Technical Blog
Working notes from shipping agentic AI into production. Agent systems, MCP servers, RAG that cites its sources, evals that catch drift before your customers do, and the AIDLC method I use to move B2B teams past the pilot stage.
SpecForge: Spec-Driven AI Development With Approval Gates That Actually Block
SpecForge fuses spec-kit's executable specs with AI-DLC governance, then enforces approval with a Claude Code hook that blocks code edits until you sign off.
Read- Members
The Verification Loop: Reviewing Code Your Agents Wrote
When agents write most of the code, review stops being a checkpoint and becomes the job. A members-only playbook for building a verification loop that keeps trust high without slowing the team to a crawl.
Read - Members
Bolts: A Team Playbook for Running Agentic Work in Hours
A bolt is a short spec, generate, verify cycle that a team runs in hours instead of a week-long sprint. A members-only playbook for intake, roles, cadence, and the metrics that keep it honest.
Read 
Bolts vs Sprints: How Agentic Teams Measure Work Now
The two-week sprint was built around human typing speed. When agents write the code, the bolt replaces it. A side-by-side on planning, cadence, roles, and the metrics that change.
Read
How to Build an App With a Ralph Loop and a Goal Prompt
A practical guide to building an app by pointing a harness at a goal prompt and running it in a loop: how to write the goal, wire the verification gate, and know when to stop.
Read
How to Write a Spec an AI Agent Can Actually Build
A spec is the highest-leverage ten minutes in an agentic cycle. A practical guide to writing specs that stop intent drift, from acceptance checks to sizing for a single bolt.
Read
Managing and Training a Technical Team to Ship With Agents
Buying AI seats does not make a team agentic. In 2026 the bottleneck moved from writing code to verifying it. Here is how to retrain the workflow, the people, and the way you manage them.
Read
The Spec-to-Bolt Loop: The Agentic Development Cycle End to End
Specs and bolts are two halves of one cycle. How the spec-to-bolt loop runs end to end, from intake to verified merge, and why it scales to many agents at once.
Read
What Is a Bolt? The Work Unit That Replaced the Sprint
A bolt is the AIDLC unit of work that replaces the two-week sprint with a cycle measured in hours. What a bolt is, why AWS renamed the sprint, and how teams run one.
Read
What Is an Agent Harness? The Layer That Turns a Model Into an Agent
An agent harness is the deterministic layer that wraps an LLM: the loop, the tools, the sandbox, the permissions. Why the harness, not the model, is the 2026 differentiator.
Read
What Is Spec-Driven Development? Specs as the New Source of Truth
Spec-driven development treats a written specification as the executable source of truth and code as a regenerable output. What SDD is, why it beat vibe coding, and the tools that ship it.
Read
What Is the Ralph Loop? Agentic Coding, Deterministically Simple
The Ralph loop runs a coding agent in a plain while loop against one goal prompt, with memory in files and git instead of context. What it is, why it works, and where it breaks.
Read
The 2026 AI Transformation Playbook for UAE and Dubai Businesses
A 2026 AI transformation playbook for UAE and Dubai firms covering a phased roadmap, real ROI, PDPL and DIFC compliance, and where a consultant fits.
Read
AIDLC vs SDLC: What Changes When Agents Write the Code
AIDLC vs SDLC compared phase by phase. What AIDLC means, where effort shifts from implementation to verification, and how teams adopt agentic development.
Read
Ollama Cloud vs Claude and GPT: Real Cost, Limits, and Quality in 2026
Ollama Cloud starts at $0 and caps at $100/mo flat. Claude Sonnet runs $3/$15 per 1M tokens. Where each wins on cost, limits, and quality in 2026.
Read
Wiring Ollama Into Visual Studio 2026 Copilot the Right Way
Run local LLMs with GitHub Copilot in Visual Studio 2026 via Ollama. BYOK setup, model choices, endpoint wiring, and where local beats cloud.
Read
The Data Engineer in the Agentic Era: From Pipelines to Retrieval and Ground Truth
Agents can write the ETL. What they cannot do is decide what an agent should retrieve, how to ground it in your data, and which sources are trustworthy enough to feed a decision. Data engineering moved to retrieval and ground truth.
Read
The Engineering Manager in the Agentic Era: Managing People and Agents Together
When part of your team is human and part is autonomous, velocity metrics lie and the old planning rhythm breaks. The engineering manager's job moved to designing the operating model where people and agents ship together.
Read
The Technical Writer in the Agentic Era: From Documenting Code to Authoring Context
Agents draft docs in seconds, so writing prose is no longer the scarce skill. The technical writer's value moved to authoring the specs and context that agents read, and to making sure both humans and machines can act on it.
