Engineers' Corner
Exploring the frontiers of artificial intelligence and innovation
Three must-have AI agent skills every engineer should use. Improve alignment and productivity in coding, fewer surprises when you let the agent work.
Negative instructions in AGENTS.md are not enforcement. Turn recurring coding-agent mistakes into fast deterministic checks instead.
An LLM wiki is a knowledge base your AI agents read and maintain: what it is and how to build one.
Foundation models can handle vision tasks from a prompt—but ML fundamentals still matter for production-grade systems.
Ada Hieta takes the stage at RustConf 2026 to share lessons from building a GPU-accelerated ONNX runtime in Rust.
How to build an AI engine for SaaS in 2026. LLM provider and framework comparison with data to guide architecture.
Deploy Qdrant on Azure with gRPC auth using a FastAPI singleton client. Covers access control and Python integration.
Common AI architecture mistakes that lead to fragile systems. Build scalable applied AI and avoid technical debt.
Serverless REST API development with Azure Functions. Build cloud-native APIs faster using serverless architecture.
Metaflow on Azure: reduce infrastructure friction for data science teams. Guide to cloud-native data science workflows.
Metaflow production guide: reproducible, collaborative, cloud-ready data science workflows. Real engineering examples.
Metaflow and Dask tutorial for scaling data science workflows from local to cloud on Azure. Guide for ML engineers.
Python-based hardware testing for R&D and production lines. Software-driven automation cuts cost and speeds delivery.
Argo and Metaflow on Azure: schedule and automate data science pipelines at scale. Guide for data engineering teams.
Which Python data streaming framework wins? Compare Spark, Flink, and Bytewax for stateful real-time workloads.
Build NLP services using embeddings, vector search, and LLM integration. Covers LangChain, LlamaIndex, and Qdrant.
Applied AI tools: LangChain, LlamaIndex, Qdrant, and Guardrails AI. Frameworks and patterns for reliable LLM apps.
Train small specialized language models using MEGABYTE and TinyStories. Lessons on capability with limited compute.
Qdrant Python client on Azure: cloud setup, access control, and integration guide for applied AI engineering teams.
Three LLM anti-patterns to avoid in production. Guide to reliable, scalable language model application architecture.
Build a real-time AI Slackbot with stateful streaming and RAG using Bytewax. Lessons from Softlandia's live workshop.
Softlandia's open source work — including opencv-python, used by NASA on the Ingenuity Helicopter Mars mission.
LLMs can be unreliable—evaluate systematically. Use LLM-as-a-judge and Promptfoo to boost AI reliability.
AI transcription turns speech into text for fast, detailed docs, voice insights, and multilingual content creation.
LLMs struggle with tabular data like CRM, SQL, or Excel. See how agentic workflows tackle this challenge effectively.
