Byte-size guides on DevOps, Cloud, and AI

I’m Nerav Doshi. I went from supply chain and logistics to Cloud Infrastructure and DevOps — and I write the plain-English guides I wish existed when I was making that switch. New article every week.

Re-Ranking the Top 20 With Local Models: Only the 12B Fixed the Miss, and It Demoted Two Right Answers

Entries 17 and 19 filtered the ranking the embedding search produced. The cap decides which chunks to hide, and it can’t change why the managed-versus-self-hosted question lost in the first place. This entry changes the ranking itself: take the top 20 chunks for each question, ask a local model to rate each one from 0 to 10 for how well it answers the question, re-sort by that rating, then run the same cap sweep on the new order. Ties keep their original embedding order, and chunks 21 and beyond stay below. ...

November 1, 2026 · 5 min · Nerav Doshi

Swept the Per-Article Cap From 1 to 3: The Gains Run Out Before the Costs Do

Entry 18 compared no cap with a cap of one chunk per article, and ended by saying the middle was untested. Same twelve questions this time, at caps of none, 1, 2 and 3. The labels are unchanged from Entry 18, so this run doesn’t settle whether a question can have more than one acceptable article. That still needs someone to read the articles. The first run failed before it started: ...

October 23, 2026 · 4 min · Nerav Doshi

Scored the Index Against Known Answers: 10 of 12, and What the Cap Really Costs

Entry 17 ended on a problem I’d made for myself: I’d been judging rankings with nothing to check them against. This entry fixes that, at least a little. Twelve questions, each with one article that should answer it, plus two controls where the collection has no answer. I labeled each right article from the filenames and the descriptions in the repo index, not by rereading the articles, so the labels are my best read, not verified ground truth. ...

October 18, 2026 · 5 min · Nerav Doshi

Tested a Per-Document Cap at Real Scale — and Found I Had No Ground Truth

Entry 07 ended on a loose thread: a document split into 17 chunks crowds out equally relevant single-entry documents, just by having more shots at ranking. The usual fix is a per-document cap, so I flagged it and moved on. Now that the collection holds 741 real chunks instead of 20, it was time to find out whether the problem was real at this size, and whether the fix worked. ...

October 15, 2026 · 4 min · Nerav Doshi

IAM and Identity Across Clouds: Why Permissions Take Longer Than the Install

Pipeline & Prompts | Byte size guides on DevOps, Cloud and AI DevOps from Zero #12 ⚡ Byte Size Summary Tell the difference between authentication (who is this?) and authorization (what can it do?) on AWS, Azure and GCP Map the same idea to each cloud’s vocabulary: IAM roles, managed identities and role assignments, service accounts and IAM bindings Add an identity pre-check to your runbook so approvals stop blocking installs The Story A ROSA install cannot start until the customer has accepted the terms and activated the ROSA listing on the AWS Marketplace. That part takes minutes. The part after it is where the time goes. ...

October 12, 2026 · 5 min · Nerav Doshi

Agentic AI Governance: Five Controls for Safe Write Access

🤖 AI in the Stack #8 Pipeline & Prompts | Byte size guides on DevOps, Cloud and AI ⚡ Byte Size Summary This article closes the governance gap Article 01 opened with — the gap between TP4 (observing systems) and TP5 (autonomous incident response) that no amount of model capability alone can close. Five components are required before AI gets real operational authority: bounded blast radius, mandatory human checkpoints for state-changing actions, complete audit trails, rollback as a first-class operation, and a tested kill switch. None of this is theoretical. Every component in this article has already appeared somewhere in this series — RBAC scoping from Article 03, human-in-the-loop approval from Article 07, the reason field in rollbacks from Article 04, and bounded retries from Article 06. This article is where they get assembled into one governance model. The Story Eight articles ago, I told you about sitting in a data scientist demo at IBM and feeling something click that wasn’t comfortable. The models were good. The theory was sound. But almost none of it reached production, and underneath the impressive demos was data nobody had governed, bias nobody had checked for, and a gap between what we sold and what we could actually deliver safely. ...

