AI agents & tool use
An LLM in a loop: reason, call a tool, observe the result, repeat — turning a text generator into a system that does things.
In one line
An agent is a model given tools (functions with typed parameters) and a goal; it decides which tool to call, reads the result, and continues until the task is done — the ReAct pattern of interleaved reasoning and acting.
How it works
The application declares tools ("searchKosha(query)", "lookupConcept(code)"). The model emits a structured tool call instead of prose; the runtime executes it and feeds the result back; the loop continues. Everything that makes this safe is engineering, not model magic: schema-validated arguments, scoped permissions, human confirmation for consequential actions, loop limits, and full audit logs. Multi-agent systems are this pattern composed — specialist agents calling each other as tools.
Where it shows up in digital health
Prior-authorisation drafting that reads policy and the chart; data-quality agents that scan and flag; lab tutors that inspect a learner's working state before hinting — Vaidya in this platform's labs reads your mapping state as a tool call, never as guesswork. The non-negotiable in health: agents act under least privilege, on synthetic or consented data, with every action logged.