Read
The Security Engineer in the Agentic Era: New Attack Surfaces, Same Accountability
Prompt injection, tool abuse, and data exfiltration through an agent are not edge cases, they are the new baseline. The security engineer's job expanded from securing code to securing autonomous decision-making.
Read
The DevOps Engineer in the Agentic Era: From Pipelines to Observability for Autonomy
Agents can write the Terraform and the CI config. What they cannot do is decide what an autonomous system must expose to stay safe in production. DevOps moved from automating pipelines to instrumenting agency.
Read
The QA Engineer in the Agentic Era: From Writing Tests to Designing Evals
Deterministic test suites cannot judge probabilistic systems. The QA engineer's role moved from asserting exact outputs to designing evals, golden datasets, and LLM-as-judge suites that gate agentic behaviour.
Read
The Frontend Developer in the Agentic Era: From Building Components to Curating Them
Agents scaffold components, wire state, and match a design in minutes. The frontend developer's edge moved to design systems, accessibility, performance budgets, and the taste to reject output that merely looks done.
Read
The Backend Developer in the Agentic Era: From Writing Endpoints to Reviewing Them
Agents now write most of the CRUD, the handlers, and the glue. The backend developer's value moved to data contracts, correctness review, and the judgment to catch the bug the agent shipped with confidence.
Read
The Software Architect in the Agentic Era: Designing Boundaries Agents Can't Cross
Agents generate code fast, including the wrong abstraction fast. The architect's job shifted from drawing diagrams to designing the boundaries, contracts, and scaffolds that keep agent output inside the lines.
Read
The Product Manager in the Agentic Era: From Backlog Owner to Spec Author
When agents write the code, the product manager's leverage moves upstream. The PMs who win in 2026 author executable specs, own the success metric, and frame problems agents can act on. Here is how the role changed.
Read
AIDLC: The Development Life Cycle for Building Software With Agents
The traditional SDLC assumes humans write the code. AIDLC assumes agents do. Eight phases — Frame, Spec, Scaffold, Generate, Eval, Harden, Ship, Operate — that turn agentic speed into shipped, eval-guarded systems instead of chaos.
Read
Gemma 4 on Ollama: Multi-Token Prediction, Benchmarks, and Local Setup (May 2026)
Google's Gemma 4 update ships Multi-Token Prediction for roughly 3x faster decoding. Benchmarks against Qwen 2.5 and Llama 3.3, exact ollama pull commands, and the hardware floor.
Read
'AI Doesn't Code' Is a Skills Problem, Not an AI Problem
Engineers complain that AI hallucinates, burns tokens, and ships nothing. Each of those failures has a named technique that fixes it. The frustration is a skills gap, and the fix is a working method.
Read
How I Build AI Agent Teams That Actually Ship for B2B Companies
Most B2B companies hire for AI and end up with a single ChatGPT wrapper. The agent teams that ship use a specific architecture for roles, memory, tools, evals, and deployment. Here is the process I run with clients in 2026.
Read
riyal v1.2.0: The Saudi Riyal Symbol Toolkit for React, Vue, Svelte, and Web Components
riyal v1.2.0 ships the Saudi Riyal symbol (U+20C1) as a web font, React, Vue 3, Svelte 5, React Native, and Web Component primitives. Includes a masked SAR input, cart math with 15% VAT, a Tailwind plugin, OG cards, a CLI, and a shadcn registry. Built off the playbook that took the dirham package to 8K monthly downloads.
Read
Stop Burning Claude Tokens: How RTK Cuts AI Coding Costs 60-90% in 2026
Engineers blow through Claude Max quotas in four days because tool output floods the context. RTK is a Rust proxy that filters command output at source and reclaims 60-90% of every coding session.
Read
dirham v1.5.3: The Complete Guide to UAE Dirham in React, Web Components, and Vanilla JS
dirham v1.5.3 ships animated price counters, masked currency inputs, live exchange rate hooks, a Tailwind plugin, a Next.js font helper, and React Native support. Full implementation guide with code examples.
Read
AI Agent Memory Systems: How Claude, GPT, and Gemini Remember Context Across Sessions
Claude Projects, GPT memory, and Gemini context windows compared. How each AI maintains state across conversations, token limits, and implementation patterns for production agents.
Read
AI Code Review at Scale: How Teams Ship 40% Faster Without Sacrificing Quality
Teams using AI code review tools ship 40% faster with equivalent bug rates. Implementation patterns, tool comparison, and metrics from companies like Shopify, Vercel, and Linear.