October 5, 2026 · 14 min · Nerav Doshi

Cloud Fundamentals: VPCs and VNets Explained

Cloud Fundamentals: VPCs and VNets Explained Pipeline & Prompts | Byte size guides on DevOps, Cloud and AI The Planning Call That Almost Went Sideways I was advising a client on their cloud architecture as they planned an Azure Red Hat OpenShift (ARO) deployment. Early in the planning phase, someone pulled up the client’s existing network address ranges next to the new environment we were designing. They overlapped. Nothing was broken yet — we caught it before anything got deployed. But it meant a Microsoft networking engineer had to get pulled into the conversation before we could move forward. I have seen the exact same pattern show up on AWS engagements too. Different cloud, same root cause: whoever set up the original network picked an address range without thinking about what it might need to connect to later. ...

October 5, 2026 · 5 min · Nerav Doshi

Grew the Collection from 5 Entries to 741 Real Chunks

Every retrieval test since Entry 05 has run against the same handful of entries — three documents in Entries 05-06, twenty after Entry 07’s chunking. Realistic enough to prove the mechanics work, not realistic enough to trust the actual rankings. Growing this into something closer to the real published catalog was overdue, and getting there cleanly took two wrong turns first. First attempt pointed the bulk-embed script at what looked like the right content folder and got back three files that were in Repo scaffolding, not articles — the real posts weren’t there at all. Hugo commonly organizes content as page bundles, each article living in its own subfolder as <slug>/index.md, and the script’s flat glob("*.md") only looked one level deep. Fixed by pointing at the actual posts directory directly rather than guessing at folder depth. ...

October 5, 2026 · 3 min · Nerav Doshi

Reconnected Claude Code Over SSE — and Found the Distance Scores Aren't as Stable as I Thought

Loose end from Entry 14: switching mcp_search_server.py from stdio to SSE broke the Entry 08 Claude Code connection, which was registered expecting a spawned process, not a network server. Fixing it turned out to be the easy part: claude mcp remove today-i-ran-notes claude mcp add --transport sse today-i-ran-notes http://localhost:8090/sse claude mcp list ✔ Connected, server still running from Entry 14. Clean. Re-ran Entry 08’s original test — ask it to use the tool, search for the oc pod-status question. It worked, and gave a solid narrative answer identifying Entry 02’s wrong command. But I wanted the actual distance score this time, not just the summary, so I asked for the raw tool output directly. That’s where this got more interesting than “confirmed the reconnect works.” ...

October 2, 2026 · 4 min · Nerav Doshi

Wired n8n to Ollama and the MCP Tool — and Hit Almost Every Wall on the Way

n8n running as a container is a decent stand-in for “how would a real automation platform actually call this stuff”. Everything up to now has been me calling things directly. Two integrations, same workflow: Ollama first, since it’s simpler, then the MCP tool from Entry 08. The n8n container, as podman inspect n8n shows it. This is the equivalent run command: podman run -d --name n8n -p 5678:5678 -v n8n_data:/home/node/.n8n docker.io/n8nio/n8n Ollama went cleanly. Container running, one HTTP Request node pointed at http://host.docker.internal:11434/api/generate — host.docker.internal matters here specifically, it’s how a container reaches something running on the host machine itself, not localhost, which inside the container just points back at the container. Real response came back, done: true, no drama. ...

September 28, 2026 · 5 min · Nerav Doshi

Kubernetes Cost Attribution: Namespace vs. Cost-Center

Pipeline & Prompts | Byte size guides on DevOps, Cloud and AI ☁️ Cloud Without the Chaos #5 ⚡ Byte Size Summary Why native Kubernetes cost attribution (namespace/project-level, via CMMO) and organizational cost-center attribution are different problems, and why one mechanism can’t do both jobs How cost detection (fast, alert-based) and cost attribution (detailed, reconciled) are separate concerns that don’t need — and shouldn’t need — the same mechanism What actually happens to attribution when the organizational-label layer goes away, and why that’s not the same as losing all visibility The Story Cloud cost estimates tend to look straightforward when a workload is first being planned. Size the application, estimate average utilization, account for expected growth, enable autoscaling, and build the procurement number. ...

September 27, 2026 · 17 min · Nerav Doshi

Built a Hand-Rolled Agent Loop and Found a Weird Retrieval Bias

Every “agent” framework boils down to the same three-step loop underneath: look at the world, decide what to do, do it. I wanted to build that by hand instead of reaching for a framework, mostly because I’ve never actually seen the seams of one up close, and frameworks are good at hiding exactly the parts I wanted to look at. Started with a completely fake skeleton, hardcoded task and all, just to prove the shape works before adding anything real: ...

