Faster to What? The Four Ways to Build Software with AI
Waterfall, Agile, AI Build, Vibe Coding — AI promises a prototype in days. But most teams want a reliable car, not a supercar. How to pick your approach.
Featured essay · Jun 1, 2026 · AI & Machine Learning
How to Measure ROI from AI in Engineering Teams (Without Fooling Yourself)
AI coding feels faster, but one study found developers 19% slower while feeling 20% faster. How to measure real AI ROI with DORA and SPACE.
More from this week
01Faster to What? The Four Ways to Build Software with AI5 min read02The Next Leap Isn't a Smarter Model — It's Models That Review Each Other7 min read03Fable 5 Is Here — and the Way Anthropic Gates Its Most Powerful Models Tells a Story6 min read04Agentic AI in Software Engineering: Productivity Leap or Expensive Trend?6 min read
Archive · 55 postsView all →
/calculatorHome Loan EMI CalculatorCalculate home loan EMI, compare interest rates across Indian banks, analyze prepayment options, and view detailed amortization schedules./calculatorSIP vs FD Calculator (India)Daily-refreshed Market Mood Index, post-tax SIP/FD verdicts, and AMFI-sourced category returns. Free, transparent, and honest about taxes./utilityImage Metadata & AI AnalyzerExtract image metadata, generate AI-powered captions, tags, and keywords. Supports Ollama, LM Studio, OpenAI, and custom endpoints./utilityAI Prompt OptimizerAnalyze and refine your AI prompts for clarity, specificity, and ethics. Detects vague words, bias, and missing elements, with customizable refinement options.
Section · /tools
Interactive tools, indexed.
~/tools $
/ focus · ↵ open · ★ featured
01home-loan-calc(1)Calculate home loan EMI, compare interest rates across Indian banks, analyze prepayment options, and view detailed amortization schedules.calculatoropen →02sip-fd-calc(1)Daily-refreshed Market Mood Index, post-tax SIP/FD verdicts, and AMFI-sourced category returns. Free, transparent, and honest about taxes.calculatoropen →03image-metadata-analyzer(1)Extract image metadata, generate AI-powered captions, tags, and keywords. Supports Ollama, LM Studio, OpenAI, and custom endpoints.utilityopen →04prompt-optimizer(1)Analyze and refine your AI prompts for clarity, specificity, and ethics. Detects vague words, bias, and missing elements, with customizable refinement options.utilityopen →05video-to-animated(1)Convert video clips to animated WebP or GIF images. Features trimming, presets for Discord and social media, and quality controls. All processing happens locally in your browser using FFmpeg.converteropen →06markdown-to-slack-conv(1)Convert standard Markdown or formatted text to Slack's mrkdwn format. Perfect for developers posting formatted messages in Slack.converteropen →07family-roots(1)Build and preserve your family story. Add members, link generations, upload photos and export your family history — all stored privately on your device.utilityopen →08ai-job-risk-calc(1)Assess how AI will impact your job. Get a personalized risk score based on your role, work composition, experience, and AI skills — with actionable career recommendations.analyzeropen →
Section · /projects
Side projects & experiments.
Tools and small games built in the open. Source on GitHub.
A quiet dispatch when something ships.
One email per essay or tool — no drip, no upsell, unsubscribe in one click. Roughly twice a month.
55 posts published8 tools shipped0 trackers on this page
Section · /post
Recent essays & field notes.
Long-form on software, AI, and the practice of building things you actually use.
13JUN · 2026
5 min read
read →
read →
10JUN · 2026
The Next Leap Isn't a Smarter Model — It's Models That Review Each Other
Single models hit diminishing returns. The next gains come from making top models critique each other: debate, judge, synthesize — with starter code.
7 min read
read →
read →
10JUN · 2026
Fable 5 Is Here — and the Way Anthropic Gates Its Most Powerful Models Tells a Story
Anthropic shipped Fable 5, a tier above Opus. Its pricing and constraints reveal a philosophy: the more capable the model, the more carefully it's gated.
6 min read
read →
read →
01JUN · 2026
Agentic AI in Software Engineering: Productivity Leap or Expensive Trend?
Uber burned its 2026 AI budget by April; Microsoft cut Claude Code seats. Yet the gains are real. Is agentic coding a leap or an expensive trend?
6 min read
read →
read →
01JUN · 2026
When AI Spend Becomes Waste: A Cost-Governance Framework for Engineering Leaders
Enterprises will spend $665B on AI in 2026, yet 73% can't prove a return. A practical governance framework to stop experiments becoming budget leaks.
8 min read
read →
read →
01JUN · 2026
Open-Source vs Paid AI Tools: Which Is Actually More Cost-Effective in 2026?
Open-source AI isn't free — it shifts cost from an API bill to your payroll. The real total cost of ownership, the break-even point, and how to choose.
6 min read
read →
read →