LangChain Irrelevance

Observations that Anthropic doesn't use LangChain or LangGraph, preferring prompt-based orchestration, questioning the value of these frameworks

The revelation that Anthropic’s Claude Code utilizes prompt-based orchestration rather than frameworks like LangChain has sparked a debate over whether these abstraction layers are becoming obsolete for serious AI development. Critics argue that LangChain is often overly opinionated and restrictive, suggesting that sophisticated prompting and standard code offer more flexibility for dynamic, multi-agent coordination. While some defenders maintain that state-graph frameworks remain valuable for observability and deterministic production workflows, others point out a growing gap between "prompt-based guidance" and the structural governance—such as hard-coded voting logic or mandatory human thresholds—needed for true agentic control. Ultimately, the discussion suggests that as model capabilities increase, the need for heavy orchestration frameworks may diminish in favor of more fluid, instruction-driven architectures.

View on HN · Topics

> The multi-agent coordinator mode in coordinatorMode.ts is also worth a look. The whole orchestration algorithm is a prompt, not code.

So much for langchain and langraph!! I mean if Anthropic themselves arent using it and using a prompt then what’s the big deal about langchain

View on HN · Topics

Langchain is for model-agnostic composition. Claude Code only uses one interface to hoist its own models so zero need for an abstraction layer.

Langgraph is for multi-agent orchestration as state graphs. This isn't useful for Claude Code as there is no multi-agent chaining. It uses a single coordinator agent that spawns subagents on demand. Basically too dynamic to constrain to state graphs.

View on HN · Topics

You may have a point but to drive it further, can you give an example of a thing I can do with langgraph that I can't do with Claude Code?

View on HN · Topics

I'm not an supporter of blindly adopting the "langs" but langgraph is useful for deterministically reproducable orchestration. Let's say you have a particular data flow that takes an email sends it through an agent for keyword analysis the another agent for embedding then splits to two agents for sentiment analysis and translation - there is where you'd use langgraph in your service. Claude Code is a consumer tool, not production.

View on HN · Topics

I see what you mean. Maybe in the cases where the steps are deterministic, it might be worth moving the coordination at the code layer instead of AI layer.

What's the value add over doing it with just Python code? I mean you can represent any logic in terms of graphs and states..

View on HN · Topics

Most of the value I’ve gotten out of is has been observability. Graph and DAG workflow abstractions just help OTel structure your LLM logs in a clean hierarchy of spans. I could imagine figuring out a better solution to this than the whole graph abstraction.

Other than that I’m not too sure.

View on HN · Topics

nobody serious uses langchain. The biggest agent products are coding tools, and I doubt any of them use langchain

View on HN · Topics

You didn't even use it yet.

View on HN · Topics

I've tried to use langchain. It seemed to force code into their way of doing things and was deeply opinionated about things that didn't matter like prompt templating. Maybe it's improved since then, but I've sort of used people who think langchain is good as a proxy for people who haven't used much ai?

View on HN · Topics

The Claude Code leak suggests multi-agent orchestration is largely driven by prompts (e.g., “do not rubber-stamp weak work”), with code handling execution rather than enforcing decisions.

Prompts are not hard constraints—they can be interpreted, deprioritized, or reasoned around, especially as models become more capable.

From what’s visible, there’s no clear evidence of structural governance like voting systems, hard thresholds, or mandatory human escalation. That means control appears to be policy (prompts), not enforcement (code).

This raises the core issue:
If governance is “prompts all the way down,” it’s not true governance—it’s guidance.

And as model capability increases, that kind of governance doesn’t get stronger—it becomes easier to bypass without structural constraints.

Has anyone actually implemented structural governance for agent swarms — voting logic, hard thresholds, REQUIRES_HUMAN as architecture not instruction?

Summarizer