A swipe file on agentic engineering.
Best practices distilled from reading open-source projects and building an agentic framework.
I spent five years on Firebase making serverless feel simple. Agents are the same job. Now as part of the founding team at Genkit, we're building SDKs to make agentic engineering simple. Follow as I build and share my thoughts in public.
Recent
All writing →-
Gemini Agent + FastAPI: The Production-Ready Boilerplate for AI Chat APIs
from genkit.plugins.fastapi import genkitfastapihandler
-
Generating Video with Genkit Python: Veo's New First-Class generate() API
The normal Genkit model path is ai.generate() calling a model action, waiting for a ModelResponse, and returning it. That path assumes the model responds in mil
-
Genkit vs LangChain vs ADK: Python Edition 2026
Genkit makes a different bet: one primitive, minimum abstraction, everything else is your code.