September 24, 2026 · 4 min · Nerav Doshi

What EU Data Sovereignty Actually Requires Beyond Hosting

Pipeline & Prompts | Byte size guides on DevOps, Cloud and AI ☁️ Cloud Without the Chaos #4 ⚡ Byte Size Summary Why “the data is in an EU data centre” doesn’t answer a sovereignty question. Support access, logs, and metrics are separate surfaces, and each needs its own boundary What happened when a blanket EU-only routing fix broke a 2-hour P1 SLA, and the tier we built instead Why sovereignty isn’t something you automate. You can only shrink the surface area where a human has to touch the boundary The Story The data residency box was already checked. Managed Kubernetes clusters, multi-region, customer workload data pinned to EU regions from day one. That part of the compliance conversation had been closed for months. ...

September 21, 2026 · 10 min · Nerav Doshi

Found the Real Kubernetes Memory Ceiling — It Wasn't Double

Last entry left a real question hanging: the exact Podman number got killed under kind, twice. Did that mean the gap between the two runtimes was huge — needing something close to double the memory — or was the real ceiling only a little higher than 1663Mi, and I’d just clipped it? Only one way to find out. Redeployed with the limit bumped to 2048Mi — a deliberately big jump, so the answer would be unambiguous either way. ollama-pod-2gb.yaml is the same manifest as Entry 11’s, renamed to ollama-2gb, with the memory block raised: ...

September 18, 2026 · 3 min · Nerav Doshi

The Same Memory Number That Worked in Podman Got OOMKilled in Kubernetes

OOMKilled is what Kubernetes says when a container tries to use more memory than its limit allows and the kernel steps in and kills it. Going into this one, my assumption was straightforward: Entry 09 measured 1.663GB under Podman, so setting a Kubernetes limit to that exact number should be enough. Same model, same host, same measurement. That assumption was wrong, and finding out why turned into the most interesting result in the series so far. ...

September 15, 2026 · 3 min · Nerav Doshi

Deployed Ollama to Local Kubernetes With No Resource Limits

Before testing whether last entry’s real Podman number (1.663GB) holds up as an actual Kubernetes resource limit, I wanted a baseline: what happens with nothing set at all. kind runs a full local Kubernetes cluster inside containers acting as nodes — Kubernetes on top of the same containers everything else in this series has been using. Spun up a fresh cluster and deployed Ollama with no resources section in the pod spec whatsoever. The whole manifest, ollama-pod-naive.yaml: ...

September 12, 2026 · 2 min · Nerav Doshi

Containerized Ollama and Found the Real Memory Overhead

On Linux, containers run natively — straight on the host kernel. On macOS, they can’t, because containers need a Linux kernel underneath and your Mac isn’t running one. So Podman and Docker Desktop quietly spin up a small Linux VM in the background and put every container inside that instead. Which means every container on a Mac is sharing a fixed slice of memory carved out for that VM — not your Mac’s actual RAM — and that distinction is about to matter a lot. ...

September 9, 2026 · 3 min · Nerav Doshi

Direct Connect and ExpressRoute: Fixing Asymmetric BGP Routing

The Story Back in Article 1, I said we’d get back to this: once you’ve decided what goes in the cloud and who manages it, there’s a third question that decides whether any of it actually works — how does your data get there? A telecom customer I worked with was pushing sustained real-time Kafka streams past 850 Mbps between on-prem and the cloud, with big unpredictable spikes on top, over an AWS Site-to-Site VPN. A single tunnel is rated up to 1.25 Gbps. On paper they had headroom. ...

August 31, 2026 · 8 min · Nerav Doshi

Wired the Local MCP Server into Claude Code

Everything up to this point — building the Chroma index, chunking, querying — was done by hand, one Python command at a time. An MCP server is what turns that into an actual tool: a small program exposing specific capabilities to an AI client, so it can call your stuff directly instead of you running queries yourself every time. What I actually wanted to prove here wasn’t that the server starts. It’s that a real client can reach it and get something useful back. ...

