<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Posts on Newton Rocha</title><link>https://rochanewton.github.io/posts/</link><description>Recent content in Posts on Newton Rocha</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Newton Rocha</copyright><lastBuildDate>Thu, 24 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://rochanewton.github.io/posts/index.xml" rel="self" type="application/rss+xml"/><item><title>Becoming a Claude Architect: 100-Question Practice Quiz — Part 7</title><link>https://rochanewton.github.io/posts/claude-architect-07-practice-quiz/</link><pubDate>Thu, 24 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/claude-architect-07-practice-quiz/</guid><description>&lt;h2 class="relative group"&gt;What this is
 &lt;div id="what-this-is" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-this-is" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;This wraps up the &lt;strong&gt;Becoming a Claude Architect&lt;/strong&gt; series with a self-check: 100 practice questions, 20 per domain, covering everything from &lt;a href="https://rochanewton.github.io/posts/claude-architect-02-agentic-architecture-orchestration/" &gt;Domain 1 — Agentic Architecture &amp;amp; Orchestration&lt;/a&gt; through &lt;a href="https://rochanewton.github.io/posts/claude-architect-06-context-management-reliability/" &gt;Domain 5 — Context Management &amp;amp; Reliability&lt;/a&gt;. Click an answer and you&amp;rsquo;ll see immediately whether it&amp;rsquo;s right, with a short explanation either way.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/claude-architect-07-practice-quiz/cover.png"/></item><item><title>Becoming a Claude Architect: Agentic Architecture &amp; Orchestration — Domain 1</title><link>https://rochanewton.github.io/posts/claude-architect-02-agentic-architecture-orchestration/</link><pubDate>Thu, 24 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/claude-architect-02-agentic-architecture-orchestration/</guid><description>&lt;h2 class="relative group"&gt;What this is about
 &lt;div id="what-this-is-about" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-this-is-about" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;Domain 1 — &lt;strong&gt;Agentic Architecture &amp;amp; Orchestration&lt;/strong&gt; — is the single heaviest domain on the Claude Certified Architect – Foundations exam, worth 27% on its own. The exam guide breaks it into seven task areas: the agentic loop, multi-agent orchestration, subagent configuration, multi-step workflows, SDK hooks, task decomposition, and session management. That&amp;rsquo;s a lot of ground, so this post condenses it into the five ideas that actually carry the weight, with the smaller two folded into a quick round-up at the end.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/claude-architect-02-agentic-architecture-orchestration/cover.png"/></item><item><title>Becoming a Claude Architect: Claude Code Configuration &amp; Workflows — Domain 3</title><link>https://rochanewton.github.io/posts/claude-architect-04-claude-code-configuration-workflows/</link><pubDate>Thu, 24 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/claude-architect-04-claude-code-configuration-workflows/</guid><description>&lt;h2 class="relative group"&gt;What this is about
 &lt;div id="what-this-is-about" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-this-is-about" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;Domain 3 — &lt;strong&gt;Claude Code Configuration &amp;amp; Workflows&lt;/strong&gt; — ties Prompt Engineering &amp;amp; Structured Output for second-heaviest domain on the Claude Certified Architect – Foundations exam, at 20%. Its six task areas are all about how you set up and drive Claude Code itself: configuration file hierarchy, custom commands and skills, conditional rules, choosing plan mode vs. diving straight in, iterating well, and wiring Claude Code into CI/CD.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/claude-architect-04-claude-code-configuration-workflows/cover.png"/></item><item><title>Becoming a Claude Architect: Context Management &amp; Reliability — Domain 5</title><link>https://rochanewton.github.io/posts/claude-architect-06-context-management-reliability/</link><pubDate>Thu, 24 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/claude-architect-06-context-management-reliability/</guid><description>&lt;h2 class="relative group"&gt;What this is about