Read
Claude Max and the High-Volume Engineer: How Senior Developers Use Anthropic's Top Tier
Anthropic's Claude Max subscription costs $350/month but enables 20x more usage than Claude Pro. Benchmarks from senior engineers who switched: code review velocity, architectural decision speed, and documentation generation at professional scale.
Read
Contentful vs Sanity vs Strapi vs Payload 2026: Developer Experience Benchmarks and Real Pricing
I fired 500 requests per tier at five headless CMS from us-east-1 in April 2026. The DX chart and the price table name different winners.
Read
CrewAI vs LangGraph vs AutoGen 2026: Benchmarks & Pricing
CrewAI pricing for 2026 next to LangGraph, AutoGen and Smolagents, plus 200 benchmark tasks each on Qwen3 32B. The cheapest plan rarely wins on cost.
Read
Hermes Agent with Ollama: The Self-Improving AI Agent That Runs Entirely Local
Hermes Agent from Nous Research runs entirely local through Ollama with 70+ built-in skills, cross-session memory, and messaging gateway integrations. Setup guide, model benchmarks, and comparison with Claude Code for autonomous workflows.
Read
Ollama Cloud Pricing 2026 and Where Self-Hosting Takes Over
Ollama revised Cloud quotas twice since GA. Three tiers measured against a 36-month amortized RTX 4090 and Mac Studio, plus the volume where each flips.
Read
Rust vs Go vs Zig for High-Performance Backend Services in 2026
Benchmarks comparing Rust, Go, and Zig for backend services. Memory safety, concurrency models, compilation times, and production experiences from teams that migrated.
Read
Why TypeScript 6.0 Is Trending: The Technical and Cultural Shift Behind the Viral Moment
TypeScript 6.0 npm downloads jumped 12.5% in two weeks after release. The trending story is not about new syntax. It is about erasable types, native NodeJS support dropping, and a decade of promises finally shipping. Here is what changed.
Read
Claude Opus 4.6 vs GPT-5.3-Codex: The State of Frontier AI Models in April 2026
Claude Opus 4.6 leads on agentic coding with computer use capabilities. GPT-5.3-Codex excels on terminal operations and web development. A detailed benchmark comparison for engineering teams choosing AI coding tools.
Read
Gemini 2.0 vs GPT-5 vs Claude 4: The Spring 2026 AI Model Rankings
Google Gemini 2.0, OpenAI GPT-5, and Anthropic Claude 4 represent the current frontier. A comprehensive benchmark comparison across coding, reasoning, multimodal, and agentic capabilities for engineering team AI tool selection.
Read
Local AI Coding Models 2026: Why Developers Pick Open Source
Ollama's top HumanEval score runs at 8 tokens per second. Four VRAM tiers, an RTX 5070 baseline, and break-even math at 500 queries a day.
Read
Maximize Claude Code: Advanced Configuration for Senior Engineers
Claude Code configuration options that separate junior from senior usage. Custom instructions, workspace modes, tool restrictions, and workflow patterns that unlock maximum productivity for experienced developers.
Read
Principles of Design with AI-Generated Photos
Explore the fundamental principles of design including balance, contrast, emphasis, movement, pattern, rhythm, proportion, unity, and white space through cinematic AI-generated black and white photographs.
Read
Reasoning Models Emergence: How Chain-of-Thought Unlocks Complex Problem Solving
Chain-of-thought reasoning models demonstrate emergent reasoning capabilities. Understanding how reasoning emerges, when it fails, and what it means for AI problem-solving in production systems.
Read
The $500 GPU That Outperforms Claude Sonnet on Coding Benchmarks
A $500 RTX 5070 running Qwen 3.5 Coder 32B outperforms Claude Sonnet 4.6 on HumanEval at 40 tokens per second. The local AI revolution has reached consumer hardware.
Read
Inside the .claude/ Folder: How Claude Code Organizes Your AI Workspace
Most teams commit it by accident. Every path Claude Code writes, the 30-day cleanup command, and how its memory holds up against Copilot and Cursor.
Read
Claude and the New Developer: How AI Is Reshaping Coding Skills in 2026
GitHub's Octoverse 2025 data plus interviews with 22 advanced AI users, charted. The language rankings flipped. So did the job description.
Read
GitHub Copilot with Ollama: Agentic AI Models Running Locally in Your IDE
GitHub Copilot now runs agentic workflows through Ollama. Deploy Qwen, DeepSeek, and Llama models locally. Zero latency, complete privacy, no API costs. Full setup guide with benchmarks.