August 31, 2026 · 3 min · Nerav Doshi

Chunked a Document and Found a New Retrieval Problem

Chunking means splitting a long document into smaller overlapping pieces and embedding each one separately, instead of embedding the whole thing or lopping off the end like Entry 05’s truncation hack. It fixes the content-loss problem cleanly — nothing gets silently dropped. What it doesn’t fix, and what I didn’t see coming until I was staring at the results, is a structural bias: a document split into 17 pieces now has 17 separate shots at showing up in search results, while a short document still only gets one. More chunks means more chances to rank, whether or not any individual chunk is actually the most relevant thing in the store. ...

August 27, 2026 · 4 min · Nerav Doshi

Queried the Local Embeddings Store for the First Time

Building the vector store last time was only half the job. The actual point of embeddings is asking a question and getting back the right document, not just any document that happens to be sitting there. Chroma does this with distance: turn the question into a vector the same way you turned each document into one, then measure how close the question’s vector is to each stored vector. Lower distance, more similar in meaning — at least in theory. The real test isn’t whether it returns something, because it always will. It’s whether the number actually means anything. ...

August 24, 2026 · 3 min · Nerav Doshi

Built My First Local Embeddings Pipeline (Files + a Live URL)

An embedding model doesn’t generate text — it converts text into a list of numbers that represents what that text means. Two pieces of writing about similar topics end up with similar vectors even if they don’t share a single word, which is the whole trick behind semantic search: you can find “things that mean something like this,” not just “things that contain this exact word.” The detail that actually surprised me: the vector is always the same fixed length no matter how long the source text is. A one-sentence note and a ten-page article both come out as the same-sized list of numbers — a fingerprint, basically, summarizing something much bigger into a fixed shape. ...

August 21, 2026 · 4 min · Nerav Doshi

Managed Services vs Self-Hosted: When to Hand Over the Keys

Managed Services vs Self-Hosted: When to Hand Over the Keys ☁ Cloud Without the Chaos — Article 02 You’ve placed the workload in the cloud. That decision is done. Now comes the one nobody gives you a clean framework for: do you run the infrastructure yourself, or do you hand the keys to a managed service? I worked with a customer who answered this the hard way — twice. Once on their own platform, and once after they’d already made the switch. Both incidents involved the same underlying failure mode. Neither one turned out the way anyone in the room expected. ...

August 20, 2026 · 9 min · Nerav Doshi

Compared Quantization Levels: Q4 vs Q8 vs FP16 on llama3.2:1b

A model’s weights are normally stored at high precision — FP16, 16-bit floating point. Quantization compresses those numbers down to fewer bits to shrink the file and memory footprint, trading some precision for space. Same idea as squashing a high-res photo down to a smaller JPEG: the file shrinks a lot, technically some detail is lost, and in practice you usually can’t tell. Before pulling anything new for this one, I ran ollama show llama3.2:1b out of curiosity — and immediately had to correct myself. The model I’d been calling “the default” in Entries 01 and 03 turned out to already be Q8_0, not some unspecified baseline. Worth owning that plainly rather than quietly fixing it: I’d been comparing against a number without actually knowing what it was. ...

August 19, 2026 · 3 min · Nerav Doshi

Agentic AI Infrastructure: What It Takes to Do It Safely

⚡ Byte Size Summary See why we shipped an OpenShift diagnostic MCP server as read-only by design, and the RBAC wall that made write access harder than it looks Walk through a real failed remediation test where an agent recommended a correct-looking fix built on stale, deprecated config — and what that failure mode actually is Get the maturity-gated approval architecture we designed for write access — and why it’s still sitting on paper, not in production The Story In Article 06 we wired an n8n workflow to MCP and RAG for automated incident triage. That article ended with a question: what happens when the agent gets a longer leash? ...

August 18, 2026 · 9 min · Nerav Doshi

Compared llama3.2:1b vs llama3.2:3b Memory Footprint

The number in a model name — 1b, 3b — is parameter count, roughly the tunable values inside the model that encode whatever it’s learned. More parameters, generally, means better reasoning, at the cost of more memory and slower responses. I wanted an actual number for that tradeoff instead of just nodding along to the general idea, so I pulled the 3-billion-parameter sibling of Entry 01’s model and put them side by side. ...

August 14, 2026 · 3 min · Nerav Doshi

The Hybrid Cloud Isn't a Destination. It's a Set of Tradeoffs.

