Loading…
Loading…
Written by Max Zeshut
Founder at Agentmelt
A pattern where an AI model dynamically invokes external tools—calculators, APIs, databases, code interpreters—during response generation to produce more accurate and grounded outputs. TAG extends RAG (which retrieves static documents) by enabling the model to take actions: run a SQL query to get current data, call an API for live pricing, or execute code to verify a calculation. TAG is the foundation of how production agents interact with business systems.
A finance agent asked 'what's our burn rate this quarter?' doesn't retrieve a cached document—it queries the accounting database for actual expenses, calculates the monthly average, and compares against budget. The answer is computed from live data, not retrieved from a static source.