 &lt;div id="what-this-is-about" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-this-is-about" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;Domain 5 — &lt;strong&gt;Context Management &amp;amp; Reliability&lt;/strong&gt; — is the lightest domain on the Claude Certified Architect – Foundations exam at 15%, but its six task areas cover what decides whether a long-running agent stays trustworthy: preserving critical facts across long interactions, knowing when to escalate, letting a multi-agent system recover from failure instead of silently degrading, managing context at scale, and calibrating how much to trust the output.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/claude-architect-06-context-management-reliability/cover.png"/></item><item><title>Becoming a Claude Architect: Overview — Claude Certified Architect – Foundations</title><link>https://rochanewton.github.io/posts/claude-architect-01-overview/</link><pubDate>Thu, 24 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/claude-architect-01-overview/</guid><description>&lt;h2 class="relative group"&gt;What this is about
 &lt;div id="what-this-is-about" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-this-is-about" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;&lt;strong&gt;Claude Certified Architect – Foundations&lt;/strong&gt; is Anthropic&amp;rsquo;s certification for designing Claude systems, not just using them. Where the Claude Certified Associate exam tests whether you can operate Claude with professional discipline — good prompts, sound judgment on output, the right entry point for the job — the Architect exam tests something a level up: can you design the agentic system, the tool integrations, and the configuration that other people build on top of. The ideal candidate has 6+ months of hands-on experience building with the Claude API, the Claude Agent SDK, Claude Code, and Model Context Protocol (MCP) — this isn&amp;rsquo;t a first certification, it&amp;rsquo;s the next one.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/claude-architect-01-overview/cover.png"/></item><item><title>Becoming a Claude Architect: Prompt Engineering &amp; Structured Output — Domain 4</title><link>https://rochanewton.github.io/posts/claude-architect-05-prompt-engineering-structured-output/</link><pubDate>Thu, 24 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/claude-architect-05-prompt-engineering-structured-output/</guid><description>&lt;h2 class="relative group"&gt;What this is about
 &lt;div id="what-this-is-about" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-this-is-about" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;Domain 4 — &lt;strong&gt;Prompt Engineering &amp;amp; Structured Output&lt;/strong&gt; — ties Claude Code Configuration &amp;amp; Workflows for second-heaviest domain on the Claude Certified Architect – Foundations exam, at 20%. Its six task areas move from how you write a prompt to how you guarantee what comes back is actually usable: explicit criteria, few-shot examples, schema-enforced output, validation loops, multi-instance review, and batch processing for scale.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/claude-architect-05-prompt-engineering-structured-output/cover.png"/></item><item><title>Becoming a Claude Architect: Tool Design &amp; MCP Integration — Domain 2</title><link>https://rochanewton.github.io/posts/claude-architect-03-tool-design-mcp-integration/</link><pubDate>Thu, 24 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/claude-architect-03-tool-design-mcp-integration/</guid><description>&lt;h2 class="relative group"&gt;What this is about
 &lt;div id="what-this-is-about" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-this-is-about" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;Domain 2 — &lt;strong&gt;Tool Design &amp;amp; MCP Integration&lt;/strong&gt; — is 18% of the Claude Certified Architect – Foundations exam, across five task areas: designing tool interfaces, structuring error responses, distributing tools across agents, integrating MCP servers, and choosing built-in tools well. It&amp;rsquo;s a lighter domain than Agentic Architecture, but arguably the most immediately practical one — every point here shows up the first time you give an agent a tool that doesn&amp;rsquo;t work the way you expected.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/claude-architect-03-tool-design-mcp-integration/cover.png"/></item><item><title>Claude Certified Associate – Foundations: Domain 7 — Troubleshooting and Optimization</title><link>https://rochanewton.github.io/posts/claude-cert-09-troubleshooting-and-optimization/</link><pubDate>Sat, 19 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/claude-cert-09-troubleshooting-and-optimization/</guid><description>&lt;h2 class="relative group"&gt;What this is about
