AI Agents in Python
A three-part progression from simple decision agents to LLM-powered agents and clarifying loops that ask before acting.
This site is currently being refined after migration. If something seems missing, try Search or visit the older site.
oldws.anupshinde.com Software, trading infrastructure, AI experiments, and unusual research.
Built and documented here.
Four pillars
The blog still matters, but the structure now starts with the main threads underneath it: projects, technology, trading, and time.
Work
Libraries, tools, browser extensions, trading infrastructure, and experiments that turned into real systems.
From goeph and backtesting tools to older frameworks like Nirman and Livebase.
ExploreCode
AI agents, Go systems, JavaScript, architecture, debugging, and the practical side of building software.
Current writing leans heavily into AI workflows, software design, and developer tooling.
ExploreMarkets
Backtesting, strategy evaluation, trading psychology, and the systems thinking needed to survive real markets.
A mix of code-first research, practical trading process, and uncomfortable lessons.
ExploreResearch
Time cycles, quantitative astrology, celestial data, and the research thread tying outcomes, astronomy, and pattern-seeking together.
Where celestial data meets quantitative methods and pattern research.
ExploreSelected work
A three-part progression from simple decision agents to LLM-powered agents and clarifying loops that ask before acting.
A custom backtesting engine built for strategies that stopped fitting neatly inside off-the-shelf Python frameworks.
A Go ephemeris toolkit born from porting a real Skyfield-based workflow instead of treating astronomy code as a toy exercise.
A sitemap-driven SEO analysis workflow built almost entirely with AI agents, then corrected by hand where the agents drifted.
Recent writing
Feb 25, 2026
AI-assisted port of Skyfield (Python) to a Go ephemeris library. Validation-first approach, golden tests, and bug hunts.
Sep 3, 2025
From simple rules to clarifying loops: explore this 3-part series on building AI agents in Python, with examples.
Aug 31, 2025
Build a Clarifying Agent in Python with GPT-5 that asks follow-up questions until inputs are clear, providing a safer, smarter, and user-friendly experience.
Aug 28, 2025
Build an LLM-powered agent in Python: use GPT-5 to turn natural language into structured data, then apply simple rules for smart meal suggestions.
Aug 28, 2025
Learn how to build a simple rule-based decision-making agent in Python. Perfect for beginners, this is Part 1 of the Building Agents series and includes code, logic flow, and real-world analogies.
Aug 23, 2025
High-level look at building an SEO analysis tool with GitHub Copilot and Claude Sonnet 4 - what worked, what broke, and why AI speed still needs human direction.
Topic trails
Agent workflows, prompting, validation loops, and where AI helps or burns.
Strategy testing, execution logic, risk, and practical trading process.
Web development, browser tools, static sites, and older JavaScript work.
Performance-minded tooling, compiled workflows, and system-level implementation.
ML, analysis, scripting, and the places where Python still fits best.
Meta writing about work, tools, migration decisions, and how I think through tradeoffs.