All Things AI 2025
who it's for
machine learning engineers, data engineers, platform engineers, developer tool builders, engineering managers, open source maintainers
topics
vector databases for RAG; approximate nearest neighbors; embeddings stored in Chroma; retrieval augmented generation (RAG); local AI agents with tool calling; human-in-the-loop issue triage; cross-encoder and BGE re-ranking; red teaming and prompt sanitization; Streamlit LangChain LlamaIndex stacks; enterprise SaaS to semantic pipelines; production semantic search for multimedia
| title | author | length |
|---|---|---|
| The AI trick that cut AWS's issue triage time by 90% and caught regressions in 2 minutes | Darin Klinda | 09m |
Claims a ~90% triage time cut from typical 15–60 minutes down to 5–10 minutes per issue by combining automated sentiment analysis with domain-specific LLMs… | ||
| What makes vector databases essential for RAG and AI apps? | Jessica Garson | 06m |
Explains why vector databases replace token-based inverted indexes for RAG by storing ML-produced embeddings as arrays of floats/bytes so queries and documents… | ||
| Codename Goose: An open source local AI agent built on MCP | Angie Jones | 12m |
Goose is an open‑source local AI agent that runs locally and connects to any LLM that supports tool calling, using 1,700+ MCP servers as extensions. It… | ||
| 7 practical tips for safer AI and language models | Sophia Rowland | 06m |
Seven practical tips cover concrete safeguards: sanitize inputs to strip PII and block prompt injection, choose models by deployment (on‑prem vs cloud), size… | ||
| How I created Bookshelf : An open source AI-powered personal knowledge base | Ash Tewari | 13m |
Bookshelf is an open source RAG app that actually exists and runs locally using Streamlit, LlamaIndex, Chroma, LangChain and pandas, with optional… | ||
| What 80 years of coding history says about AI tools today | Brandon Mathis | 14m |
Argues today’s AI-assisted coding feels more evolutionary than revolutionary by tracing concrete shifts from Hollerith punch cards to UNIX, GPUs, TensorFlow… | ||
| 68% of enterprise AI fails here—here's how to fix it | Kevin Blanco | 11m |
Claims that 68% of enterprise AI stalls on fragmented data and shows a live build that avoids complex MLOps, connecting real-time Salesforce Notion Zendesk… | ||
| nothing matches | ||