 &lt;div id="what-this-is-about" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-this-is-about" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;Domain 7 of the &lt;a href="https://anthropic-partners.skilljar.com/claude-certified-associate-foundations-certification" target="_blank" rel="noreferrer"&gt;Claude Certified Associate – Foundations&lt;/a&gt; exam is &lt;strong&gt;Troubleshooting and Optimization&lt;/strong&gt;. It&amp;rsquo;s worth 10% — the lightest domain on the exam. But it&amp;rsquo;s the one that closes the loop on the other six: everything from prompting to configuration to model selection eventually produces an output that underperforms, and this domain is the discipline of tracing that failure to its root cause, fixing it, and making sure the fix persists instead of getting re-discovered next week.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/claude-cert-09-troubleshooting-and-optimization/cover.png"/></item><item><title>Claude Certified Associate – Foundations: Domain 6 — Configuration and Knowledge Management</title><link>https://rochanewton.github.io/posts/claude-cert-08-configuration-and-knowledge-management/</link><pubDate>Fri, 18 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/claude-cert-08-configuration-and-knowledge-management/</guid><description>&lt;h2 class="relative group"&gt;What this is about
 &lt;div id="what-this-is-about" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-this-is-about" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;Domain 6 of the &lt;a href="https://anthropic-partners.skilljar.com/claude-certified-associate-foundations-certification" target="_blank" rel="noreferrer"&gt;Claude Certified Associate – Foundations&lt;/a&gt; exam is &lt;strong&gt;Configuration and Knowledge Management&lt;/strong&gt;. It&amp;rsquo;s worth 12%. The line it draws: using Claude means typing a good prompt today. Operating Claude means building an environment where the right context, instructions, and procedures already exist, so every conversation starts from a configured baseline instead of a blank slate. Configuration is leverage — set it up once, benefit on every conversation that follows — and it&amp;rsquo;s also what turns individual skill into team capability, since two people asking the same question against the same configured Project get the same quality of answer.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/claude-cert-08-configuration-and-knowledge-management/cover.png"/></item><item><title>Claude Certified Associate – Foundations: Domain 5 — Product and Model Selection</title><link>https://rochanewton.github.io/posts/claude-cert-07-product-and-model-selection/</link><pubDate>Thu, 17 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/claude-cert-07-product-and-model-selection/</guid><description>&lt;h2 class="relative group"&gt;What this is about
 &lt;div id="what-this-is-about" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-this-is-about" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;Domain 5 of the &lt;a href="https://anthropic-partners.skilljar.com/claude-certified-associate-foundations-certification" target="_blank" rel="noreferrer"&gt;Claude Certified Associate – Foundations&lt;/a&gt; exam is &lt;strong&gt;Product and Model Selection&lt;/strong&gt;. It&amp;rsquo;s worth 12%. The framing: before prompting even starts, four decisions already set the quality ceiling for the session — the right entry point, the right capability layer, the right model tier, the right context strategy. Get those four wrong and no amount of prompt polish fixes it. Get them right and the prompt has to do a lot less work.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/claude-cert-07-product-and-model-selection/cover.png"/></item><item><title>Claude Certified Associate – Foundations: Domain 4 — Prompting and Task Execution</title><link>https://rochanewton.github.io/posts/claude-cert-06-prompting-and-task-execution/</link><pubDate>Wed, 16 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/claude-cert-06-prompting-and-task-execution/</guid><description>&lt;h2 class="relative group"&gt;What this is about
