Back to projects
AI Agent2026

Ticket Triage Agent

An autonomous support-triage agent — hand-rolled, no LangChain.

Ticket Triage Agent — An autonomous support-triage agent — hand-rolled, no LangChain.

The problem

Support teams drown in repetitive tickets, but full automation is risky: a wrong auto-reply on a billing issue, or one leaking a card number, is worse than a slow human.

The solution

A from-scratch agent that classifies a ticket, enriches it via tool-use lookups, then auto-resolves, drafts for review, or escalates. Confidence thresholds and guardrails decide when a human must stay in the loop.

What it does

  • Hand-rolled agent loop — no framework
  • Tool-use with validated schemas + Pydantic v2 structured output
  • Confidence-gated escalation & human-in-the-loop
  • Guardrails: PII detection, prompt-injection heuristics, output filtering
  • Offline eval harness — 45 tests, 98% coverage, no API key required

How it works

  1. 1

    Guard the input

    Incoming tickets pass input guardrails; injection or invalid content is escalated immediately.

  2. 2

    Loop with tools

    The LLM backend proposes steps; a ToolRegistry validates arguments and executes knowledge-base and CRM lookups.

  3. 3

    Decide by policy

    A policy engine gates the terminal action on confidence and category — safe & confident auto-resolves, billing/legal drafts for review, PII leaks escalate.

Architecture

Click a node to see what it does.

How it looks

The optional web UI and a real, unedited CLI run — classified, KB-matched, decided by policy.

Tech stack

  • Python 3.11
  • Pydantic v2
  • Tool-use
  • pytest