Function Calling is All You Need — Full Workshop, with Ilan Bigio of OpenAI

AI Engineer · Intermediate ·🤖 AI Agents & Automation ·1y ago
Let's talk about Function Calling for o1/o3, Agent SDK (fka Swarms), Realtime API...) Ilan Bigio is a founding member of OpenAI’s Developer Experience team, where he built the 2024 AI phone ordering demo showcased at DevDay and was also the technical lead for Swarm, a framework for multi-agent orchestration and the precursor to the Agents SDK. Prior to that, he was a Solutions Architect at OpenAI, partnering with companies like Cursor, Khan Academy, and Klarna to shape their AI products. Before OpenAI, he was a full-stack Software Engineer at Google, building for YouTube at scale. Ilan’s journey started as a hobby hacker, diving into operating systems and reverse engineering, before shifting to language models in 2020. He created projects like ShellAI—an open-source, AI-powered terminal assistant—and is passionate about sharing knowledge. With a multidisciplinary background spanning web development, AI/ML, and operating systems, he’s designed and taught courses at Brown and continues to share his expertise through in-depth technical OpenAI guides on topics like Function Calling and Latency Optimization. https://www.twitter.com/ilanbigio Timestamps 0:00:00 – 0:01:44 Intro 0:01:44 – 0:10:19 History of Function Calling 0:10:19 – 0:25:00 Agent Loop Setup 0:25:00 – 0:34:11 Memory 0:34:11 – 0:54:06 Delegation 0:54:06 – 1:01:56 Async Delegation 1:01:56 – 1:17:14 Misc Questions 1:17:14 – 1:27:01 Dynamic Agent-Written Tools 1:27:01 – 1:43:06 [end] More Misc The special code from the last part of the talk - Dynamic Agent-Written Tools from swarm import Agent from swarm.repl import run_demo_loop agent = Agent( name="Bootstrap", instructions="", functions=[], ) def parse_function(code_str): namespace = {} exec(code_str, namespace) fn_name = next(k for k in namespace if not k.startswith("__")) return namespace[fn_name] def add_tool(python_implementation: str): function_obj = parse_function(python_implementation) agent.functions.append(function_obj) return "success" age
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Playlist