 &lt;div id="what-this-is-about" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-this-is-about" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;Domain 4 of the &lt;a href="https://anthropic-partners.skilljar.com/claude-certified-associate-foundations-certification" target="_blank" rel="noreferrer"&gt;Claude Certified Associate – Foundations&lt;/a&gt; exam is &lt;strong&gt;Prompting and Task Execution&lt;/strong&gt;. It&amp;rsquo;s worth 14%. The framing that matters here: ask Claude to &amp;ldquo;write something about our Q3 results&amp;rdquo; and you get a generic paragraph. Specify the audience, the three results that matter, the format, and the length, and you get a draft you can almost send. The model didn&amp;rsquo;t get smarter between those two requests. The prompt did. This domain treats prompting as a communication discipline with learnable structure, not a knack some people have.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/claude-cert-06-prompting-and-task-execution/cover.png"/></item><item><title>Claude Certified Associate – Foundations: Domain 3 — Governance, Risk, and Responsible Use</title><link>https://rochanewton.github.io/posts/claude-cert-05-governance-risk-and-responsible-use/</link><pubDate>Tue, 15 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/claude-cert-05-governance-risk-and-responsible-use/</guid><description>&lt;h2 class="relative group"&gt;What this is about
 &lt;div id="what-this-is-about" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-this-is-about" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;Domain 3 of the &lt;a href="https://anthropic-partners.skilljar.com/claude-certified-associate-foundations-certification" target="_blank" rel="noreferrer"&gt;Claude Certified Associate – Foundations&lt;/a&gt; exam is &lt;strong&gt;Governance, Risk, and Responsible Use&lt;/strong&gt;. It&amp;rsquo;s worth 15%. The framing is blunt: sensitive data uploaded to the wrong place, an untrusted Skill granted broad access, a quiet policy violation at the wrong moment — any one of these can freeze an entire organization&amp;rsquo;s AI program and cost every team the productivity it had gained. Governance isn&amp;rsquo;t a policy binder on a shelf. It&amp;rsquo;s exercised by practitioners, one decision at a time — which makes it a skill you build, not a document you read once.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/claude-cert-05-governance-risk-and-responsible-use/cover.png"/></item><item><title>Claude Certified Associate – Foundations: Domain 2 — Workflow Integration and Solution Design</title><link>https://rochanewton.github.io/posts/claude-cert-04-workflow-integration-and-solution-design/</link><pubDate>Mon, 14 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/claude-cert-04-workflow-integration-and-solution-design/</guid><description>&lt;h2 class="relative group"&gt;What this is about
 &lt;div id="what-this-is-about" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-this-is-about" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;Domain 2 of the &lt;a href="https://anthropic-partners.skilljar.com/claude-certified-associate-foundations-certification" target="_blank" rel="noreferrer"&gt;Claude Certified Associate – Foundations&lt;/a&gt; exam is &lt;strong&gt;Workflow Integration and Solution Design&lt;/strong&gt;. It&amp;rsquo;s worth 16% — second only to Output Evaluation, which &lt;a href="https://rochanewton.github.io/posts/claude-cert-03-output-evaluation-and-validation/" &gt;Part 3&lt;/a&gt; already covered. Where that domain asked &amp;ldquo;is this one output good?&amp;rdquo;, this one asks a different question entirely: &lt;strong&gt;where does Claude actually belong in a workflow made of multiple steps, systems, and people — and where doesn&amp;rsquo;t it?&lt;/strong&gt; Getting an individual answer right doesn&amp;rsquo;t matter much if you&amp;rsquo;ve wired it into the wrong place in the process.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/claude-cert-04-workflow-integration-and-solution-design/cover.png"/></item><item><title>Claude Certified Associate – Foundations: Domain 1 — Output Evaluation and Validation</title><link>https://rochanewton.github.io/posts/claude-cert-03-output-evaluation-and-validation/</link><pubDate>Sun, 13 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/claude-cert-03-output-evaluation-and-validation/</guid><description>&lt;h2 class="relative group"&gt;What this is about
