Sonith ManakkatArticles
Picture-led, plain-language explanations of AI tools, software engineering, and the industries I work in, each with an expert layer for readers who want more depth.
Series
Claude AI: from first steps to mastery
A twelve-part, picture-led path from what Claude is, through prompts, plans, pricing and tokens, to context, CLAUDE.md, skills, sharing with a team, MCP versus APIs, Claude Code and a map of the wider AI tools landscape.
Software engineering, explained
Clean architecture, building apps with AI help, the forward deployed engineer role, agile in the age of AI, a two-part playbook for planning and running short AI-era delivery cycles, and a balanced look at vibe coding, explained without jargon.
Industry software, explained
How warehouse systems, finance software and digital twins work, for people who are not engineers.
Algorithms explained
A twelve-part, picture-led tour of how algorithms work, from judging speed with Big-O to sorting, searching, graphs, hashing, dynamic programming, machine learning and encryption.
Trading explained
A nine-part, picture-led explainer of how markets, orders, intraday trading, options, risk and automated trading systems work. General education only, not investment advice.
All articles
Claude AI: from first steps to mastery
What is Claude AI? A plain-language guide
Who makes Claude, what a language model is, what it can and cannot do, and how people use it, with the newest models as of 21 October 2026.
The basics to understand before you use Claude seriously
The prompt, system prompts, the context window, thinking, tools, agents and hallucination, each explained with a picture first and an expert layer second.
How to get really good with Claude: ten practical habits
Clear prompts, context, examples, planning, iteration and checking, with before-and-after prompts, and how to give Claude standing instructions.
Claude pricing and plans explained
Plans for people and teams versus paying per token through the API, why input and output cost differently, and how caching and batching cut the bill. Prices checked on 21 October 2026.
Tokens explained: how to use Claude without wasting them
What a token is, why long chats cost more and work worse, and nine practical ways to save tokens, with a small calculator where you enter your own rates.
Context explained: what Claude knows right now
What goes into Claude's context, why long chats get worse and cost more, what survives compaction, and practical ways to give Claude exactly the right context.
CLAUDE.md and memory: teach Claude once, reuse forever
What CLAUDE.md is, where it lives, what to put in it (and what never to), how auto memory differs, and how Projects in the Claude app do a similar job.
Skills explained: reusable know-how packages for Claude
What Agent Skills are, how a skill is just a folder with a SKILL.md, why skills save context, and how they differ from prompts, CLAUDE.md, MCP and subagents.
Reuse context and share it with your team: a practical playbook
How to turn what you taught Claude into something the whole team shares: CLAUDE.md in git, project skills, shared connections, plugins, Projects, plus a cheat sheet for choosing the right tool.
MCP vs API: what is the difference, and when do you need which
A picture-led comparison of the Model Context Protocol and ordinary APIs: who calls whom, how tools are discovered, why they are partners rather than rivals, the security picture, and how to try an MCP server safely in Claude Code.
Claude Code and AI agents for builders, and how to use them safely
What Claude Code is, how an agent loop works, which permissions protect you, how skills, subagents, hooks and MCP fit in, and a safe working routine.
The AI tools landscape: from beginner to advanced
A depth ladder of AI tools by what you want done and how much control you give: beginner chat and writing, intermediate voice, video and automation, advanced agents and connections, with a decision path, a permission ladder and a 30-day plan.
Software engineering, explained
Clean Architecture in .NET Core, explained simply
A kitchen analogy for layers, the one rule that makes the design work, a small C# example, what it does for testing, common mistakes, and when not to use it.
How I build small Android apps with AI assistance
A first-person, honest account of designing, building, testing and preparing 24 small offline Android apps with AI tools, what the AI does well and badly, and why a human still reviews everything.
Forward Deployed Engineering explained
What a forward deployed engineer does, where the term comes from, how the role differs from nearby roles, and how AI is making it more important.
Agile in the age of AI: shorter cycles, same discipline
Do we still follow agile when AI writes much of the code? Yes, but compressed: shorter cycles, sharper briefs, stricter verification, and lessons fed back into the team's instruction files.
Planning short delivery cycles in the AI era: the board and the plan
A practical playbook for planning one-to-three day delivery cycles when AI does much of the building: the board, a 30 to 45 minute planning ritual, sizing by verification effort, and a worked week.
The AI-era delivery system: roles, meetings, quality gates and release
Part B of the playbook for short AI-assisted delivery cycles: who briefs, builds, verifies and ships, the three meetings, ready and done, quality gates, release and rollback, and sharing context with a team.
