The resource
Articles & guides
Field notes on building for the cloud and adopting AI without the hype. Written for engineers and the people who lead them.
Your AI Policy Is a PDF. Make It Executable.
Acceptable-use PDFs don't govern agents — permission scopes, tool allowlists, hooks, and CI gates do. Move policy from the wiki into configuration where it's enforced by default.
Read articleYou're Paying for the Same AI Five Times
GitHub, Atlassian, Slack, your IDE, and your cloud provider each sell you the same assistant. An overlap audit and a 'one primary tool per job' rule beats consolidating by inertia.
August 5, 2026Kill Your Pilot
AI pilots without an end date become permanent budget lines that never produce a decision. Every pilot needs graduation criteria, a kill date, and a named owner accountable for calling it.
August 3, 2026Delegation Without Atrophy
An RCT found AI-assisted developers scored 17% lower on comprehension. The skills that decay are exactly the ones verification depends on — so treat skill maintenance as a managed budget.
July 31, 2026Estimate the Review, Not the Writing
Story points measured human drafting effort, which agents just zeroed out. Work is now bimodal: size verification cost, split agent-eligible from human-led lanes, and cap agent output at review capacity.
July 29, 2026The "AI-First" Memo Won't Save You
Executive AI mandates reliably produce gamed metrics and compliance theater. Mandate the conditions — a funded paved road, friction-killing, outcome metrics, protected skeptics — not the behavior.
July 27, 2026You Don't Have a Multi-Agent Problem
Multi-agent architecture is the microservices of 2026. Name the ceiling you actually hit — context saturation, tool overload, parallelism, capability isolation — or build one well-harnessed agent instead.
July 24, 2026Keep Hiring Juniors. Yes, Still. Especially Now.
The junior hiring freeze is manufacturing a senior shortage. The collapse is mostly macro — and orgs that redesign the on-ramp around specification, review, and judgment will own the mid-level talent pool in three years.
July 22, 2026Stop Watching the Cursor: Managing Coding Agents Like Delegated Work
Background agents moved the game from pair-programming to async delegation, but most teams still babysit. The transferable skill is management — scoped handoffs, review budgets, delegation logs — not prompting.
July 20, 2026Legacy Code Is the Killer App for Coding Agents
Greenfield demos mislead pilot selection. Coding agents' real ROI is in discovery, characterization tests, and mechanical migrations on the code nobody wants to touch.
July 17, 2026Your Test Suite Is the Autonomy Dial
How much autonomy you can safely give a coding agent is set by your weakest verification layer, not the model's IQ — with a four-level autonomy ladder and anti-reward-hacking practices.
July 15, 2026Write It Down or the Agent Makes It Up
Agent output quality tracks documentation quality, not model quality. AGENTS.md/CLAUDE.md turn tribal knowledge into a maintained dependency — and agent failures become documentation bugs.
July 13, 2026Your DORA Metrics Can't See Your AI Investment
Developers using agents ship far more, yet DORA metrics barely move. Why your delivery metrics can't see your AI investment — and the three things to instrument before you scale.
July 10, 2026The Token Bill Is the New Cloud Bill
Consumption-priced coding agents have no natural ceiling, and the variance is what kills budgets. A FinOps-from-day-one playbook so the token bill doesn't ambush you the way the cloud bill once did.
July 8, 2026Foundry vs. Gemini Enterprise: Choosing an Agent Platform Without Betting the Farm
Two rebrands in eight months tell you the abstractions aren't stable yet. Why 'Foundry or Gemini Enterprise?' is the wrong question — and how to get value now while keeping your switching costs low.
July 6, 2026Your Agent Has a Confused Deputy Problem
The scary agent demo is the one that succeeds — using its own credentials, not the user's. Tool poisoning, the confused-deputy problem, and the boring controls that actually shrink the blast radius.
July 3, 2026Who Reviews the Robot's Code?
Coding agents didn't remove work — they moved it from writing to reviewing, the real bottleneck. How to redesign code review for the agent era before your senior engineers drown.
July 1, 2026The Token Bill Nobody Forecasted
Agent cost isn't a bigger chatbot bill — it's a different function driven by fan-out, growing context, retries, and model choice. How to forecast it by tokens-per-completed-task and keep it predictable.