 &lt;div id="what-this-is-about" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-this-is-about" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;Domain 1 of the &lt;a href="https://anthropic-partners.skilljar.com/claude-certified-associate-foundations-certification" target="_blank" rel="noreferrer"&gt;Claude Certified Associate – Foundations&lt;/a&gt; exam is &lt;strong&gt;Output Evaluation and Validation&lt;/strong&gt;. It&amp;rsquo;s worth 21% — more than any other domain on the exam. The whole domain comes down to one idea: &lt;strong&gt;good-looking output is not the same thing as validated output.&lt;/strong&gt; Fluent, confident text doesn&amp;rsquo;t tell you anything about whether it&amp;rsquo;s actually correct. This post breaks down the framework for closing that gap, on purpose, instead of by accident.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/claude-cert-03-output-evaluation-and-validation/cover.png"/></item><item><title>You're Using Claude Like It's ChatGPT 2020</title><link>https://rochanewton.github.io/posts/claude-cert-02-using-claude-chat-projects-artifacts-and-research/</link><pubDate>Sat, 12 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/claude-cert-02-using-claude-chat-projects-artifacts-and-research/</guid><description>&lt;h2 class="relative group"&gt;The chat window is where most people stop
 &lt;div id="the-chat-window-is-where-most-people-stop" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#the-chat-window-is-where-most-people-stop" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;Open Claude, type a question, get an answer, close the tab. Next week, same question-shaped task, same blank chat window, same explaining from zero: who you are, what you&amp;rsquo;re working on, what &amp;ldquo;good&amp;rdquo; looks like for this kind of output. If that&amp;rsquo;s the whole relationship, you&amp;rsquo;re using one of the most capable tools available today exactly like you&amp;rsquo;d use a search box — or, more to the point, exactly like people used ChatGPT in 2020, when a fresh context window every time was just how these things worked.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/claude-cert-02-using-claude-chat-projects-artifacts-and-research/cover.png"/></item><item><title>The 4D Framework: Delegation, Description, Discernment, Diligence</title><link>https://rochanewton.github.io/posts/claude-cert-01-fluency-4d-framework/</link><pubDate>Fri, 11 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/claude-cert-01-fluency-4d-framework/</guid><description>&lt;h2 class="relative group"&gt;What this is about
 &lt;div id="what-this-is-about" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-this-is-about" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;Anthropic&amp;rsquo;s AI Fluency course breaks working with AI into four competencies instead of a pile of prompt tricks: &lt;strong&gt;Delegation, Description, Discernment, Diligence&lt;/strong&gt;. The 4Ds. I went in expecting a prompting course and came out with a decision framework instead — one that&amp;rsquo;s less about writing better prompts and more about deciding what to hand off, how to communicate it, how to judge what comes back, and who&amp;rsquo;s accountable for it. Here&amp;rsquo;s each one, condensed to what actually matters.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/claude-cert-01-fluency-4d-framework/cover.png"/></item><item><title>SSH known_hosts: How Host Key Verification Actually Works (and What to Do When It Breaks)</title><link>https://rochanewton.github.io/posts/sterling-b2bi-08-ssh-known-hosts-host-key-verification/</link><pubDate>Thu, 10 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/sterling-b2bi-08-ssh-known-hosts-host-key-verification/</guid><description>&lt;h2 class="relative group"&gt;The warning nobody should click past
