Bridging Pendo Product Telemetry into an AI Knowledge Graph with Cognee

Description and use

Connecting Pendo to Cognee automatically extracts and semantically enriches product telemetry, converting it into a knowledge graph that lets product managers and AI agents answer qualitative questions without manual exports.

Problem

Product managers and AI agents cannot easily answer qualitative questions from Pendo telemetry without writing complex CSV exports or Segment queries.

Outcome

The connector automatically extracts and semantically enriches Pendo data, allowing agents to answer questions like "Which enterprise accounts struggled with our latest SSO migration guide?" without manual exports.

Workflow

• Install the connector with pip
• Create a PendoSource instance with integration key and optional flags
• Add the source to Cognee memory
• Run cognee.cognify on the dataset
• Query the knowledge graph with cognee.search

Evidence

Yet, when product managers or AI agents want to answer fundamental qualitative questions—like "Which enterprise accounts struggled with our latest SSO migration guide?"—they are forced to write multi-tab CSV exports or complex Segment queries.

Source

To bridge this gap, we built and shipped the Pendo Connector for Cognee.

Source

pip install cognee-community-connector-pendo

Source

uv run pytest packages/connector/pendo/tests/test_pendo.py -v

Source