June 29, 2026Your AI Pilot Isn't Failing — Your Scoreboard Is
A VP told me their AI rollout was "a wash." The verdict was wrong — not because the tools are magic, but because the scoreboard measured the wrong things. Fix the instrument before you judge the pilot.
June 26, 2026Reimbursing AI Subscriptions Is Not a Tooling Strategy
Plenty of engineering orgs think they've solved AI tooling: expense anyone's individual subscription, done. It feels generous and fast. It's also a governance blind spot — you pay every bill and can introspect on none of it. Here's how to actually choose AI tooling for an org, and why the answer is a team or enterprise tier.
June 25, 2026The 90-Day Line: Why Some Teams Ship AI and Others Stall
High performers go from pilot to production in ~90 days. Everyone else takes nine months — with the same tools and models. The 3x gap is change management, not technology. Here's the fast path.
June 24, 2026Stop Writing an AI Policy. Start Running One.
Most leaders ask me how to write an AI policy. It's the wrong first question. The document is the easy part — and while you draft it, two-thirds of your team is already using AI they think you've banned. What you actually need is a standing committee and an operating cadence. Here's how to build both.
June 23, 2026Stop Picking a Model. Pick a Control Plane.
Two smart teams burned three hours debating Gemini vs. Claude — the wrong meeting. In 2026 the durable enterprise AI decision isn't the model, it's the control plane you standardize on.
June 22, 2026You Don't Have to Build AI. You Can Just Call It.
Most leaders picture AI as a project: hire data scientists, collect data, wait two quarters. But a huge share of useful AI isn't built — it's called. Google Cloud exposes a shelf of pretrained AI as plain APIs: speech-to-text and back, document intelligence, entity recognition, translation, image generation. Here are the quick wins you could ship this week.
June 20, 2026A Pragmatic Playbook for AI Adoption
Most AI projects stall not because the models are bad, but because the problem was never scoped for value. Here's a grounded framework for picking, shipping, and measuring AI work.
June 19, 2026You're Behind on AI. Here's How to Start.
A leader I'm working with came back from an industry event rattled — every peer was talking about their AI, and their company had nothing. The panic that produces leads to the worst first move. Here's how to start from zero deliberately: pick one workflow, measure it, and prove the win before you scale.
June 18, 2026Infrastructure as Code That Survives Contact With a Team
IaC promises reproducible infrastructure, then quietly rots into a pile of copy-pasted modules nobody trusts. Here's how to keep Terraform (or its cousins) maintainable as the team and the estate grow.
June 17, 2026Cloud Architecture Without the Over-Engineering
You probably don't need microservices, a service mesh, and multi-region active-active. Here's how to right-size architecture to the problem in front of you.
June 15, 2026FinOps Without a FinOps Team
You don't need a dedicated cost org to stop overpaying for cloud. A handful of habits — ownership, visibility, and a few right-sizing reflexes — recover most of the waste.
June 12, 2026How to Evaluate LLMs for Production
Benchmarks won't tell you if a model works for your task. Build a task-specific eval that reflects your real inputs, your real failure costs, and your real users.
June 10, 2026Serverless or Containers? A Decision, Not a Religion
The serverless-versus-containers debate generates more heat than light. Skip the tribalism — here's a concrete way to decide based on your workload, team, and constraints.
June 8, 2026Reach for Retrieval Before You Reach for Fine-Tuning
When an LLM doesn't know your domain, fine-tuning feels like the obvious fix. Usually it's the expensive one. Here's why retrieval should be your first move — and when fine-tuning actually earns its keep.
June 5, 2026Cloud on a Shoestring: A Bootstrapped Startup's GCP Playbook
For a bootstrapped startup, the cloud gives you data-center-grade infrastructure — and can quietly eat your runway faster than payroll. Here's how to stretch every dollar on Google Cloud: free credits, spot VMs, serverless that scales to zero, and spend alerts so a bill never ambushes you.
June 3, 2026Why I Build Startup Teams With Nearshore Talent in Argentina and Brazil
The highest-return decision I've watched founders make isn't a tool or a framework — it's where they hire. Nearshore engineers in Latin America, and Argentina and Brazil especially, have been extraordinary: brilliant, great communicators, and the kind of leverage that lets a small company move like a big one while protecting its runway.
June 1, 2026The Goldwater dispatch
No-hype cloud & AI, in your inbox.
New articles land Monday, Wednesday, and Friday. Get them delivered — no spam, unsubscribe anytime.