Read
State of the Product Job Market in Early 2026
7,300 open PM roles. 67,000 engineering openings. A 340% surge in AI positions. The data on who is actually getting hired in early 2026.
Read
AI-Powered Code Migration: How We Rewrote JSONata and Saved $500K Annually
A real-world case study of using AI to rewrite JSONata in a single day, reducing infrastructure costs by $500K per year. Learn the methodology, tools, and lessons learned.
Read
AI-Scientist-v2: How AI is Automating Scientific Discovery
AI-Scientist-v2 timed against human researchers across six research phases, four agents, four domains. Where the autonomy claim stops holding.
ReadThe UAE Dirham Currency Symbol (U+20C3): Why It Took 18 Years and How to Use It Today
UAE Dirham symbol U+20C3 is now official. dirham v1.3.0 renders it today in React, Web Components, and vanilla JS with zero migration when OS support ships.
Read
GitHub Copilot Data Policy Changes: What Developers Must Know in 2026
GitHub rewrote Copilot's data terms in 2026. Which tiers it touches, the opt-out click path GitHub buries, and five assistants compared.
Read
Software Developer Job Market 2026 and Who Is Actually Getting Hired
Federal Reserve posting data charted from Q1 2023 to Q1 2026, seven sectors and six skills ranked. The headline number hides which developers get hired.
Read
Supply Chain Attacks on Developers: Lessons from LiteLLM and Trivy
Recent supply chain attacks targeting LiteLLM and Trivy expose critical vulnerabilities in developer tooling. Learn how these attacks work and how to protect your projects.
Read
TypeScript 6.0: New Features Every Developer Should Know
Three charts trace build time, memory, and inference accuracy from TS 5.0 to 6.0, plus a five-step upgrade path and the tsconfig options that break.
Read
NVIDIA Nemotron + OpenManus: $31.4B Agent Market and the Open Source Disruption
NVIDIA Nemotron 70B achieves 88.4% MMLU at 5.4x lower cost than GPT-4o. OpenManus reaches 72K GitHub stars, capturing 89% of Manus performance at 12% the cost. How open source AI agents are reshaping the $31.4B market and driving semiconductor stock valuations.
Read
MCP in 2026: The Protocol That Replaced Every AI Tool Integration
Local stdio MCP servers break once SSE traffic meets a load balancer. Sticky sessions, circuit breaker thresholds, and a charted three-year cost model.
Read
AI Reasoning Systems and the Theory of Mind Breakthrough
From pattern matching to measured reasoning. Benchmarks show large gains from chain of thought prompting and frontier model accuracy.
Read
Self-Hosting AI in 2026, the TCO Math and the Stack That Replaces Cloud APIs
Cloud inference bills climb forever. Hardware bills stop. Five charts plot 18 months of TCO, benchmark four GPUs, and mark the break-even month.
ReadAI Agents in 2026: LangGraph vs CrewAI vs Smolagents with Real Benchmarks on Local LLMs
Four agent frameworks, five local models, three tool-use benchmarks run on Ollama. GitHub stars rank them one way. The benchmark data ranks them another.
Read
RevOps AI: Build Your Entire Sales Team on Notion with Gemini and MCP
How I built a full Revenue Operations platform using Notion as the database, Gemini 2.5 Flash as the AI agent, and the Model Context Protocol to wire 22 Notion tools together without a single hardcoded query.
Read
RAG Pipelines in Production: Vector Database Benchmarks, Chunking Strategies, and Hybrid Search Data
72% of enterprises run RAG in production. Qdrant hits 6ms p50 latency. Hybrid search boosts recall 17%. Compare Pinecone, Qdrant, Weaviate, ChromaDB with embedding model scores, chunking benchmarks, and deployment patterns.
Read
Vibe Coding in 2026: $9.2B Cursor, 92% HumanEval, and the End of Boilerplate
$9.2B Cursor valuation. 92.4% HumanEval score for Claude 3.5 Sonnet. 340% enterprise adoption growth. Compare pricing, benchmarks, and productivity data for every major vibe coding platform in 2026.
Read
Local AI in 2026, Ollama Benchmarks and What Inference Really Costs
Zero per token is not zero cost. I benchmarked seven open-weight models on MMLU, HumanEval, and MT-Bench in March 2026, then ran the amortization math.
Read
The Future of AI Prediction: Uncertainty Quantification, Monte Carlo Methods & Statistical Mathematics
Deep dive into uncertainty-aware AI: Monte Carlo methods, Bayesian inference, conformal prediction, and the statistical foundations shaping the future of trustworthy machine learning.