Vibe coding explained: what it is, where it works, where it breaks
A balanced, picture-led guide to vibe coding: what the term means, a spectrum from pure vibe to careful AI-assisted engineering, where each fits, the honest limits, a safety checklist and a gate between prototype and production.
Industry software, explained
How a warehouse management system works
From the truck arriving to the parcel leaving, a picture-led tour of receiving, putaway, picking, packing and shipping, and the software that keeps track of every item.
Software in finance, explained for non-technical people
Why software that handles money is built differently: ledgers and double-entry, accuracy, audit trails, reconciliation, idempotency, security and a compliance mindset. General education only.
Digital twins and simulators in industrial automation, explained
What a PLC does, what a digital twin is, how simulators let engineers test control software safely before it touches a real machine, and why this matters.
Algorithms explained
Big-O: how we judge algorithms
What an algorithm is, why we count steps instead of seconds, and how Big-O describes the way work grows as a job gets bigger, with everyday pictures for each common class.
Searching: linear and binary search
Two ways to find an item in a list, shown as animations: look at everything, or halve a sorted list again and again. What each costs and when each is the right tool.
Sorting: bubble, insertion, merge and quick sort explained
Four ways to put things in order, shown as animated bars, with the idea behind each, what it costs, which are stable, and when each one is a good choice.
Hashing and hash tables
How a hash function turns a key into a bucket number so lookups take about one step on average, what collisions are, how tables grow, and why password hashing is a different job.
Graphs: BFS, DFS and shortest paths
How a map of towns and roads becomes a graph, and how breadth-first search, depth-first search and Dijkstra's algorithm explore it, with animated pictures and the costs of each.
Recursion and dynamic programming
How a problem that contains smaller copies of itself can be solved by recursion, why naive recursion can explode, and how remembering answers (dynamic programming) fixes it.
Greedy, divide and conquer, and backtracking
Three classic problem-solving styles, grab the best now, split the job, or try and back up, with everyday pictures, when each works, when it fails, and how to choose.
Trees and heaps
How trees organise data like a family tree, how a binary search tree finds things quickly, and how a heap always hands you the most urgent item first.
How ranking and recommendations work
A general, plain-language look at scoring, similarity, "people who liked this also liked that", the idea behind PageRank, and the cautions around bias, feedback loops and privacy.
How machine learning algorithms learn
Learning from examples instead of fixed rules, gradient descent as walking downhill, decision trees, neural networks, overfitting, and how this connects to language models.
Encryption and digital signatures, the basics
How locks and keys explain encryption, why there are two families (shared-key and public-key), what digital signatures prove, and how HTTPS combines them. Concepts only, no recipes.
Choosing the right algorithm
A decision cheat sheet that turns the whole series into questions you can ask about a problem, plus the practical advice experts give about measuring, clarity and using libraries.
Trading explained
How markets work, in plain words
A market is a meeting place for buyers and sellers. This part explains exchanges, brokers, the order book, the bid-ask spread, how a trade happens, settlement and liquidity, with pictures.
Order types and the life of an order
Market, limit, stop and stop-limit orders explained with illustrative numbers, plus the life of an order from creation to fill or cancel, partial fills, rejections and slippage.
Intraday trading explained
What intraday trading means, how square-off, leverage and margin work, why costs and time pressure matter, and a plain statement of the risks. General education, not advice.
Options explained for beginners
What calls and puts are, how strike, expiry and premium fit together, what an option is worth at expiry, and why buyers and sellers face very different risks. Illustrative numbers only.
The Greeks and implied volatility in plain words
Delta, gamma, theta, vega and rho are the dials that show how an option's price tends to react. Implied volatility is the market's uncertainty expressed as one number. Illustrative values only.
Shares, futures and options compared
What you own or owe with a share, a futures contract and an option, how leverage and expiry change the risk, and why derivatives exist at all. Illustrative examples only.
Risk management basics
Why the first question is how much could be lost, and how position size, stop limits, drawdown, diversification and pre-order checks work. General education only.
How an automated trading platform is built
A generic tour of the parts of an automated trading system: data, decisions, an abstention gate, risk checks, an order state machine, an operator console, and safeguards.
Common mistakes and myths
Picture cards for common myths, plain explanations of over-leverage, emotional trading, overfitting and other biases, scam red flags, and habits that are education rather than advice.