Developer Voices Can Google's ADK Replace LangChain and MCP? (with Christina Lin)
28 snips
Nov 20, 2025 Christina Lin, a Google engineer pioneering the Agent Development Kit (ADK), delves into the transformative potential of AI in production systems. She explains the nuanced distinction between agentic pipelines and basic LLM calls. Christina discusses ADK's role in simplifying the construction of agents and tools, emphasizing the importance of grounding for accurate, cited results. Additionally, she highlights the Agent-to-Agent (A2A) protocol for enhancing communication and scalability in distributed systems while addressing crucial deployment and debugging strategies.
AI Snips
Chapters
Transcript
Episode notes
When To Use Agents Versus Single LLM Calls
- Agents are LLMs plus tools and memory that can think and act, enabling autonomous workflows beyond single LLM calls.
- Use agents when tasks require multi-step execution, tool integration, or parallel/subagent coordination.
Structure Agents Around Three Core Parts
- Design agents with a clear separation: model, system prompt (intent), and a toolbox of tools to execute actions.
- Make those three components mandatory and opt into extras like memory or policies only when needed.
Seed System Prompts With Example Outputs
- Provide example outputs in your system prompt so the LLM knows the desired response format and structure.
- Use structured examples when you need parsable results and natural language examples for conversational outputs.