Agentic AI PM Build Session: Claude Code & Co-Work Explained - Build AI Agents That Work for You
Skills:
Agent Foundations90%Tool Use & Function Calling80%Multi-Agent Systems70%Autonomous Workflows70%
Sign up to get Free AI resources: https://forms.gle/sRNjXnsurNxNAUQW7
AI agents are evolving fast — and tools like Claude Code and Co-Work are changing how automation works.
In this session, Mahesh explains the new agentic AI stack and demonstrates how you can build an AI agent that can search and apply to jobs automatically.
You’ll learn:
• What Claude Code and Co-Work are
• The new Agent SDK and agent loop architecture
• Why agent orchestration is becoming automated
• The new capabilities introduced by Claude Code
• How AI agents can access your file system and run scripts
• How agents gather context, take actions, and verify work
• How to build your own assistant with AI agents
You’ll also see a live demo of an AI agent that searches for jobs online and applies to them automatically.
This session covers:
- Agentic AI architecture
- Claude Code vs traditional AI agents
- Context engineering and automation
- File system access and bash execution
- Multi-agent orchestration
- The future of AI productivity tools
If you're building AI products or exploring the future of automation, this session will help you understand how the new generation of AI agents actually works.
Timestamps
00:00 – Introduction: What Claude Code changed
01:30 – Mahesh's background and experience building AI agents
04:20 – Agenda: Claude Code, Co-Work and agentic AI
06:30 – Demo: AI agent that applies to jobs automatically
11:30 – How the agent searches and applies to jobs
15:00 – What changed in agentic AI since 2025
18:30 – Traditional multi-agent architecture
22:40 – The new Agent SDK and agent loop
27:30 – Claude Code vs previous agent frameworks
31:00 – Major new capability: File system access
35:10 – Running bash commands and scripts with agents
39:20 – Context gathering and context compression
44:00 – Actions: tools, scripts, MCP servers
48:30 – Verification: rule-based checks and LLM judges
52:40 – Claude Code vs Co-Work (developer vs business users)
57:00 – Real enterprise use ca
Watch on YouTube ↗
(saves to browser)
Sign in to unlock AI tutor explanation · ⚡30
More on: Agent Foundations
View skill →Related AI Lessons
⚡
⚡
⚡
⚡
How AI Is Replacing Manual Operations in Growing Businesses
Medium · AI
How I Evaluate Agent Skills Before Installing Them
Dev.to · 张文超
AI Automation for Small Business: Where to Start
Dev.to · AdamVibe
You Built the AI Feature. Now Sell It to the C-Suite Without Getting Stonewalled
Dev.to · Marc Newstead
Chapters (16)
Introduction: What Claude Code changed
1:30
Mahesh's background and experience building AI agents
4:20
Agenda: Claude Code, Co-Work and agentic AI
6:30
Demo: AI agent that applies to jobs automatically
11:30
How the agent searches and applies to jobs
15:00
What changed in agentic AI since 2025
18:30
Traditional multi-agent architecture
22:40
The new Agent SDK and agent loop
27:30
Claude Code vs previous agent frameworks
31:00
Major new capability: File system access
35:10
Running bash commands and scripts with agents
39:20
Context gathering and context compression
44:00
Actions: tools, scripts, MCP servers
48:30
Verification: rule-based checks and LLM judges
52:40
Claude Code vs Co-Work (developer vs business users)
57:00
Real enterprise use ca
🎓
Tutor Explanation
DeepCamp AI