IBM Docling for GenAI and RAG Workflows: A Hands-On Test
IBM's Docling (69,878 GitHub stars) converts complex, unstructured documents into structured data for GenAI and RAG workflows. This hands-on test runs it on a local machine against a plain-extraction baseline — Docling's own technical report, the Transformer paper, a scanned page, a speech clip, and a video — with timings, output evidence, and a Go / No-Go / Monitor verdict.
Beyond the Chatbot: Engineering a Multi-Agent System That Survives Enterprise Production
I skipped the single "super-agent" and built five domain-isolated specialists on Vertex AI Agent Engine — then worked through the production hurdles that only show up at scale: orphaned sessions, silent memory failures, token bloat, and learning from transcripts without leaking PII.
The Timeline of Modern AI · Decades in the Making
The real story of how modern AI came to exist: decades of ignored research, one competition, a few bold defections, and one chatbot that changed everything. 1986–2026.
Connecting MCP Servers to GitHub for Real-Time SQL Lineage
How I used the Model Context Protocol to build a ‘Code Analyst’ agent that traces SQL lineage across GitHub repos — and answers questions about the codebase in plain English.
Get new posts by email.
One email per article, when I publish. No spam, no sharing your address, unsubscribe anytime.
Prefer RSS? Grab the feed.