[ Tech stack ]
OpenAI Agents SDK
OpenAI's open-source SDK for building tool-using LLM agents that hand off to each other.
The OpenAI Agents SDK is an open-source framework (Python, TypeScript) for building agents from a small set of primitives: agents, tools (functions, web search, MCP servers), handoffs between agents, and guardrails that validate inputs and outputs. Its run loop handles tool calls and delegation, with built-in tracing to debug and evaluate every run. It's our choice when an application runs on OpenAI models and needs to move from an agent prototype to a readable multi-agent system.
[ Why OpenAI Agents SDK at Dexon ]
What this technology does well, and why we use it.
Typical usage: Multi-agent assistants, automated customer support, research agents and tool-driven workflows.
- 01
Minimal primitives: agents, tools, handoffs, guardrails and sessions.
- 02
Native handoffs: one agent delegates to a specialist with no plumbing.
- 03
Input and output guardrails that validate or block, run in parallel.
- 04
Built-in tracing, hosted tools (web search, files) and MCP servers.
[ Complementary technologies ]
The building blocks we often mobilise alongside.
A stack rarely exists alone. Here are the technologies Dexon most often pairs with this one, through pipeline habits, usage similarity or internal mastery. Click on a building block to see its scope.
[ Reassurance ]
- 0+
- custom projects delivered
- 30
- engineers, designers, project managers
- 80 %
- from top French schools
- 24 h
- average reply time
[ They trust us ]
More than 100 French and European companies trust us
[ Press ]
They talk about us.
Nationwide coverage by BFM Business, Le Figaro, Challenges, La Tribune and CNews. An outside reading of our work and our innovations.
