Thank you for making me see the whole picture and journey!

I think a problem to DSPy is that they don't know the concept of THE WHOLE PRODUCT: https://en.wikipedia.org/wiki/Whole_product

Look at https://mastra.ai/ and https://www.copilotkit.ai/ to see how more inviting their pages look. A company is not selling only the product itself but all the other things around the product = THE WHOLE PRODUCT

A similar concept in developer tools is the docs are the product

Also I'm a fullstack javascript engineer and I don't use Python. Docs usually have a switch for the language at the top. Stripe.com is famous for it's docs and Developer Experience: https://docs.stripe.com/search#examples It's great to study other great products to get inspiration and copy the best traits that are relevant to your product as well.

Mannnn, here I thought this was going to be an informative article! But it’s just a commercial for the author’s consulting business.

I think the real problem with using DSPy is that many of the problems people are trying to solve with LLMs (agents, chat) don't have an obvious path to evaluate. You have to really think carefully on how to build up a training and evaluation dataset that you can throw to DSPy to get it to optimize.

This takes a ton of upfront work and careful thinking. As soon as you move the goalposts of what you're trying to achieve you also have to update the training and evaluation dataset to cover that new use case.

This can actually get in the way of moving fast. Often teams are not trying to optimize their prompts but even trying to figure out what the set of questions and right answers should be!

We build a product that's somewhat similar in spirit to DSPy, but people come to us for different reasons than the OP listed here.

1) It's slow: you first have to get acquainted with DSPY and then get hand-labeled data for prompt optimization. This can be a slow process so it's important to just label cases that are ambiguous, not obvious.

2) They know that manual prompt engineering is brittle, and want a prompt that's optimized and robust against a model they're invoking, which DSPy offers. However, it's really the optimizer (ex. GEPA) doing the heavy-lifting.

3) They don't actually want a model or prompt at all. They want a task completed, reliably, and they want that task to not regress in performance. Ideally, the task keeps improving in production.

Curious if folks in this thread feel more of these pains than the ones in the article.

I tried it in the past, one time “in earnest.” But when I discovered that none of my actual optimized prompts were extractable, I got cold feet and went a different route. The idea of needing to do fully commit to a framework scares me. The idea of having a computer optimize a prompt as a compilation step makes a lot of sense, but treating the underlying output prompt as an opaque blob doesn’t. Some of my use cases were JUST off of the beaten path that dspy was confusing, which didn’t help. And lastly, I felt like committing to dspy meant that I would be shutting the door on any other framework or tool or prompting approach down the road.

I think I might have just misunderstood how to use it.

Good article, and I think the "evolution of every AI system" is spot on.

In my opinion, the reason people don't use DSPy is because DSPy aims to be a machine learning platform. And like the article says -- this feels different or hard to people who are not used to engineering with probabilistic outputs. But these days, many more people are programming with probability machines than ever before.

The absolute biggest time sink and 'here be dragons' of using LLMs is poke and hope prompt "engineering" without proper evaluation metrics.

> You don’t have to use DSPy. But you should build like someone who understands why it exists.

And this is the salient point, and I think it's very well stated. It's not about the framework per se, but about the methodology.

It's not as ergonomic as they made it to be.

The fact that you have to bundle input+output signatures and everything is dynamically typed (sometimes into the args) just make it annoying to use in codebases that have type annotations everywhere.

Plus their out of the box agent loop has been a joke for the longest time, and writing your own if feasible but it's night and day when trying to get something done with pydantic-ai.

Too bad because it has a lot of nice things, I wish it were more popular.

Never heard of it, that is already a reason.

I used dspy in production, then reverted the bloat as it literally gave me nothing of added value in practice but a lot of friction when i needed precise control over the context. Avoid!

Main reason to me is that its layers on layer on top of the base LLM calls with not so much to show for it. Also a lot of native features (like for examples geminis native structured responses) aren't well supported.

https://www.tensorzero.com/docs has similar abstractions but doesn't require Python and doesn't require committing to the framework or a language. It's also pretty hard to onboard, but solves the same problems better and makes evaluating changes to models / prompts much easier to reason about.

This matches my experience with Dspy. I ended up removing it from our production codebase because, at the time, it didn't quite work as effectively as just using Pydantic and so forth.

The real killer feature is the prompt compilation; it's also the hardest to get to an effective place and I frequently found myself needing more control over the context than it would allow. This was a while ago, so things may have improved. But good evals are hard and the really fancy algorithms will burn a lot of tokens to optimize your prompts.

> Data extraction tasks are amongst the easiest to evaluate because there’s a known “right” answer.

Wrong. There can be a lot of subjectivity and pretending that some golden answer exists does more harm and narrows down the scope of what you can build.

My other main problem with data extraction tasks and why I'm not satisfied with any of the existing eval tools is that the schemas I write change can drastically as my understanding of the problem increases. And nothing really seems to handle that well, I mostly just resort to reading diffs of what happens when I change something and reading the input/output data very closely. Marimo is fantastic for anything visual like this btw.

> Abstract model calls. Make swapping GPT-4 for Claude a one-line change.

And in practice random limitations like structured output API schema limits between providers can make this non-trivial. God I hate the Gemini API.

If [programming_language] is so great, why isn't anyone using it?

For many of the same reasons. A plethora of alteratives, personal preference, weird ideology, appropriateness for the task, inertia, not-invented-here.

The list goes on.

i've tried it a few times and it's never really helped as much as i expected. though i know they've released a couple times since I last tried it.

If you find yourself adding a database because thats less painful than regular deployments from your version control, something is hair on fire levels of wrong with your CICD setup.

I consistently hear great things from Dspy users. At the same time, it feels like adoption is always low.

Stranger still: it seems like every company I have worked with ends up building a half-baked version of Dspy.

Would have been nice if the post actually showed how Dspy does the things that were handrolled

Curious what you think of https://github.com/pipevals/pipevals (author)

"Great engineers write bad AI code" made my day ;)

at /u/ sbpyane - very useful info and pricing page as well.

useful for upcoming consultants to learn how to price services too.

This article seemingly misses any explanation of what DSPy even is or why it's supposedly so complicated and unfamiliar. Supposedly it solves the problems illustrated in the article, but it isn't explained how.

>"Stage 2: “Can we tweak the prompt without deploying?”

Are we playing philosophy here? If you move some part of the code from the repo and into a database, then changing that database is still part of the deployment, but now you just made your versioning have identity crisis. Just put your prompts in your git repo and say no when someone requests an anti-pattern be implemented.

I think the entire premise that the prompting is the surface area for optimizing the application is fundamentally the wrong framing, in the same way that in 1998 better cpam will save CGI. It's solving the wrong problems now, and the limitations in context and model intelligence require a tool like Dspy.

The only thing I'd grab dspy for at this point is to automate the edges of the agentic pipeline that could be improved with RL patterns. But if that is true, you're really shorting yourself by giving your domain DSPY. You should be building your own RL learning loops.

My experience: If you find yourself reaching for a tool like Dspy, you might be sitting on a scenario where reinforcement learning approaches would help even further up the stack than your prompts, and you're probably missing where the real optimization win is. (Think bigger)

Nobody uses it except for maybe the weaviate developer advocates running those jupyter cells.

A lot of these ideas Dspy and RLM (from the same people IIRC) are more marketing than solving a real problem.

[dead]

[dead]

[dead]

[dead]