PODCAST 8 min
I haven't written a line of code in two years. Agents write it
Tasks left to agents overnight and the morning bin, Claude Code and Codex paired like pair programming, and why not programming is now the expensive part.
CLAUDE CERTIFICATION 14 min
Claude exam vouchers in India: what exists today
Anthropic sells no Claude exam vouchers. USD fees converted to INR, who can register, the employer route and 7 checks before you pay anyone.
PODCAST 11 min
Web3, AI, robotics: what remains when the hype fades
What survived the Web3 hype in payments, why an AI agent cannot open a bank account, and why robots are trained in one data center today.
FORWARD DEPLOYED 11 min
What Is a Forward Deployed Engineer? Role, Pay and Who Hires
What a forward deployed engineer (FDE) does, how the role differs from software and solutions engineers, posted salary ranges and who hires FDEs in 2026.
FORWARD DEPLOYED 10 min
Forward Deployed AI Engineer: The Job, the Work and Who Hires
What a forward deployed AI engineer does on LLM and agent projects, how it relates to applied AI engineer, and who hires: OpenAI, Anthropic, Google.
FORWARD DEPLOYED 11 min
How to Become a Forward Deployed Engineer: 5 Steps
How to become a forward deployed engineer: the skills eight live FDE postings ask for, five steps to the job, and whether you need a course or certification.
GEMINI 4 13 min
Gemini 4 Argon: what Google announced and what it means
The 1M-token output limit, benchmarks, pricing, Google's own case studies and the rollout order. Timeline and sources.
GEMINI 4 11 min
Gemini 4 vs GPT-6 Astra vs Claude: reading the benchmarks
Google's table row by row: where Argon wins, where it loses, who built the benchmarks and how to pick a model for a client.
GEMINI 4 11 min
Gemini 4 Argon API pricing and the 1M-token answer
What a million-token answer costs, when caching pays and why a budget should start from the post-promo price.
GEMINI 4 11 min
Gemini 4 Argon release date: who gets it first, and when
The Fairwind Program, US government pre-release access, then the paid API and Google AI Ultra. What is known about the EU, and whether it is Gemini 4 Pro.
DEVDAY 2026 12 min
OpenAI DevDay 2026: Every Announcement and What It Means
Dots, GPT-6.1 Sol, Ultrafast, Pro 500, the Agents API and Codex cloud. The keynote minute by minute and what works in the EU.
DEVDAY 2026 9 min
OpenAI Dots: ChatGPT's always-on agents, and who can use them
Who can get a dot, what it costs, and what a company has to decide before an agent starts working around the clock.
DEVDAY 2026 10 min
GPT-6.1 Sol, Ultrafast and Pro 500: OpenAI pricing after DevDay 2026
Against GPT-6 Sol, only the cache got cheaper. Ultrafast costs six times more and skips EU residency. The math is per task.
DEVDAY 2026 10 min
OpenAI Agents API: Codex's harness as a service and computer use
What the harness does for you, what stays your job, and why US-only data can end the conversation for an EU company.
DEVDAY 2026 9 min
Codex cloud after DevDay 2026: environments, CLI, code review
What changes when a coding agent runs in the cloud, what is new in the CLI and code review, and what to set up before it works unattended.
DEVDAY 2026 11 min
ChatGPT Space, Pages, plugins: what DevDay 2026 changes at work
What to switch on first at work, what to check before you start, and what the new ChatGPT features do not give you under GDPR.
DEVDAY 2026 6 min
AI Consultants After DevDay 2026: Where the Work Will Be
Five client jobs OpenAI's launches leave open, what happened to the OpenAI Partner Network, and which skills the work needs.
AI CONSULTING 9 min
AI Consultant Jobs: Where to Find Work and Client Projects
Where to find AI consulting jobs, contracts and freelance projects. Prepare a portfolio, respond to a brief and agree on the scope of a first pilot.
AI CONSULTING 9 min
AI Certifications for Consultants: Claude, AWS and Microsoft
Compare Claude, AWS and Microsoft certifications and OpenAI learning options. Scope, access, costs and a project that demonstrates your AI consulting skills.
NEWSLETTER 3 min
Introducing The Agentic Architect: a weekly newsletter on building AI agents
Once a week: one agent architecture pattern, one case study from production and the AI news that changes how you build.
OPENAI PARTNER 5 min
OpenAI Select Partner: what the status means
A company tier in the OpenAI Partner Network: the three tiers, the road to the status and how it differs from a certificate.
CLAUDE CERTIFICATION 7 min
Anthropic Claude Certification: Associate, Developer & Architect
Compare the four Claude certifications: Associate, Developer and Architect Foundations or Professional. Exam scope, fees, access and choosing by role.
CLAUDE CERTIFICATION 9 min
Claude certification cost in 2026: $99 to $175, and what is free
What each Claude exam costs, whether Claude Certified Architect is free, partner discounts, retakes, renewal and a first-year budget. Checked September 2026.
CLAUDE CERTIFICATION 8 min
Can you register for Claude Certified Architect (CCA-F / CCAR-F) without a partner?
Partner-account and email-domain requirements, plus your options when your company is outside Claude Partner Network.
CCAR-P 11 min
Claude Certified Architect Professional: CCAR-P Exam Guide
CCAR-P exam guide: 63 questions, seven domains, the $175 fee and differences from Foundations. A study plan and three original questions with explanations.
CLAUDE CERTIFICATION 7 min
Is Claude Certified Architect worth it? Jobs and demand in 2026
Who hires Claude certified architects and why: partner tier thresholds, 200,000 certifications committed by ten firms, and what the certificate changes.
SYSTEM ONE 16 min
Non generative AI. What Jev returns instead of sentences
Jev answers with a probability distribution rather than prose. 372 calls over this blog: what it measured, and what it loses to a boring classifier.