 &lt;div id="the-warning-nobody-should-click-past" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#the-warning-nobody-should-click-past" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;Every SSH and SFTP client has the same scary moment: you connect to a server you&amp;rsquo;ve connected to a hundred times before, and instead of a normal prompt you get something like this from OpenSSH:&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/sterling-b2bi-08-ssh-known-hosts-host-key-verification/cover.png"/></item><item><title>SFTP, FTP, FTPS: Protocol Behind the Adapters</title><link>https://rochanewton.github.io/posts/sterling-b2bi-07-sftp-protocol-fundamentals/</link><pubDate>Wed, 09 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/sterling-b2bi-07-sftp-protocol-fundamentals/</guid><description>&lt;h2 class="relative group"&gt;Three protocols, one job, very different guts
 &lt;div id="three-protocols-one-job-very-different-guts" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#three-protocols-one-job-very-different-guts" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;FTP, FTPS, and SFTP all claim to do the same thing — move a file from one place to another — and partners use the names almost interchangeably, which is exactly the problem. They are three genuinely different protocols with different port models, different security properties, and different failure modes, and the &lt;a href="https://rochanewton.github.io/posts/sterling-b2bi-02-adapters-vs-services/" &gt;SFTP Server Adapter and SFTP Client Adapter&lt;/a&gt; you configure in Sterling only make sense once you know which one you&amp;rsquo;re actually running. This post goes through each one on its own terms, then spends the back half on SFTP specifically, since that&amp;rsquo;s what carries the overwhelming majority of partner traffic in B2Bi.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/sterling-b2bi-07-sftp-protocol-fundamentals/cover.png"/></item><item><title>Perimeter Servers in IBM Sterling B2B Integrator: Why the DMZ Box Calls Home Instead of the Other Way Around</title><link>https://rochanewton.github.io/posts/sterling-b2bi-06-perimeter-servers/</link><pubDate>Tue, 08 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/sterling-b2bi-06-perimeter-servers/</guid><description>&lt;h2 class="relative group"&gt;The connection runs backward from what you&amp;rsquo;d guess
 &lt;div id="the-connection-runs-backward-from-what-youd-guess" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#the-connection-runs-backward-from-what-youd-guess" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;Most people&amp;rsquo;s first assumption about a box sitting in the DMZ is that your trusted, internal network reaches out to it — the secure side initiates, the exposed side listens. A Perimeter Server does the opposite. The core B2Bi engine sitting safely inside your network never opens a connection out into the DMZ at all. Instead, the Perimeter Server — the box actually facing partners and the internet — dials &lt;em&gt;back in&lt;/em&gt; to the core engine and holds that connection open. Partner traffic lands on the DMZ box first, and only then gets forwarded inward over a channel the DMZ side itself established.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/sterling-b2bi-06-perimeter-servers/cover.png"/></item><item><title>Mailboxes and File Gateway in IBM Sterling B2B Integrator: One Layer, Not Two Products</title><link>https://rochanewton.github.io/posts/sterling-b2bi-05-mailboxes-file-gateway/</link><pubDate>Mon, 07 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/sterling-b2bi-05-mailboxes-file-gateway/</guid><description>&lt;h2 class="relative group"&gt;The confusion I flagged back in Part 1
 &lt;div id="the-confusion-i-flagged-back-in-part-1" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#the-confusion-i-flagged-back-in-part-1" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;I called this out in &lt;a href="https://rochanewton.github.io/posts/sterling-b2bi-01-overview/" &gt;Part 1&lt;/a&gt; and promised to come back to it: &lt;strong&gt;File Gateway is not a separate product competing with B2Bi.&lt;/strong&gt; It&amp;rsquo;s a purpose-built UI and routing layer sitting directly on top of B2Bi&amp;rsquo;s mailbox and adapter machinery, built specifically so partner file exchange can be managed without anyone touching BPML directly. I still see people who&amp;rsquo;ve run Sterling for years talk about the two as if they&amp;rsquo;re alternatives you choose between. They&amp;rsquo;re not — one is the foundation, the other is a way of working with that foundation without writing a Business Process by hand.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/sterling-b2bi-05-mailboxes-file-gateway/cover.png"/></item><item><title>Business Processes and BPML in IBM Sterling B2B Integrator: Two Views of the Same Engine</title><link>https://rochanewton.github.io/posts/sterling-b2bi-03-business-processes-bpml/</link><pubDate>Sun, 06 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/sterling-b2bi-03-business-processes-bpml/</guid><description>&lt;h2 class="relative group"&gt;What is a Business Process
