Writing
Notes on building AI that ships
Agentic AI, architecture, scaling teams, and the fractional-CTO playbook — from the trenches.
Jul 22, 2026Agent State Machines: Stop Runaway Agents With Explicit StatesJul 22, 2026Inkling: The US Open-Weights Model That Rewrites the Self-Host CalculusJul 21, 2026Prompt Caching Is the Fastest ROI in Your LLM Stack Right NowJul 21, 2026GPT-5.6 Context Window Cut: The 2× Billing Trap AuditJul 20, 2026Agent Observability: The Telemetry Gap Killing Your Agentic StackJul 20, 2026Agentic AI Just Ran Its First Confirmed Production BreachJul 19, 2026Tool Calling at Scale: Why Agent Tool Design BreaksJul 18, 2026Agent Failure Modes: 5 Production Breaks Nobody DemosJul 17, 2026RAG Reranking: The One Layer Most Teams Skip That Kills PrecisionJul 17, 2026Kimi K3: What 2.8 Trillion Parameters Actually Means for Your StackJul 16, 20265 Signals It's Time to Hire a Fractional CTOJul 15, 2026Hybrid RAG: When Vector Search Alone Stops Being EnoughJul 15, 2026ChatGPT Work Has Write Access: The Security Tax You Must PayJul 14, 2026Fine-Tune vs. Prompt Engineer vs. RAG: A Decision Table for 2025Jul 14, 2026Grok 4.5: The Token Efficiency Number That Rewrites Agentic Cost MathJul 13, 2026The MENA Engineering Leadership Traps No Playbook Warns You AboutJul 13, 2026Meta Muse Spark 1.1: The 6x Output Cost Gap Changes Inference MathJul 12, 2026The AI ROI Audit: 5 Signals That Separate Real Gains from TheaterJul 12, 2026Ultra Mode vs. Your Custom Orchestrator: Make the Call NowJul 11, 2026Your AI Stack Is Your Cap Table: Investors Audit ThisJul 11, 2026GPT-Live-1: The UX Gap Your Voice Agent Can't Close YetJul 10, 2026RAG Is Not Retrieval: 5 Pipeline Mistakes Killing AccuracyJul 10, 2026GPT-5.6 Is Live: The Terra Cost Play Every Team Should Run NowJul 9, 2026Agent Memory: The Bottleneck Killing Multi-Agent SystemsJul 8, 2026Technical Due Diligence: 11 Red Flags That Kill AI Startup DealsJul 8, 2026gpt-realtime-2.1: The 25% Latency Cut That Changes Voice Agent EconomicsJun 17, 2026The US Pulled Fable 5 in 96 Hours. Plan for It.Jun 15, 2026Claude Fable 5 Is Free Until June 22 — Here's the PlayJun 15, 2026AI Cost Governance: A Playbook for Variable AI BillsJun 15, 2026Anthropic Ended Flat-Rate Agent Billing: Reprice NowJun 14, 2026Multilingual Codebases: Engineering Culture in MENA TeamsJun 14, 2026OpenAI Killed Agent Builder: Price Platform Risk NowJun 13, 2026AI Readiness Is a Data Problem, Not a Model ProblemJun 13, 2026OpenAI's August 26 Hard Cutoff: Migrate Assistants API NowJun 12, 2026AI ROI Map: Where It Pays, Where It Pretends ToJun 12, 2026GitHub Copilot Went Token-Metered: Reprice Your Dev Stack NowJun 11, 2026OpenAI and Anthropic Both Filed S-1s: What CTOs Must DoJun 11, 2026The Orchestrator Trap: Why Your Multi-Agent System Keeps Falling Apart at the SeamsJun 11, 2026When the Vendor Becomes the Ceiling: How to Spot the AI Platform Lock-In Before It Costs YouJun 11, 2026GPT-5.3-Codex Is the First AI Coding Agent That Actually Closes the Full Software LifecycleJun 11, 2026Scheduled Agents + Self-Hosted Sandboxes: Anthropic Just Closed the Demo-to-Production GapJun 11, 2026The AI Build-vs-Buy Trap: Why the Wrong Question Is Costing You MonthsJun 11, 2026The Hiring Sequence That Breaks Scaling Teams (And What to Do Instead)Jun 10, 2026The AI Product Stability Stack: What to Wire Up Before You Move FastJun 8, 2026Why MENA Engineers Ship Faster When You Remove the Approval LayerJun 7, 2026Stop Paying for Tokens You Don't Need: A Practical Guide to LLM Cost ControlJun 7, 2026You Don't Need a Full-Time CTO — You Need the Right Decisions Made Now
The AI CTO playbook
Get my AI playbooks — straight to your inbox
Practical notes on shipping production AI, scaling teams, and the calls a CTO actually has to make. A few times a month. No spam, no fluff.