HARNESS 16 min
The harness is not the model. What you actually pick when you install an agentic CLI
Who really welds the harness to the provider, what the Claude Agent SDK actually locks, and the five layers a model swap rewrites.
POWER 15 min
AI Futures: OpenAI asks who holds power when AI stops needing people
A good argument, the same one Anthropic published seven months earlier, and one citation that leads back to OpenAI.
GTM 19 min
The AI GTM stack: five stages you can buy, four handoffs you define
The four handoffs between funnel stages that no vendor sells, what an agent can run alone, and where a person still has to stand.
VERIFICATION 16 min
A public report written with AI: nine errors you can see in the file
A number that contradicts its own footnote, one methodology in three versions, and nine checks that stop all of it.
MUTATION TESTING 17 min
Mutation testing: can you trust AI-generated tests?
Coverage measures execution, mutation score measures assertion. How mutation works, what it found in production code, and how to run it in CI.
TRAINING 14 min
AI training for a non-technical team: how to run it
One task instead of twenty tools, the sceptic against the blocker, and six failures from outside the programme. Built on a session for the TVP Television Academy.
COST 9 min
What an AI agent costs and what actually drives the quote
Six line items a quote is made of, two of which only show up after launch. How to count a deployment in days of work instead of licences.
SECURITY 9 min
Prompt injection: an instruction hidden in content the agent fetches itself
How prompt injection works, five risks specific to agents, and a checklist your team can run before the agent reaches production.
TRAINING 10 min
AI agents on a team: what training gives you and who is ready
Agents are one of the last steps of AI adoption, not the first. What a team learns in two days, what it will not learn, and who should skip it.
WORKFLOW STUDIO 13 min
Workflow Studio: observe and design Claude Code workflows
A local dashboard that reads Claude Code's own run artifacts, plus a 12-block canvas that compiles to a runnable Workflow script.
CLAUDE CERTIFIED 8 min
Claude Certified Architect (CCAR-F): What It Is, Exam Format and Study Guide
Claude Certified Architect Foundations in one guide: 60 questions, 120 minutes, 720 to pass, five weighted domains, who should take it and a study plan.
CLAUDE CERTIFIED 11 min
60 Claude Certified Architect Exam Questions & Answers (CCAR-F)
All 60 CCAR-F practice questions with answers and explanations, plus three worked through with the traps and where to study.
CLAUDE CERTIFIED 4 min
Claude Certified Architect Foundations: my exam experience
I passed CCAR-F on July 15, 2026. My account of check-in, proctoring, choosing answers and how my exam compared with the sample questions I used to prepare.
RULES 13 min
12 rules for building agents
Notes from prepping for the Anthropic certification. The rules that decide whether an agent survives production.
CLAUDE PARTNER 5 min
Claude Partner Badge Claude Code: what it is
Eight Anthropic courses and a capstone: the Claude Code learning path and what its partner badge confirms.
OPEN SOURCE 4 min
awesome-ai-gtm: a map of the autonomous GTM funnel
138 AI tools arranged into 7 funnel stages. Not a link list, but a blueprint.
PITFALL 5 min
Model self-evaluation: the agent that grades itself
The most common agentic engineering pitfall — and the fix.
PITFALL 5 min
Multi-agent consensus isn’t verification
Three models agree and fail the same way. What to do instead of voting.
BUILD LOG 4 min
RATCHET: iterating against a frozen yardstick
Keep-if-better, else revert — a pattern you can’t game.
PITFALL 5 min
Silent failures in agentic systems
Silent retry and fallback return “OK” and hide the errors.
BUILD LOG 5 min
Position bias: the first answer wins on order
An adversarial panel with rotation instead of a single judge.
PITFALL 4 min
A confidence score isn’t correctness
Confidence is a tone of voice. Validate it from the outside.
PATTERN 5 min
Bounded Autonomy in AI Agents: Definition and Framework
What bounded autonomy means, its four pillars and how it differs from constrained and governed autonomy.
PATTERN 3 min
5 questions before deploying AI
A checklist that will save you months and thousands.
PATTERN 3 min
AI Governance: How not to lose a million
A governance framework that works in practice.
PATTERN 5 min
Multi-Agent Systems: When one agent isn't enough
Orchestrating multiple agents and communication patterns.
PATTERN 3 min
Hybrid AI: Combining models for better results
When and how to combine different AI models in one system.
BUILD LOG 3 min
AI in logistics: A deployment case study
How we built an agent for route optimization.
BUILD LOG 3 min
From pilot to scale: Lessons learned
What changes when an agent hits production.
BUILD LOG 3 min
AI Stack for your company: My tool choices
The stack I use in every agent project.
ESSAY 4 min
Agentic AI in 2026: From experiments to production
62% of companies are experimenting with AI agents. Only 11% have them in production.
ESSAY 3 min
Why AI strategies end up in a drawer
Strategy documents vs. real change in the organization.
ESSAY 3 min
ROI from AI: How to measure it without fooling yourself
The metrics that actually show the value of a deployment.
ESSAY 4 min
Legacy Systems vs AI: How to bridge old and new
Integrating AI agents with existing infrastructure.
ESSAY 3 min
6 roles of a CTO in the AI era
How the role of the tech leader is changing.
SECURITY 3 min
AI Ethics Lead: A new role on the team
Why every AI team needs someone owning ethics.
SECURITY 3 min
Workforce 2026: AI and the future of work
How to prepare your team to work alongside AI agents.
Newsletter
The Agentic Architect
Practical patterns, case studies and AI news. Zero spam, once a week.
You'll get one email to confirm. Unsubscribe with one click. Privacy policy