NetPulse AI - Telecom incident ticketing in seconds

From customer complaint to NOC ticket
in seconds.

Multi-agent assistant on Google ADK + Vertex AI Gemini. MCP Toolbox serves five parameterized SQL tools over a bundled SQLite store; the response formatter persists every ticket back to the same file.

4 ADK sub-agents · SequentialAgent root · MCP Toolbox · SQLite

Launch NetPulse AI View on GitHub

SequentialAgent 4 · all on Gemini

IN Slow internet in Jakarta during peak hours

01 Classifier tags category

02 Net Inv. reads SQLite

03 CDR Anlz. queries SQLite

04 Formatter writes ticket

native tool SQLite · R SQLite · R SQLite · W

OUT Ticket #35

network Jakarta critical

Monitor backbone stability after the recent failover; conduct post-incident review of backhaul path.

/ 01 — How it works

Four agents, one ticket.

A complaint enters the chat. Four ADK sub-agents run in sequence — each one reads the shared session state, queries its data store, and enriches the state for the next. The fourth writes the ticket and the run ends.

Full architecture

IN Customer complaint Flask · SSE chat

→ prompt customer_complaint

01 Classifier Tags category & region from raw complaint text.

Gemini native tool

→ emits category, region

02 Network Investigator Pulls related outages from the bundled SQLite store.

Gemini SQLite · MCP

→ emits network_findings

03 CDR Analyzer Queries call records via parameterized SQL through MCP Toolbox.

Gemini SQLite · MCP

→ emits cdr_findings

04 Response Formatter Synthesises & persists the incident ticket.

Gemini SQLite · INSERT

→ emits incident_tickets

OUT Incident ticket SQLite · NOC dispatch

→ persists incident_report

/ 02 — Data Viewer

The data behind every ticket.

Read-only views into the live sources the agents query — for poking at edge cases, validating fixtures, or seeing what the system saw before writing a ticket.

All sources

SQLite · indexed