Posted on Fri 01 October 2027 in GenAI • Tagged with GenAI, LLM, AI-product, startups, opinion
People use "AI" to mean a lot of different things in the same breath — GPT-4 is "AI," ChatGPT is "AI," a company's customer support bot built on top of both is also "AI." But these are three genuinely different things, sitting at different layers …
Posted on Tue 28 September 2027 in Tutorial • Tagged with FastAPI, Python, environment-variables, security, pydantic-settings, deployment
Almost every FastAPI app eventually needs something it shouldn't have hardcoded in the source code: a database URL, an LLM API key, a JWT secret, a third-party service token. When you're building GenAI apps, this shows up on day one, because you can't call an LLM API …
Posted on Mon 27 September 2027 in Tutorial • Tagged with FastAPI, Python, API-docs, Swagger, OpenAPI
If you've built even a basic FastAPI app, you've probably stumbled onto /docs and been pleasantly surprised — a fully interactive API documentation page, complete with every endpoint, request schema, and a "Try it out" button, without writing a single line of documentation yourself. This isn't a small …
Posted on Sun 04 October 2026 in GenAI • Tagged with GenAI, LLM, AI-literacy, career, opinion
A lot of career advice around GenAI right now focuses on learning to build with AI — prompt engineering, RAG, agents, fine-tuning. That's valuable, and it's most of what this blog covers too. But I've started noticing a quieter, less talked-about skill gap that might matter even …
Posted on Sat 03 October 2026 in Tutorial • Tagged with FastAPI, Python, dependency-injection, beginner
The first time I saw Depends() scattered through FastAPI route functions, it looked like unnecessary complexity for something simple. Why not just call a function directly inside the route? It took actually building a few endpoints that needed shared logic — authentication, database connections, settings …
Posted on Fri 02 October 2026 in GenAI • Tagged with GenAI, LLM, context-engineering, prompt-engineering, opinion
A few months ago I wrote about whether prompt engineering was a dying skill, and landed on "it's not dying, it's getting absorbed into something bigger." Since then, I keep running into a new term that feels like exactly that "something bigger" showing up with a …
Posted on Wed 30 September 2026 in Tutorial • Tagged with FastAPI, Python, chatbot, OpenAI, Claude, GenAI, LLM
Every GenAI journey eventually hits the same milestone: building your first real chatbot API, not just calling a model from a script. This is the project that ties together everything else — API keys, request/response models, calling an LLM provider, and returning a clean response your frontend …
Posted on Tue 29 September 2026 in Tutorial • Tagged with FastAPI, Python, async, performance, beginner
One of the first things that trips people up in FastAPI is seeing both def and async def used for routes, sometimes in the same codebase, and not knowing which one to use or why it matters. Some tutorials use async def everywhere out of habit …
Posted on Sat 26 September 2026 in Tutorial • Tagged with FastAPI, Python, SSE, streaming, GenAI, LLM
If you've used ChatGPT or Claude, you've seen the response appear word by word instead of showing up all at once after a long wait. That's not just a visual nicety — it makes the app feel dramatically faster, even though the total time to finish the response …
Posted on Fri 25 September 2026 in GenAI • Tagged with GenAI, LLM, benchmarks, model-evaluation, opinion
Every new model release comes with a wall of benchmark charts — MMLU, HumanEval, GPQA, some new benchmark nobody had heard of six months ago — all showing the new model beating the old one by a few percentage points. And yet, plenty of people who actually use …