OpenAI's new agent models

Welcome back to Building AI Agents, your biweekly guide to everything new in the field of agentic AI!

If it’s after 4 pm on a Friday, please refer all queries to my executive assistant, ChatGPT.

NEW SECTION: 📅 Agent of the Week will highlight an agent built to tackle a real-world business problem—and open-source the code through the n8n platform so you can try it too.

This week, we’re featuring a sales development representative (SDR) agent built for a client by our agency, Orynt AI. Check it out below!

In today’s issue…

• OpenAI’s two new families of models for agent builders

• Instantly swap between every major agent framework

• MCP integrations from dozens of major companies

• How agents could transform enterprise spending

…and more

🔥 IN CASE YOU MISSED IT

Readers’ favorite items from the past week

1. AutoGen becomes the #1 agent framework

2. How PwC is rolling out AI agents to 75,000 employees

3. Understanding multi-agent handoffs

4. Google’s new standard for agent-agent communication

5. Learn to use LLMs with OpenAI academy

📅 AGENT OF THE WEEK

Sales Development Rep (SDR) Agent

Client: UK-based agency selling high-ticket ad placements for major media brands

Problem: Sales team was bogged down researching leads, answering repeat questions, and chasing bookings

Solution: We built Scout—an SDR agent that:

• Researches inbound leads

• Answers questions instantly via email

• Books qualified leads

• Re-engages cold leads

Result: ⏱️ Sales team saves 1.5 hours per lead—time reinvested into what the team does best: closing deals.

If agents like this would save your business time and money, set up a free 30 minute strategy call with Building AI Agents’ official agency, Orynt AI!