Uploads from AI Engineer · AI Engineer · 0 of 60

← Previous Next →
1 AI Engineer Summit 2023 — DAY 1 Livestream
AI Engineer Summit 2023 — DAY 1 Livestream
AI Engineer
2 AI Engineer Summit 2023 — DAY 2 Livestream
AI Engineer Summit 2023 — DAY 2 Livestream
AI Engineer
3 Principles for Prompt Engineering - Karina Nguyen (Claude Instant @ Anthropic)
Principles for Prompt Engineering - Karina Nguyen (Claude Instant @ Anthropic)
AI Engineer
4 Announcing the AI Engineer Network: Benjamin Dunphy
Announcing the AI Engineer Network: Benjamin Dunphy
AI Engineer
5 The 1,000x AI Engineer: Swyx
The 1,000x AI Engineer: Swyx
AI Engineer
6 Building AI For All: Amjad Masad & Michele Catasta
Building AI For All: Amjad Masad & Michele Catasta
AI Engineer
7 The Age of the Agent: Flo Crivello
The Age of the Agent: Flo Crivello
AI Engineer
8 See, Hear, Speak, Draw: Logan Kilpatrick & Simón Fishman
See, Hear, Speak, Draw: Logan Kilpatrick & Simón Fishman
AI Engineer
9 Building Context-Aware Reasoning Applications with LangChain and LangSmith: Harrison Chase
Building Context-Aware Reasoning Applications with LangChain and LangSmith: Harrison Chase
AI Engineer
10 Pydantic is all you need: Jason Liu
Pydantic is all you need: Jason Liu
AI Engineer
11 Building Blocks for LLM Systems & Products: Eugene Yan
Building Blocks for LLM Systems & Products: Eugene Yan
AI Engineer
12 The Intelligent Interface: Sam Whitmore & Jason Yuan of New Computer
The Intelligent Interface: Sam Whitmore & Jason Yuan of New Computer
AI Engineer
13 Climbing the Ladder of Abstraction: Amelia Wattenberger
Climbing the Ladder of Abstraction: Amelia Wattenberger
AI Engineer
14 Supabase Vector: The Postgres Vector database: Paul Copplestone
Supabase Vector: The Postgres Vector database: Paul Copplestone
AI Engineer
15 [Workshop] AI Engineering 101
[Workshop] AI Engineering 101
AI Engineer
16 The Hidden Life of Embeddings: Linus Lee
The Hidden Life of Embeddings: Linus Lee
AI Engineer
17 [Workshop] AI Engineering 201: Inference
[Workshop] AI Engineering 201: Inference
AI Engineer
18 The AI Pivot: With Chris White of Prefect & Bryan Bischof of Hex
The AI Pivot: With Chris White of Prefect & Bryan Bischof of Hex
AI Engineer
19 The AI Evolution: Mario Rodriguez, GitHub
The AI Evolution: Mario Rodriguez, GitHub
AI Engineer
20 Move Fast Break Nothing: Dedy Kredo
Move Fast Break Nothing: Dedy Kredo
AI Engineer
21 AI Engineering 201: The Rest of the Owl
AI Engineering 201: The Rest of the Owl
AI Engineer
22 Building Reactive AI Apps: Matt Welsh
Building Reactive AI Apps: Matt Welsh
AI Engineer
23 Pragmatic AI with TypeChat: Daniel Rosenwasser
Pragmatic AI with TypeChat: Daniel Rosenwasser
AI Engineer
24 Domain adaptation and fine-tuning for domain-specific LLMs: Abi Aryan
Domain adaptation and fine-tuning for domain-specific LLMs: Abi Aryan
AI Engineer
25 Retrieval Augmented Generation in the Wild: Anton Troynikov
Retrieval Augmented Generation in the Wild: Anton Troynikov
AI Engineer
26 Building Production-Ready RAG Applications: Jerry Liu
Building Production-Ready RAG Applications: Jerry Liu
AI Engineer
27 120k players in a week: Lessons from the first viral CLIP app: Joseph Nelson
120k players in a week: Lessons from the first viral CLIP app: Joseph Nelson
AI Engineer
28 The Weekend AI Engineer: Hassan El Mghari
The Weekend AI Engineer: Hassan El Mghari
AI Engineer
29 Harnessing the Power of LLMs Locally: Mithun Hunsur
Harnessing the Power of LLMs Locally: Mithun Hunsur
AI Engineer
30 Trust, but Verify: Shreya Rajpal
Trust, but Verify: Shreya Rajpal
AI Engineer
31 Open Questions for AI Engineering: Simon Willison
Open Questions for AI Engineering: Simon Willison
AI Engineer
32 Storyteller: Building Multi-modal Apps with TS & ModelFusion - Lars Grammel, PhD
Storyteller: Building Multi-modal Apps with TS & ModelFusion - Lars Grammel, PhD
AI Engineer
33 GPT Web App Generator - 10,000 apps created in a month: Matija Sosic
GPT Web App Generator - 10,000 apps created in a month: Matija Sosic
AI Engineer
34 Using AI to Build an Infinite Game: Jeff Schomay
Using AI to Build an Infinite Game: Jeff Schomay
AI Engineer
35 How to Become an AI Engineer from a Fullstack Background - Reid Mayo
How to Become an AI Engineer from a Fullstack Background - Reid Mayo
AI Engineer
36 The Code AI Maturity Model and What It Means For You: Ado Kukic
The Code AI Maturity Model and What It Means For You: Ado Kukic
AI Engineer
37 AI Engineer World’s Fair 2024 - Keynotes & Multimodality track
AI Engineer World’s Fair 2024 - Keynotes & Multimodality track
AI Engineer
38 From Text to Vision to Voice Exploring Multimodality with Open AI: Romain Huet
From Text to Vision to Voice Exploring Multimodality with Open AI: Romain Huet
AI Engineer
39 The Making of Devin by Cognition AI: Scott Wu
The Making of Devin by Cognition AI: Scott Wu
AI Engineer
40 The Future of Knowledge Assistants: Jerry Liu
The Future of Knowledge Assistants: Jerry Liu
AI Engineer
41 Llamafile: bringing AI to the masses with fast CPU inference: Stephen Hood and Justine Tunney
Llamafile: bringing AI to the masses with fast CPU inference: Stephen Hood and Justine Tunney
AI Engineer
42 Open Challenges for AI Engineering: Simon Willison
Open Challenges for AI Engineering: Simon Willison
AI Engineer
43 Lessons From A Year Building With LLMs
Lessons From A Year Building With LLMs
AI Engineer
44 From Software Developer to AI Engineer: Antje Barth
From Software Developer to AI Engineer: Antje Barth
AI Engineer
45 Unlocking Developer Productivity across CPU and GPU with MAX: Chris Lattner
Unlocking Developer Productivity across CPU and GPU with MAX: Chris Lattner
AI Engineer
46 Copilots Everywhere: Thomas Dohmke and Eugene Yan
Copilots Everywhere: Thomas Dohmke and Eugene Yan
AI Engineer
47 Fixing bugs in Gemma, Llama, & Phi 3: Daniel Han
Fixing bugs in Gemma, Llama, & Phi 3: Daniel Han
AI Engineer
48 Low Level Technicals of LLMs: Daniel Han
Low Level Technicals of LLMs: Daniel Han
AI Engineer
49 Emergence Launch: AI Agents and the future enterprise: Dr. Satya Nitta
Emergence Launch: AI Agents and the future enterprise: Dr. Satya Nitta
AI Engineer
50 How Codeium Breaks Through the Ceiling for Retrieval: Kevin Hou
How Codeium Breaks Through the Ceiling for Retrieval: Kevin Hou
AI Engineer
51 What's new from Anthropic and what's next: Alex Albert
What's new from Anthropic and what's next: Alex Albert
AI Engineer
52 Using agents to build an agent company: Joao Moura
Using agents to build an agent company: Joao Moura
AI Engineer
53 Decoding the Decoder LLM without de code: Ishan Anand
Decoding the Decoder LLM without de code: Ishan Anand
AI Engineer
54 Running AI Application in Minutes w/ AI Templates: Gabriela de Queiroz, Pamela Fox, Harald Kirschner
Running AI Application in Minutes w/ AI Templates: Gabriela de Queiroz, Pamela Fox, Harald Kirschner
AI Engineer
55 Building with Anthropic Claude: Prompt Workshop with Zack Witten
Building with Anthropic Claude: Prompt Workshop with Zack Witten
AI Engineer
56 Building Reliable Agentic Systems: Eno Reyes
Building Reliable Agentic Systems: Eno Reyes
AI Engineer
57 10x Development: LLMs For the working Programmer - Manuel Odendahl
10x Development: LLMs For the working Programmer - Manuel Odendahl
AI Engineer
58 Disrupting the $15 Trillion Construction Industry with Autonomous Agents: Dr. Sarah Buchner
Disrupting the $15 Trillion Construction Industry with Autonomous Agents: Dr. Sarah Buchner
AI Engineer
59 Hypermode Launch: Kevin Van Gundy
Hypermode Launch: Kevin Van Gundy
AI Engineer
60 Git push get an AI API: Ryan Fox-Tyler
Git push get an AI API: Ryan Fox-Tyler
AI Engineer

