cd /news/large-language-models/pipeline-flow-or-chain-picking-the-r… · home topics large-language-models article
[ARTICLE · art-55390] src=dev.to ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Pipeline, Flow, or Chain? Picking the Right Tool to Wire LLM Calls Together

A developer building LLM workflows argues that choosing between chaining libraries and general orchestrators depends on whether the problem is LLM glue or reliable execution. The developer built PromptKit, a 4D toolkit for chaining prompts, to explore trade-offs like state management and failure handling. The post advises naming workflows honestly—chain, pipeline, flow, or agent—based on how much autonomy the system has.

read3 min views1 publishedJul 11, 2026

In the previous post I argued that agents are great

planners and DAGs are great executors. This one is the practical follow-up: when

you actually sit down to wire several LLM calls together, what tool do you reach for?

Because the moment one prompt's output feeds the next, you've built a workflow —

whether you call it that or not.

download transcript → summarize → translate
       (tool)          (LLM)       (LLM)

That tiny pipeline is already the whole problem in miniature: a non-LLM step (fetch a

YouTube transcript), then a model call, then another model call that depends on the

first. Run it as one giant prompt and you lose visibility; split it into steps and you

gain debuggability — at the cost of more calls and more state to manage.

Half the confusion is vocabulary. The same idea ships under a dozen labels:

Name What it whispers
Chain sequential, output → input
Pipeline stages, data flowing through
Flow branches and conditions
Workflow general orchestration
Agent workflow the model also decides

The word sets expectations. "Chain" promises a straight line; "agent workflow"

promises the thing might re-plan on you mid-run. Pick the label that matches how much

autonomy you're actually handing over — calling a deterministic two-step pipeline an

"agent" only invites disappointment.

There are two families of tools, and they solve different problems.

LLM-native chaining librariesLangChain,

LlamaIndex Workflows,

Azure Prompt Flow,

or visual layers like Flowise. These understand

LLM-specific concerns out of the box: prompt templating, passing context between

steps, token budgets, streaming, retries on a flaky model.

General orchestratorsAirflow,

Prefect, AWS Step Functions,

Azure Logic Apps. These treat

each LLM call as just another task in a DAG, and give you the heavyweight reliability

machinery: durable state, scheduling, checkpointing, audit trails, human approval.

The rule of thumb that falls out of the last post:

Few prompts, mostly LLM glue   → chaining library
Many steps, must not fail      → orchestrator (LLM call = one task)
The model decides the path     → agent, with one of the above underneath

Don't reach for a framework reflexively. If the task is genuinely simple, one well-crafted prompt (few-shot or chain-of-thought) often beats a three-step pipeline

To get a feel for the moving parts I built PromptKit,

a small 4D toolkit where a chain is just named prompts piped together — the YouTube

example above, minus the download step:

var $result:=$runner.newChain().prompt("summarize").prompt("translate").run($transcript)

// $result.text     -> final translated summary
// $result.outputs  -> each step's output, for inspection

Nothing exotic — but writing it made the trade-offs tangible: where state lives, what

happens when step two fails, how you'd add a branch. Which is really the point. You

don't pick the tool by reading the marketing; you pick it by knowing whether your

problem is LLM glue or reliable execution — and most of the time, it's a bit of

both.

My take: "chain vs. workflow vs. agent" is less an architecture question than an

honesty question — how deterministic is your process, really? Name it accordingly,

then pick the lightest tool that survives the day you actually need a retry.

── more in #large-language-models 4 stories · sorted by recency
── more on @langchain 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/pipeline-flow-or-cha…] indexed:0 read:3min 2026-07-11 ·