1 ready-to-build workflow

AI agent workflows for Education & EdTech

Answer admissions questions instantly and route serious enquiries to counsellors.

Each recipe below is expressed only in VegaDūta's real workflow building blocks — Trigger, Agent, Knowledge, Condition, Approval, Output, Tool (MCP), Voice, Device, Loop, Code and Parallel — so it maps 1:1 to something you can assemble in the Workflow designer. Consequential actions always pass a human Approval step.

1. Admissions enquiry → instant answers → counsellor callback

Prospective students ask the same admissions questions at all hours; counsellors can't keep up.

Trigger: Webhook (enquiry form) or WhatsApp

How the workflow runs

  1. Trigger

    Enquiry arrives. A Webhook or WhatsApp trigger starts the flow.

  2. Knowledge

    Answer from the prospectus. A Knowledge node answers fees, courses, eligibility and dates — grounded, with citations.

  3. Agent

    Nurture + gauge intent. An Agent node keeps the conversation going and scores readiness.

  4. Approval

    Book a counsellor. An Approval/Output node schedules a human callback for serious applicants.

Channels & connectors

  • Webhook
  • WhatsApp
  • Knowledge base
  • Approval / HITL

Outcome

Every enquiry gets accurate answers instantly; counsellors focus on applicants ready to commit.

Why it helps

Instant, accurate answers keep prospects warm; humans spend time where it converts.

Build spec

1 agent1 admissions agent; the counsellor booking is an Approval node.

System prompt (paste-ready)

You are an admissions assistant for {{institution}}. Answer prospective students' questions about fees, courses, eligibility and dates strictly from the prospectus in Knowledge, with citations — never invent a fee, deadline or eligibility rule. Keep the conversation going, answer follow-ups, and gauge how ready the applicant is. When someone is serious and ready, offer a counsellor callback. Be warm and factual; if you don't find an answer, say so and offer a human.

MCP connectors

  • WhatsApp — conversation channel
  • Enquiry form — inbound via Webhook trigger
  • Counsellor calendar — via a Tool (MCP) node

Built-in tools

  • knowledge_search (prospectus: fees, courses, eligibility, dates)

Guardrails

  • Grounded-only: fees, dates and eligibility come from the prospectus with citations, never invented
  • Serious applicants are booked with a human counsellor via the Approval node
  • Unanswerable questions defer to a human rather than guessing

Output & delivery

The agent answers from the prospectus with citations over WhatsApp and, for ready applicants, schedules a human counsellor callback through the Approval node.

Related industries

Build one of these in minutes

The sandbox gives you a live agent workspace — no account, no card. Or head back to the full catalogue and compare patterns across every industry.

See how VegaDūta compares to n8n, Dify and BotpressWhy VegaDūta's architectureEstimate your WhatsApp API costs