☁ Cloud Without the Chaos — Article 01 · ⏱ 10 min read ☁ Byte Size Summary Hybrid cloud isn’t a strategy — it’s the outcome of real architectural decisions Most teams default to cloud or on-prem for the wrong reasons (inertia, not intent) Five dimensions drive every defensible placement decision: latency, data sovereignty, cost profile, operational ownership, and blast radius A reusable decision framework for evaluating any workload — run it before the migration starts, not after Network design thinking from logistics applies directly to hybrid cloud architecture — and most platform engineers have never seen it framed this way I spent a few years working in supply chain and logistics before I ended up in cloud infrastructure. One of the first things you learn in that world is that the network is never fully yours. ...

August 13, 2026 · 9 min · Nerav Doshi

Built a constrained 'oc CLI Mentor' with a system prompt

A system prompt is basically a character brief you hand a model before the real conversation starts — instructions that shape how it behaves for the rest of the session, without you repeating yourself every message. I wanted to see how far that actually holds under pressure, so I tried to build the strictest version I could think of: a model that refuses to explain anything and only ever answers with a real oc command. ...

August 10, 2026 · 3 min · Nerav Doshi

Database Migrations During Zero-Downtime Deploys on OpenShift

⚡ Byte Size Summary Implement the four-phase Expand/Contract pattern — nullable column, batched backfill, code pivot, then constraint — so schema changes never ship coupled to application code Understand why Argo CD’s “rollback” can revert your container image but cannot touch a database schema, and why that gap is the actual thesis of zero-downtime deployment failures See the enforcement gap that let a smaller version of the same incident happen twice — and why process-only guardrails (PR review, runbooks) fail under deploy pressure The Story In the previous article we shifted from managing Kubernetes to managing applications. This article shows what happens when the database layer doesn’t get the same treatment. ...

August 7, 2026 · 14 min · Nerav Doshi

Deployed llama3.2:1b locally via Ollama

I wanted to start this series with the most boring possible first step — not because it’s impressive, but because everyone skips it. Every tutorial about running LLMs locally jumps straight to “here’s how you fine-tune it” without ever answering the question I actually had: what does this thing cost me in memory, for real, on my machine? So: installed Ollama, pulled llama3.2:1b (Meta’s smallest Llama 3.2 model — 1 billion parameters, small enough that it downloads in a couple of minutes instead of eating your afternoon), and loaded it with a throwaway prompt just to force it into memory. ...

August 7, 2026 · 2 min · Nerav Doshi

I Stopped Managing Kubernetes So I Could Start Managing Applications

⚡ Byte Size Summary Understand why a Helm sub-chart with a hardcoded deprecated API can pass CI, deploy cleanly, and still crash production ten minutes later See why admission-time governance and a managed control plane solve two completely different problems — and why conflating them is how teams get burned Walk away with a clearer sense of where platform ownership should actually sit as an organization scales The Story I was building an optimization model for scheduling — an internal Red Hat project, nothing exotic. Somewhere in the middle of it I noticed something uncomfortable: I wasn’t spending my time on the application anymore. I was spending it on the platform underneath it. Roughly half my working hours were going into upgrade cycles — chasing down which APIs had quietly disappeared and which of my dependencies would break the moment the Kubernetes cluster moved forward a minor version. ...

July 24, 2026 · 10 min · Nerav Doshi

Build an AI Incident Triage Workflow in n8n with MCP

⚡ Byte Size Summary Wire n8n to an MCP (Model Context Protocol) server over Streamable HTTP and a RAG (Retrieval-Augmented Generation) pipeline to build an automated incident triage workflow — runbook lookup and live cluster diagnostics assembled before a human opens a single dashboard The moment you place an LLM agent node inside an n8n workflow, execution becomes non-deterministic — the model decides how many tool calls to make, so your timeout and call limits must assume worst case, not average case Start with hard execution limits (5-minute timeout, 2-3 max calls per run) and loosen as you validate — a runaway workflow with no bounds will exhaust API quotas and flood notification channels before you notice The Story I started using n8n because I watched a teammate build a workflow in twenty minutes that would have taken me a day to write in Python. The visual canvas, the drag-and-drop nodes, the instant execution feedback — it made automation feel fast. So I started experimenting. ...

