Support Triage — CrewAI

Classify an inbound message, propose a first reply hold, and flag escalation — human sends. (CrewAI multi-agent Python sketch for one job.)

Id: crewai/support-triage · Slug: support-triage · Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

What is this

AI Team for CrewAI. Classify an inbound message, propose a first reply hold, and flag escalation — human sends. (CrewAI multi-agent Python sketch for one job.)

How this runtime fits

This CrewAI sketch is a AI Team implementation typed as AI Team in the catalog. Where roles coordinate, it is fair to call it an agent team or multi-agent system — not a swarm.

Parent AI Team: support-triage · What is an AI Team?

What it does

Classify an inbound message, propose a first reply hold, and flag escalation — human sends. (CrewAI multi-agent Python sketch for one job.)

Who for

Builders working on Support jobs who can run CrewAI themselves.

Works with

Need to run

You will run this locally or on infra you control.
No production credentials in prompts or committed files.
Python 3.10+
CrewAI in a venv
Local or keyed LLM endpoint with budget awareness

How to use

Create a venv; install CrewAI (pin versions yourself).
Configure a local OpenAI-compatible base URL when possible.
Save crew_support_triage.py and run: python crew_support_triage.py
Replace PASTE_EXAMPLE_IN with your real input.
Read Pass/Fail gate output before trusting the draft.

Limitations

Not a substitute for professional legal, medical, or investment advice.
Outputs can be wrong; human review required before publish or spend.
Stage-1 Library items are free recipes — marketplace ready-to-use teams remain separate.
Do not attach billing cloud LLM nodes without a human budget check.
No harvesting of personal data beyond what the operator pasted.

Test status

Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

Files

crew_support_triage.py — CrewAI agents + tasks
requirements-hint.txt — Suggested packages (pin yourself)

Full prompt / config / code

# crew_support_triage.py — Support Triage (CrewAI)
# Safety: local/OpenAI-compatible endpoint preferred. No keys in source.
# pip install crewai  (pin versions yourself)

from crewai import Agent, Task, Crew, Process

SYSTEM = """You are a support triage assistant. Goal: classify and draft a hold reply.

RULES:
- Human sends the message. You do not send email/chat.
- Never ask for passwords, seed phrases, or full card numbers.
- Escalate billing disputes and safety issues.
- Keep the hold reply short and kind.

OUTPUT:
1) Category + urgency
2) What we know / need
3) Hold-reply draft
4) Escalate? yes/no + why"""

GOAL = "Classify an inbound message, propose a first reply hold, and flag escalation \u2014 human sends."

lead = Agent(
    role="Support Triage lead",
    goal=GOAL,
    backstory="Local BotShelf operator. One job, then stop. No spend. No destructive tools.",
    allow_delegation=False,
    verbose=False,
)

reviewer = Agent(
    role="Quality gate",
    goal="Check the lead output against the required sections; list gaps only.",
    backstory="Pedantic reviewer. Does not invent facts.",
    allow_delegation=False,
    verbose=False,
)

produce = Task(
    description=(
        "Follow SYSTEM strictly.\n\nSYSTEM:\n" + SYSTEM +
        "\n\nUSER INPUT:\n{user_input}"
    ),
    expected_output="Complete Support Triage structured result.",
    agent=lead,
)

gate = Task(
    description=(
        "Verify the previous result has all required sections. "
        "Return Pass/Fail + missing sections. Do not rewrite creatively."
    ),
    expected_output="Pass/Fail and gap list.",
    agent=reviewer,
)

crew = Crew(
    agents=[lead, reviewer],
    tasks=[produce, gate],
    process=Process.sequential,
)

def run(user_input: str) -> str:
    return str(crew.kickoff(inputs={"user_input": user_input}))

if __name__ == "__main__":
    print(run("PASTE_EXAMPLE_IN"))

Example in

From: user@example.com
Subject: charged twice?
Body: I see two USDT sends. Order #1842. Need help.

Example out

Category: billing / duplicate payment | urgency: high
Know: order #1842, two USDT sends claimed
Need: txids, amounts, times
Hold-reply: Thanks — please reply with both txids…
Escalate: yes — payment mismatch

Model / runtime notes

Two-agent crew (produce + gate). Keep tools disabled unless you add read-only tools on purpose.

Canonical Team

Parent: support-triage · implementation_id: crewai/support-triage

GitHub source

teams/support-triage/crewai · commit eb87e8e049fdf9908e438305ff827c7b617505b5 · license: free-use-at-own-risk

Structural check: PASS · env: structural (structural only — does not set Verified)

Related Library items

Related marketplace Team pages

Soft thematic links only — not identity merges. Marketplace Teams ≠ Library AI Team records.

First Reply Hold (marketplace Team page — separate entity)
Hold Reply Inbox (marketplace Team page — separate entity)