pythonpydantic-aiagent-frameworkafter-workstart-using
Getting Started with Pydantic AI
Install pydantic-ai, run a typed Agent with output_type, add one tool—after-work Python agents with validation.
Academy notes
Articles and updates from SoloQuant Academy.
Tag: after-work
Install pydantic-ai, run a typed Agent with output_type, add one tool—after-work Python agents with validation.
Follow adk.dev Python quickstart, run a simple ADK agent in under 20 minutes—after-work Agent Development Kit basics.
pip install openai-agents, run the hello-world Agent + Runner, then add one function tool—after-work Python agent loop.
Install CrewAI, run a one-agent crew or first Flow, keep roles tiny—after-work multi-agent Python without CEF fluff.
Install LangGraph, build a tiny tool-calling graph or functional agent, run one arithmetic task—after-work Python agent basics.
Open Bolt.new, prompt a tiny browser app, run it in WebContainers, read the files—keep after-work scope educational.
Open v0, prompt a tiny educational UI, read the React/Next code, preview in the sandbox—keep after-work scope tight.
Cheridito & Weiss (2025) use actor-critic RL to mix market and multi-level limit orders in impactful LOB simulations. Plain-language intro. Not investment advice.
Cont & de Larrard (2011) link best-queue sizes to short-term midprice moves in a reduced Markovian LOB. Plain-language intro. Not investment advice.
Olivier Guéant (2016) develops optimal market making for multiple correlated assets with tractable approximations. Plain-language intro. Not investment advice.
Almgren & Chriss (1999) introduce mean-variance optimal execution with permanent vs temporary impact and an efficient frontier of liquidation paths. Plain-language intro. Not investment advice.
Olivier Guéant (2012) gives a general framework for optimal liquidation and block-trade illiquidity pricing via Hamiltonian methods. Plain-language intro. Not investment advice.