July 22, 2026 · 20 min · Nerav Doshi

Swapping LLM Providers Without Rewriting Your Stack

⚡ Byte Size Summary Deploy a LiteLLM proxy on OpenShift to decouple your applications from individual LLM providers — switch or failover between models by changing a ConfigMap, not your code Inject cluster-specific context (API versions, cloud annotations, golden templates) before every prompt to prevent models from generating “plausible averages” that look correct but fail on your platform Validate every generated manifest with oc apply --dry-run=server before applying — the cluster’s API server catches structural errors that no amount of prompt engineering will prevent The Story I was building a GenAI data poisoning demo for a proof of concept on ROSA (Red Hat OpenShift on AWS). The demo needed OpenShift-native manifests — Routes with TLS termination, proper SecurityContextConstraints, current API versions. I built it using Claude, and it worked. The model understood OpenShift. The manifests deployed cleanly. The demo ran on the cluster. ...

July 12, 2026 · 13 min · Nerav Doshi

Managed OpenShift, Lost State, and Daily Drift Checks

Pipelines in the Wild #4 Byte Size Summary Red Hat OpenShift Service on AWS (ROSA), Azure Red Hat OpenShift (ARO), and OpenShift Dedicated on GCP (OSD) are mature, SRE-operated platforms — same OpenShift surface, three clouds, control plane work you don’t own. When prerequisites are met, installs complete in the documented window. Enterprise timelines stretch when governance approval tracks and Terraform state hygiene are treated as afterthoughts, not when the platform fails. This article separates the solid platform from the enterprise wrapper, then covers what actually prevents pain on the IaC side: remote state before the first resource, scheduled drift detection, and platform-specific recovery when partial applies leave residue behind. ...

June 30, 2026 · 17 min · Nerav Doshi

Treat Prompts Like Code: A CI Gate for LLM Workflows on OpenShift

⚡ Byte Size Summary Store prompts as versioned YAML manifests in Git and run them through a three-stage GitHub Actions gate — schema validation, secret scanning with gitleaks, and model policy enforcement — before any LLM call reaches your OpenShift environment A CI-gated prompt pipeline gives your enterprise auditors a traceable answer to “what prompt was active during the incident window” — without it, the forensic work is manual, billed, and slow Prompt versioning is necessary but not sufficient: you’re versioning one variable in a system with multiple unversioned dependencies, and this article shows you what to do about the rest of them The Story I was presenting a prototype at a conference. The demo was built over three weeks of late-night sessions — an AI-assisted operations assistant for OpenShift that could answer runbook-style questions against live cluster state. The architecture was solid. The underlying idea was good. ...

June 22, 2026 · 16 min · Nerav Doshi

Secrets Management Across Multi-Cloud Pipelines

⚡ Byte Size Summary Secret management failures are invisible until they cause a production incident — start with RBAC and namespace isolation before the first workload goes live Storing secrets in a central vault solves the sprawl problem but introduces a new failure mode: rotation lag between the vault and the namespace-level Kubernetes secret The real unsolved problem isn’t technical — it’s knowing who owns the approval and escalation path when a credential rotates at 2 AM across a multi-timezone team The Story In Article 02 we built retry logic and tiered alerting so transient pipeline failures don’t wake anyone up. This article tackles the credential layer underneath — because a retry won’t help when the secret itself is missing. ...

June 10, 2026 · 17 min · Nerav Doshi

Retry Logic and Tiered Alerting in GitHub Actions

Byte Size Summary Most pipeline failures are transient — a registry returning a 503, a smoke test catching a slow cold start, a network blip during an image push. Retrying them automatically, with exponential backoff, means engineers never see them. The failures that reach a human should be the ones that actually need one. This article builds a retry wrapper and a three-tier alerting system (transient → silent, degraded → Slack warning, critical → PagerDuty page) on top of a GitHub Actions blue/green deploy workflow. The demo application is Waybill — a FastAPI shipment tracking API backed by PostgreSQL, where the health endpoint checks real database connectivity rather than returning a static 200. That distinction matters: a smoke test that only checks HTTP status is a smoke test that passes while your database is unreachable. By the end you’ll have a working repo you can run locally with Docker Compose and test today. ...