Related AI Lessons

Designing a Multi-Agent AI System for Content Analysis and Recommendations
Learn to design a multi-agent AI system for content analysis and recommendations by leveraging specialized agents to solve complex tasks
Dev.to AI
Prescriptive actions for BFSI Banking: next-best workflow tasks, escalation, and value realization
Learn how to implement prescriptive actions in BFSI banking for next-best workflow tasks, escalation, and value realization using AI and ML
Dev.to · Ananthapathmanabhan A
I red-teamed Oracle APEX 26.1's new AI Agent feature in the 72 hours after it went GA. Claude refused 7 of my 10 attacks on its own.
Learn how to red-team test Oracle APEX 26.1's new AI Agent feature and understand its security vulnerabilities
Dev.to · Ranjith Kumar Kondoju
OpenClaw told me it failed its own trust test, and that’s the real story
Learn how OpenClaw's self-reported failure on its own trust test reveals more about agent reliability than polished benchmarks
Dev.to AI

Chapters (9)

0:01:44 Intro
1:44 0:10:19 History of Function Calling
10:19 0:25:00 Agent Loop Setup
25:00 0:34:11 Memory
34:11 0:54:06 Delegation
54:06 1:01:56 Async Delegation
1:01:56 1:17:14 Misc Questions
1:17:14 1:27:01 Dynamic Agent-Written Tools
1:27:01 1:43:06 [end] More Misc
Up next
Introducing Gemini Enterprise Agent Ready
Google Cloud
Watch →