AI &amp; Automation

Offboarding Risk Profiler

Email Deliverability Scanner

AI & Automation

AI Readiness Scan

NEW

Workflow ROI Calculator

Engineering

DevEx Maturity Scan

Ops LogEngineering journal HandbookGuides and docs Exit KitFull ownership handover

Quick Links

Workshop

Architecture & Security Design

€499 · 5-day written deliverable

Start a brief →

Ops Log About

Start a Brief

Home/Ops Log/AI & Automation

← Ops Log

Stream · 10 reports

AI & Automation

Autonomous AI agents, RAG knowledge assistants and intelligent workflow automation. We replace repetitive back-office work with production-grade LLM pipelines.

All Streams AI & Automation Modern Workspace Security & Infrastructure10 results

Level

Access

Clear all

AI & AutomationGated Intel

Security & Infrastructure

Building a Production RAG System: Lessons from 6 Months in the Field

Other streams

Browse adjacent terrain

Modern Workspace

15 reports

Open →

10 reports

Open →

Ops Log · Weekly

One report per week. Zero fluff.

Pragmatic field reports on infrastructure, cloud economics, security posture and platform engineering — straight to your inbox.

Practitioner-written — no content marketing filler
Includes config snippets and real architectures
Unsubscribe anytime with one click

Business email only. Confirmation email sent. Every email has a one-click unsubscribe.

Four production RAG deployments. Six months of operating them. What broke, what we changed, what we now do by default — and what we still cannot solve with current tooling.

17 MAY 2026Deep dive

RAG That Works in Production: Vector Stores, Reranking and the Evaluation Loop

A demo RAG pipeline is not a production RAG system. This is the playbook: chunking strategy, hybrid retrieval, reranking, the eval harness, the cost model, and the update pipeline nobody talks about.

26 APR 2026Deep dive

AI-Powered Documentation: Keeping Your Knowledge Base Alive

Three operational disciplines that keep an internal knowledge base alive: generate reference docs from code, detect staleness automatically, and build a RAG layer over the cleaned corpus.

31 MAY 2026Practitioner

ChatOps for Infrastructure: Slack/Teams Bots That Actually Work

The architecture that makes ChatOps survive contact with a real on-call rotation: authentication via your IdP, six production bot patterns, n8n primitives for long-running flows, and the audit trail your auditor will accept.

29 MAY 2026Practitioner

The IT Automation ROI Calculator: How to Build the Business Case

Five components of a CFO-ready automation business case: time saved, error cost, FTE equivalence, indirect value, and the honest cost model. The calculator that turns 18-month payback into 6-9 month payback.

27 MAY 2026Intro

Automating IT Onboarding: From 3 Days to 30 Minutes

The three-phase onboarding architecture that compresses 2-3 days of manual work into 30 minutes of clock time. Role-profile YAML, HRIS adapter pattern, parallel provisioning chain, and the offboarding mirror.

25 MAY 2026Intro

AI & AutomationGated Intel

Agentic AI in IT Operations: Real Use Cases Beyond the Hype

Eight production use cases where agents earn their keep, four where they reliably disappoint, and the five-component safety architecture that separates "useful tool" from "incident in production".

23 MAY 2026Practitioner

Self-Hosted LLMs for Regulated Industries: A Deployment Guide

vLLM, TGI, Ollama, llama.cpp compared. GPU sizing tables you can defend. Quantization trade-offs. Hosting choices for EU sovereignty. The operational stack that separates a self-hosted LLM from a self-hosted incident.

21 MAY 2026Deep dive

n8n vs Make vs Power Automate: Workflow Automation for IT Operations

Three workflow platforms scored against 12 real IT-operations scenarios. Cost shape at scale, governance surface, the decision tree, and what we actually run in our own operations.

19 MAY 2026Practitioner