 &lt;div id="what-is-a-business-process" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-is-a-business-process" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;A &lt;strong&gt;Business Process&lt;/strong&gt; is the workflow that strings adapters and services together into something that actually does a job: receive a file, validate it, map it, encrypt it, hand it to an adapter for delivery, log every step along the way. It&amp;rsquo;s the thing &lt;a href="https://rochanewton.github.io/posts/sterling-b2bi-01-overview/" &gt;Part 1&lt;/a&gt; called &amp;ldquo;the closest thing the platform has to a heart&amp;rdquo; — because almost nothing meaningful happens in Sterling B2B Integrator outside of one running.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/sterling-b2bi-03-business-processes-bpml/cover.png"/></item><item><title>IBM Sterling B2B Integrator: Adapters vs. Services - The Distinction That Actually Matters</title><link>https://rochanewton.github.io/posts/sterling-b2bi-02-adapters-vs-services/</link><pubDate>Sat, 05 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/sterling-b2bi-02-adapters-vs-services/</guid><description>&lt;h2 class="relative group"&gt;What is an Adapter
 &lt;div id="what-is-an-adapter" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-is-an-adapter" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;An &lt;strong&gt;Adapter&lt;/strong&gt; is a service whose entire job is reaching outside Sterling B2B Integrator — connecting the Business Process Engine to &amp;ldquo;dissimilar systems and applications&amp;rdquo; that live outside the environment (&lt;a href="https://www.ibm.com/docs/en/b2b-integrator/6.2.0?topic=integrator-services-adapters" target="_blank" rel="noreferrer"&gt;IBM Documentation&lt;/a&gt;). An SFTP adapter opens a connection to a partner&amp;rsquo;s SFTP server. An AS2 adapter speaks the AS2 protocol to a trading partner&amp;rsquo;s gateway. Same underlying mechanism as any other service — the Business Process Engine calls it, it runs, it returns a result — but the work itself happens somewhere else, over a network, against a system you don&amp;rsquo;t control.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/sterling-b2bi-02-adapters-vs-services/cover.png"/></item><item><title>IBM Sterling B2B Integrator: A Quick Architecture Overview</title><link>https://rochanewton.github.io/posts/sterling-b2bi-01-overview/</link><pubDate>Fri, 04 Sep 2026 00:00:00 +0000</pubDate><guid>https://rochanewton.github.io/posts/sterling-b2bi-01-overview/</guid><description>&lt;p&gt;&lt;figure&gt;&lt;img
 class="my-0 rounded-md"
 loading="lazy"
 decoding="async"
 fetchpriority="auto"
 alt="Sterling B2B Integrator admin console home page"
 width="719"
 height="405"
 src="https://rochanewton.github.io/posts/sterling-b2bi-01-overview/admin-console-home.webp"
 srcset="https://rochanewton.github.io/posts/sterling-b2bi-01-overview/admin-console-home.webp 800w, https://rochanewton.github.io/posts/sterling-b2bi-01-overview/admin-console-home.webp 1280w"
 sizes="(min-width: 768px) 50vw, 65vw"
 data-zoom-src="https://rochanewton.github.io/posts/sterling-b2bi-01-overview/admin-console-home.webp"&gt;&lt;figcaption&gt;The admin console home page — where every session starts&lt;/figcaption&gt;&lt;/figure&gt;
&lt;/p&gt;

&lt;h2 class="relative group"&gt;What is IBM B2Bi
 &lt;div id="what-is-ibm-b2bi" class="anchor"&gt;&lt;/div&gt;
 
 &lt;span
 class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;
 &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-is-ibm-b2bi" aria-label="Anchor"&gt;#&lt;/a&gt;
 &lt;/span&gt;
 
&lt;/h2&gt;
&lt;p&gt;IBM Sterling B2B Integrator does one job: move files between your business and your trading partners — banks, suppliers, logistics providers, whoever needs EDI documents, flat files, or XML exchanged reliably and traceably — and know exactly what happened to every file at every step. That&amp;rsquo;s it. Everything else exists to support that one job.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://rochanewton.github.io/posts/sterling-b2bi-01-overview/cover.png"/></item></channel></rss>