Read
use-local-llm: React Hooks for AI That Actually Work Locally
Build AI-powered React apps that talk directly to your local models—no backend required. Stream from Ollama, LM Studio, or llama.cpp with zero dependencies and 2.8 KB of code.
Read
AI and Jobs: What Anthropic's Labor Market Data Actually Shows About Your Career
Headline AI risk numbers measure capability, not deployment. All 22 occupation categories from the Anthropic Economic Index, plus the hiring regression.
Readdirham: The UAE Dirham Symbol (U+20C3) as Web Font, CSS Utility & React Component
The dirham npm package brings the UAE Dirham currency sign (U+20C3, Unicode 18.0) to production via a custom web font, React SVG component, CSS utility class, and JavaScript formatting utilities. Drop the font import when native OS support ships in September 2026.
Read
scss-helper v5: A Modern SCSS Utility Toolkit for Tailwind's Gaps
scss-helper v5 is a modern SCSS/CSS utility toolkit that complements Tailwind CSS v3/v4 with design tokens, fluid clamp() typography, container queries, dark mode, golden ratio layouts, a 12-column grid, and animations. All classes use the sh- prefix. Only 5.1 KB gzipped.
Read
vue-multiple-themes v4: Dynamic Multi-Theme Support for Vue 2 & 3
A deep dive into vue-multiple-themes v4, the open source library for dynamic CSS custom property theming in Vue 2.7+ and Vue 3. Covers the useTheme() composable, TailwindCSS plugin, WCAG contrast utilities, and dynamic theme generation from a single brand color.
Read
vue-star-rate: Zero-Dependency Vue 3.5+ Star Rating Component
Introducing vue-js-star-rating, a WCAG 2.2 accessible, TypeScript-first star rating component for Vue 3.5+. Half-star precision, multiple icon providers, full keyboard navigation, read-only mode, RTL support, and zero runtime dependencies.
Read
The CEO's Guide to Private AI in Dubai 2026: PDPL and DIFC Compliance
UAE Decree-Law 45 and DIFC Regulation 10 penalize public AI usage. This guide shows how on-premise AI keeps your Dubai business compliant and audit-ready.
Read
Best Headless CMS 2026: Pricing, Total Cost, and How to Choose
Headless is commoditized. The real split runs developer frameworks against enterprise orchestrators. Six platforms compared on architecture, AI, and TCO.
Read
WEF Future of Jobs Report 2025: 78M Jobs Created, 92M Displaced
WEF Future of Jobs 2025 data: 78M new roles, 92M displaced, 39% skills gap. See which jobs grow, which vanish, and what skills matter most through 2030.
Read
React useEffect & useCallback in 2026: Stop Unnecessary Re-renders (React 19 Guide)
Fix unnecessary React re-renders: master useCallback, useMemo, React.memo, and the new React 19 use() hook with real-world patterns, profiling tips, and pitfalls to avoid.
Read
Next.js 15 vs Astro 5 vs Remix in 2026: Which Framework Should You Choose?
Next.js 15, Astro 5, and Remix compared on performance, bundle size, and real use cases. Includes a decision framework to pick the right one for your project.
Read
AWS ECR in 2026: Pull, Inspect, Scan & Automate Docker Images: Complete Guide
Complete AWS ECR guide: authenticate with OIDC, pull Docker images, extract filesystem layers, scan with Amazon Inspector v2, set lifecycle policies, and automate with GitHub Actions.
Read
ArangoDB on AWS: Automate Install, S3 Backup & Restore with Systemd
Production-ready shell scripts for ArangoDB on AWS EC2: automated install, daily S3 backups via systemd timers, and one-command point-in-time restore.
Read
SSH SOCKS5 Proxy in 2026: macOS, Linux, Windows & sshuttle: Complete Guide
Turn any SSH server into a private VPN with one command. Includes toggle scripts for macOS/Linux, Bitvise setup for Windows, and sshuttle vs WireGuard comparison.
Read
Firebase Cloud Messaging in 2026: Web Push Notifications with Vue 3 & SDK v10
Step-by-step Firebase Cloud Messaging v10 setup with Vue 3: VAPID keys, service workers, foreground/background notifications, and Node.js server sending.
Read
Deploy Jekyll to GitHub Pages in 2026: GitHub Actions, Custom Domain & Cloudflare
Deploy Jekyll with a GitHub Actions CI/CD pipeline, configure a custom domain with HTTPS, and add Cloudflare CDN for speed and DDoS protection. Complete 2026 guide.
Read