Workflow examples

Ready-made graphs — copy the nodes into your editor or open as a new project.

Support bot (RAG + agent)

Answers customers from your own policies and price list, and does not invent what it could not find. The core of a first-line bot.

Finds the right fragment in your documents and passes it on — no retelling by the model.

Takes the routine delivery, payment and refund questions off a human: one system prompt, nothing else.

Turns the free text of a request or an email into fields — so they can be stored, counted or passed on.

Answers from fresh data on the web and shows its sources — for when the answer is not in your documents.

Remembers what was said earlier, so the customer does not have to repeat themselves every turn.

A minimal workflow — entry, an LLM agent and an answer. The basis for any chatbot.

Takes a long text and returns a short summary in a given format.

Translates incoming text into a requested language, preserving tone and formatting.

The model's answer passes through a Jinja template — one consistent shape for every reply.