AI Agents Beyond Context Limits | Maksim Shaposhnikov

The AI Native Dev - from Copilot today to AI Native Software Development tomorrow

Bots follow scripts. Assistants wait for your commands. Agents act autonomously.
Maksim Shaposhnikov, AI Research Engineer at Tessl, joins Simon Maple to unpack the capabilities of AI coding agents, including how developers can test and trust the code they generate.
On the docket:
• how sub-agents operate independently, maintaining their own context windows to handle complex tasks without overloading the main agent.
• why human-in-the-loop oversight is still essential, even as agents can autonomously generate prototypes and fix bugs.
• predictions for the next generation of agents, including self-correcting feedback loops and improved code quality over time.
Register now to AI Native DevCon - ainativedev.io/devcon
Connect with us here:
1. Maksim Shaposhnikov - https://www.linkedin.com/in/maxshapp/
2. Simon Maple - https://www.linkedin.com/in/simonmaple/
3. Tessl - https://www.linkedin.com/company/tesslio/

Join the AI Native Dev Community on Discord: https://tessl.co/4ghikjh
Ask us questions: [email protected]

Luvut

1. Trailer (00:00:00)

2. Introduction (00:00:53)

3. Deep Dive into Agents 101 (00:01:18)

4. Understanding AI Entities: Bots, Copilots, Assistants, and Agents (00:03:56)

5. Understanding Context Limitations in LLMs (00:28:58)

6. Capabilities and Limitations of AI Agents (00:33:03)

7. Security, Memory Management, and Future of AI Agents (00:36:43)