June 4, 2026 · 18 min · Nerav Doshi

MCP Server Architecture for Platform Teams — Giving AI Live Access to Your Infrastructure

⚡ Byte Size Summary MCP (Model Context Protocol) is the standard that lets AI agents interact with external systems — your cluster, your observability stack, your ticketing system — without bespoke integration code for every tool. MCP directly addresses AI hallucination and 2AM incident response by grounding AI answers in live system state. It doesn’t solve tribal knowledge alone — that needs RAG alongside it. This article covers the production-grade architecture: what MCP servers are, how to design them for platform engineering use cases, and what you need to get right before running them anywhere near production. In Article 01 we built the evaluation framework. In Article 02 we built a RAG pipeline for static runbook knowledge. Now we give AI agents access to live infrastructure. ...

June 3, 2026 · 12 min · Nerav Doshi

Build a RAG Pipeline for Internal Runbooks with FastAPI and Chroma

⚡ Byte Size Summary RAG inserts a retrieval layer between your existing runbooks and an LLM — answers come from your documentation, not generic training data, with source citations included. This article builds a complete FastAPI service with /ingest, /query, and /health endpoints, using OpenAI embeddings and Chroma as the vector store. Everything is cloneable from GitHub. The goal isn’t to replace your runbooks. It’s to make them queryable at the moment an incident is happening. In Article 01 we built a framework for evaluating where AI actually changes outcomes in platform engineering. This article implements the first concrete use case: making your existing runbooks semantically searchable. ...

May 27, 2026 · 11 min · Nerav Doshi

Zero-Downtime Deployments on OpenShift with GitHub Actions and Feature Flags

Byte size summary After reading this article, you will know how to implement a blue/green deployment pipeline on OpenShift that uses HAProxy-backed Route weight splitting for traffic control and Flagsmith for feature flag management — and more importantly, you will know where the implementation breaks silently. Specifically: the HAProxy propagation gap that lets your smoke tests lie to you, the partial rollout state that puts two versions in production simultaneously, and why the standard approach of patching a Route weight and immediately proceeding has cost teams I’ve worked with entire migrations. The implementation uses GitHub Actions for orchestration, oc commands for OpenShift-specific traffic control, and Flagsmith as the feature flag service. The patterns apply to AKS, EKS, and GKE with platform-specific variations called out. ...

May 19, 2026 · 18 min · Nerav Doshi

AI Tooling on OpenShift: A Practitioner's Evaluation Framework

Byte size summary After reading this article, you’ll have a framework for evaluating AI tools in platform engineering contexts — not by capability type, but by where in your workflow the tool actually changes the outcome. You’ll understand why the tools that sound most compelling are still hype, where genuine productivity gains exist today, and what governance infrastructure you need in place before any AI component gets near production. This article is the foundation for the series; subsequent articles implement each touch point against real OpenShift infrastructure. ...

May 12, 2026 · 16 min · Nerav Doshi

The Big Picture: How DevOps, Cloud and AI Are Converging — And What That Means for You

I Still Remember the Sound Forklifts beeping in reverse. Conveyor belts humming. Cold warehouse air hitting my face as I stood on the floor of a Delphi plant in 2002. I was staring at a maze of pallets, racks, and production lines, trying to redesign the entire material movement system. I had a chemical engineering degree, a head full of equations, and absolutely no idea how this moment would shape the next 20 years of my career. ...

May 6, 2026 · 8 min · Nerav Doshi

Generative AI and Agentic AI: From Answering Questions to Taking Action

The Meeting That Changed How I Prepare I used to spend hours before important workshops and client meetings pulling together materials. Downloading presentation decks, saving links, reading through documents, trying to hold enough in my head to answer questions confidently in the room. Then I discovered NotebookLM. NotebookLM is a generative AI tool from Google that lets you upload your own documents, presentations, and links and then have a conversation with all of that material as if it were a knowledgeable colleague who had read everything perfectly. ...

April 28, 2026 · 10 min · Nerav Doshi

What is AI? You Are Already Using It - You Just Did Not Know

I Was Selling AI Before Most People Knew What It Was A decade ago I was selling predictive and prescriptive analytics solutions to enterprise clients. Tools like SPSS Modeler — IBM’s data science platform for predicting future outcomes — and CPLEX, the optimisation engine we talked about in Article 6, which solved complex scheduling and logistics problems for supply chain and warehouse operations. Back then AI wasn’t a word that appeared in everyday conversation. It lived in university research departments, specialist software vendors, and the back offices of large corporations with data science teams. It was powerful, it was real, and almost nobody outside of those environments knew it existed. ...

