LangSmith Agent Engineering Platform (Self-Hosted)

What do you like best about the product?

What I like best about LangChain is the flexibility it gives me to experiment with AI without feeling locked into one specific setup. I can connect different models, data sources, and tools and see how they work together for a particular use case.

What do you dislike about the product?

The biggest challenge for me with LangChain is the learning curve. There are a lot of concepts, components, and different ways to approach the same task, so it can feel overwhelming when you're still getting familiar with the platform.

I've also found that troubleshooting isn't always straightforward. Sometimes a workflow that seems fairly simple can require more configuration than expected, and when something doesn't work, it can take time to figure out exactly where the issue is coming from.

What problems is the product solving and how is that benefiting you?

LangChain helps me bridge the gap between having an idea for an AI solution and actually testing how it could work in practice. Instead of working with an AI model in isolation, I can connect it to different tools, information sources, and processes to create something more useful.

What do you like best about the product?

I can use it with any model provider. Switching between models is easy.

What do you dislike about the product?

I find it very unstable, with every new release my project breaks.

What problems is the product solving and how is that benefiting you?

I’m using it to build an autonomous API testing framework that can detect backend APIs and generate automation code within the automation framework.

What do you like best about the product?

LangChain allows you to connect LLMs to your apps, data sources, and external tools with ease. Provides helpful building blocks if you want to build applications that need workflows such as searching documents, RAG-based applications, or AI assistants without starting from scratch. Great if you already know how to code APIs/backend but want some guidance on how to chain them together with LLMs.

What do you dislike about the product?

Documentation is getting there but sometimes you have to experiment to see what works best for your use case.

What problems is the product solving and how is that benefiting you?

LangChain allows us to abstract some of the heavy lifting of stitching AI into our applications. Rather than having to manually connect models to APIs/data sources/etc. we can build repeatable AI workflows much quicker. Has increased dev velocity on projects involving smart search, automation, and AI assistants.

What do you like best about the product?

I like best about langchain is that it makes working with LLM much easier I like the flexibility it provides for connecting models with tools,data and API

What do you dislike about the product?

It can feel a little complex first especially with number of concepts and available components.

What problems is the product solving and how is that benefiting you?

Langchain solves the hassle of managing different part of an LLM application in one place.It makes it easier to connect models with data,tools and API.

What do you like best about the product?

It makes building LLM apps easier by handling chains, tools, prompts, and integrations. For me, Lang chain provides good value considering how much development time it can save. I don't have to build the whole LLM workflow, prompt handling, retrieval, and tool integration from scratch. There is still some overhead when projects get more complex, and debugging can take time, but I think the flexibility and integrations make it worth the cost, especially when working on multiple AI features or prototypes.

What do you dislike about the product?

Some abstractions feel heavy, and debugging chains can get tricky when workflows become complex.

What problems is the product solving and how is that benefiting you?

LangChain helps me speed up the development of LLM-based features without building everything from scratch. I mainly use it for managing prompts, connecting models with tools, handling retrieval, and building multi-step workflows. It also makes it easier to experiment with different models and integrations. From a development point of view, it saves time during prototyping and lets me focus more on the actual application logic instead of writing a lot of boilerplate code.

What do you like best about the product?

What I like most about LangChain is that it lowers the barrier to just trying something. You want to swap GPT-4 for Claude to see which handles your use case better — that's like a two-line change instead of rewriting your whole app. When you're still figuring out what you're building, that flexibility is worth a lot.

What do you dislike about the product?

It's smooth right up until you need to bend it a little — then you're suddenly wrestling with the framework to make it do something it wasn't quite built for, when honestly, just writing those fifteen lines yourself would've taken less time and less heartache.

What problems is the product solving and how is that benefiting you?

Provider lock-in — swap between OpenAI, Anthropic, or a local model without rewriting your whole app. Big win when you're still shopping around for what works best. Prototyping speed — going from idea to working demo is genuinely faster, since a lot of the scaffolding already exists.

Recommendations to others considering the product:

Provider lock-in — swap between OpenAI, Anthropic, or a local model without rewriting your whole app. Big win when you're still shopping around for what works best. Prototyping speed — going from idea to working demo is genuinely faster, since a lot of the scaffolding already exists.

What do you like best about the product?

I like how LangChain makes it easier to connect LLMs with prompts, tools, APIs, and external data. As a developer, it helps me build AI workflows faster without managing every integration separately. For me, the value is good because LangChain reduces the amount of development work needed when building LLM applications. I can reuse components for prompts, model integrations, retrieval, and workflows instead of creating everything from scratch. The main value comes from saving development time and making experimentation easier. I think the cost is reasonable when the framework is being used regularly in projects. There can be some extra effort in understanding the abstractions at first, but once you get comfortable with them, the overall productivity benefit makes it worthwhile.

What do you dislike about the product?

The main thing I dislike is that it can feel a bit complex at first. Some abstractions add extra overhead, and debugging chains can take time when something goes wrong.

What problems is the product solving and how is that benefiting you?

LangChain helps us simplify the development of AI applications by providing a common framework for working with LLMs, prompts, tools, APIs, and external data. Instead of building every integration from scratch, I can use its components to create and test workflows more quickly. This is useful when building applications that need retrieval, tool calling, or multi-step processing. From a business perspective, it helps reduce development effort and makes it easier to experiment with AI use cases. It also gives the team a more structured way to maintain and improve AI workflows as the requirements change.

What do you like best about the product?

Makes LLM development easier, with simple integrations and flexible workflows.

What do you dislike about the product?

The setup can feel confusing, and debugging sometimes takes more time than expected.

What problems is the product solving and how is that benefiting you?

LangChain helps solve the challenge of connecting different parts of an AI application in one place. Instead of handling model calls, prompts, data retrieval, tools, and workflows separately, I can manage them through a more structured framework. This saves development time and makes experimentation much easier. I also find it useful when working with external APIs, databases, and retrieval-based applications. Overall, it reduces repetitive integration work and gives me a cleaner way to build, test, and maintain LLM-based applications without creating every component from scratch.

What do you like best about the product?

The thing I like about it is that it very easily connects me to different databases and AI models.

What do you dislike about the product?

I don't like when our app breaks we have to search and dig through multiple layers of hidden code to find error, that is very frustrating.

What problems is the product solving and how is that benefiting you?

Anytime I can easily change or swap my AI model because of this with one line of code whenever there are changes in price or performance.

What do you like best about the product?

What I like most about LangChain is how it simplifies building AI applications by connecting models with tools, data sources, and custom workflows. It gives me a flexible structure for experimenting with different approaches without having to build every integration from scratch.

What do you dislike about the product?

One thing I dislike about LangChain is that the framework can feel overly complex for smaller projects. There are many abstractions and components to understand, and sometimes figuring out the right way to implement a simple workflow takes more effort than expected.

What problems is the product solving and how is that benefiting you?

LangChain helps solve the challenge of turning standalone language models into useful, connected applications. It makes it easier to manage prompts, tool calls, external data, and multi-step workflows in one framework. For me, this reduces development time and makes it easier to test and improve AI features without building the underlying connections from scratch.