April 22, 2026 · 9 min · Nerav Doshi

Infrastructure as Code: Stop Clicking, Start Coding Your Cloud

The Problem With Doing It By Hand Early in my Cloud and Infrastructure career I watched a colleague spend three days manually building out a production environment on Azure. Clicking through dashboards, configuring virtual networks, setting up security groups, deploying OpenShift, installing operators. Three days of careful, methodical work. Two weeks later, we needed an identical environment for testing. Nobody could remember exactly what had been clicked, in what order, with what settings. The tribal knowledge lived entirely in one person’s head — and that person was on holiday. What followed was a painful reconstruction exercise involving guesswork, old notes, and a lot of “I think this is how we did it.” ...

April 15, 2026 · 8 min · Nerav Doshi

Kubernetes: The Platform That Keeps the Internet Running at Scale

From Supply Chain to Container Orchestration When IBM acquired Red Hat, I was working as a technical seller trying to position IBM’s data science platform to clients. Our internal team was containerising CPLEX — a powerful optimisation engine used in warehouse management and supply chain applications — and running it on OpenShift. I had seen CPLEX solve complex scheduling problems in the real world. I understood inputs, equations, constraints, and outputs. But pods? Nodes? Dockerfiles? It felt like a science project. I couldn’t connect what I was seeing on screen to anything that could work in real production. ...

April 8, 2026 · 8 min · Nerav Doshi

CI/CD Pipelines: How Your Code Goes from a Laptop to the Real World

The First Time I Saw a Pipeline Run I still remember the first time I watched a CI/CD pipeline run from start to finish. A developer pushed their code to GitHub. Within seconds, a series of automated steps fired off on their own — tests ran, the application was packaged into a container, and it was deployed to a live environment. Nobody pressed a button. Nobody sent an email saying “please deploy this.” It just happened. ...

April 1, 2026 · 7 min · Nerav Doshi

From Supply Chain to Software: What Containers Actually Are and Why They Matter

The Moment Someone Finally Explained Containers to Me When IBM acquired Red Hat, my world changed overnight. Suddenly everyone around me was talking about containers. Kubernetes. Pods. Orchestration. I was nodding along in meetings while internally having absolutely no idea what any of it meant. My background was in supply chain and logistics. I understood how physical goods moved around the world — warehouses, pallets, shipping routes. But containers in software? That meant nothing to me. ...

March 26, 2026 · 8 min · Nerav Doshi

Git: The Tool That Saves Your Code and Your Career

The Day I Nearly Broke Production Early in my Cloud career, I was making what I thought was a small change to a configuration file. I’d been working on it locally, testing it, feeling confident. Then I committed and pushed — straight to the main branch. Within seconds, a CI/CD pipeline picked up the change and started deploying it to production. My phone buzzed with an alert. My colleague looked over and said, very calmly, “Did you just push to main?” ...

March 18, 2026 · 5 min · Nerav Doshi

Linux: The Operating System That Runs the Internet

The Day I Realised Linux Was Everywhere When I first started working in Cloud and Infrastructure, I assumed most servers ran Windows — because that’s what I grew up using on my laptop. Then I got access to my first cloud environment and was greeted with a black screen, a blinking cursor, and absolutely no Start menu in sight. That was my introduction to Linux. I typed dir (the Windows command for listing files) and got an error. I tried clicking around and realised there was nothing to click. Just me, a terminal, and a lot to learn. ...

March 11, 2026 · 6 min · Nerav Doshi

What is DevOps? A Plain English Guide

Ever Wondered How Netflix Never Seems to Go Down? Think about this for a second. Netflix has over 260 million subscribers worldwide. People are watching shows in Tokyo, London, Lagos, and New York — all at the same time. And yet, when was the last time Netflix crashed on you? Now think about your favourite food delivery app. You open it, order food, track your driver in real time, and get a notification the moment your burger arrives. All of that happens in seconds. ...

February 19, 2026 · 6 min · Nerav Doshi