# 100x (blogs) — RSS Amplifier Recent posts from the 3 feeds in the RSS Amplifier directory that cover 100x. Page: Feed: --- ## [The Afternoon I Was the Whole Team](http://www.brandoncasci.com/2026/07/29/the-afternoon-i-was-the-whole-team.html) _2026-07-29 · Brandon Casci · Brandon Casci_ 2026-07-29 The Afternoon I Was the Whole Team You’ve heard this, and so have I. AI is collapsing roles, one person now doing what used to take a product manager, a designer, and a few engineers. I’ve read the posts. I even wrote a couple. The job titles are already bending to it. This year, LinkedIn replaced its associate product manager program with an associate product builder track,… ## [A Learning Loop That Makes My Agent Wiser Over Time](http://www.brandoncasci.com/2026/07/10/how-i-keep-my-coding-agent-from-relearning-the-same-lessons.html) _2026-07-10 · Brandon Casci · Brandon Casci_ 2026-07-10 A Learning Loop That Makes My Agent Wiser Over Time My coding agent kept solving the same problems twice. One session it would work out that a native confirm() dialog can’t be visually QA’d, so a test that leans on one proves nothing. Two days later, fresh context, it would write that exact test again. The same thing happened with the phone number that has to match when… ## [I Run a Company by Writing It Down](http://www.brandoncasci.com/2026/06/18/i-run-a-company-by-writing-it-down.html) _2026-06-19 · Brandon Casci · Brandon Casci_ 2026-06-18 I Run a Company by Writing It Down Yes, AI can write code. But running a product is not all about writing code. In a week, a food pantry running my software might ask for a person’s age next to their birthdate so the front desk stops doing the math, a warning before they enter someone twice, and a couple of small bug fixes. Each one has to be understood, decided on, built, checked… ## [Webinar: The Model That Gets Smarter Every Time It Runs](https://oumiai.substack.com/p/webinar-the-model-that-gets-smarter) _2026-06-17 · Stefan Webb · Oumi Blog_ A healthtech company built a custom AI that compounds value with every production run. The frontier model it replaced never learned a thing about their business. ## [Two UI Migrations and 56 Million Tokens Later, Claude Fable Still Needed My Eyes](http://www.brandoncasci.com/2026/06/12/two-ui-migrations-and-56-million-tokens-later-claude-fable-still-needed-my-eyes.html) _2026-06-12 · Brandon Casci · Brandon Casci_ 2026-06-12 Two UI Migrations and 56 Million Tokens Later, Claude Fable Still Needed My Eyes This week I aimed Claude at migrating the UI frameworks of two production apps. Every screen moved to a new framework, and nothing about how either app behaves changed. The migrations ran side by side and finished over two days. Two days is calendar time, not a stopwatch. I started with brainstorming… ## [Stop Correcting Your AI. Grade It, Tune It, and Compound the ROI.](http://www.brandoncasci.com/2026/06/02/stop-correcting-your-ai-grade-it-tune-it-and-compound-the-roi.html) _2026-06-02 · Brandon Casci · Brandon Casci_ 2026-06-02 Stop Correcting Your AI. Grade It, Tune It, and Compound the ROI. I arrived here by giving the AI more autonomy. The more it runs on its own, the faster a slightly-off instruction turns into wasted work. Your code-review-improve loops run longer than they should. You burn time curating skills, subagent prompts, rules files, and CLAUDE.md content, tweaking by gut feel and hoping the next… ## [Newsletter: Stop throwing money away on frontier AI (and other news)](https://oumiai.substack.com/p/stop-throwing-money-away-on-frontier) _2026-05-19 · Stefan Webb · Oumi Blog_ Updates for Week of May 18, 2026 ## [How much money are you throwing away on Anthropic and OpenAI models?](https://oumiai.substack.com/p/how-much-money-are-you-throwing-away) _2026-05-19 · Stefan Webb · Oumi Blog_ Specialized AI can be 10x-100x fold or more cheaper than a general-purpose frontier model with the same or better performance. Learn how much you could save by moving from Anthropic to specialized AI ## [Oumi OSS v0.8: Deploy, MCP, and Batch Inference Everywhere](https://oumiai.substack.com/p/oumi-oss-v08-deploy-mcp-and-batch) _2026-05-15 · Stefan Webb · Oumi Blog_ We’re excited to announce Oumi OSS (Open Source Stack) v0.8, a release focused on closing the loop from training to production. ## [Case Study: Kaizen Gaming builds a specialized text-to-SQL model for sports analytics that beats Kimi-K2](https://oumiai.substack.com/p/kaizen-gaming-builds-a-specialized) _2026-05-15 · Stefan Webb · Oumi Blog_ With Oumi, Kaizen fine-tuned a 3B model that matched or exceeded frontier-scale alternatives — at a fraction of the cost — by treating rule compliance as a fine-tuning problem, not a prompting problem ## [One OS for your AI workforce (Sponsored)](https://crawlproof.com/a/5EUCtF7dqudb) _2026-05-15 · **Sponsored**_ Build, direct, and supervise an AI workforce from a single operating workspace. ## [Case Study: Wired Informatics trains a word-sense disambiguation model on open weights that keeps sensitive data safe](https://oumiai.substack.com/p/case-study-wired-informatics-trains) _2026-05-15 · Stefan Webb · Oumi Blog_ With Oumi, a healthcare AI team moved from 84.5% to 88.9% concept-validity precision on messy clinical text — without sending a single patient record to a third-party API ## [Case Study: Original Voices builds a voice-authentic AI on proprietary persona data with 31% higher authenticity](https://oumiai.substack.com/p/case-study-original-voices-builds) _2026-05-15 · Stefan Webb · Oumi Blog_ With Oumi’s technology, Original Voices’s personal-twin product moved from 52% to 83% authenticity pass rate — driven entirely by better evaluation, not more data. ## [Newsletter: Oumi can now host your Custom AI Models with a single click (and other news)](https://oumiai.substack.com/p/oumi-can-now-host-your-custom-ai) _2026-05-11 · Stefan Webb · Oumi Blog_ Specialized Intelligence: Updates for Week of May 11, 2026 ## [Your Hiring Process Is a Mirror](http://www.brandoncasci.com/2026/05/07/your-hiring-process-is-a-mirror.html) _2026-05-07 · Brandon Casci · Brandon Casci_ 2026-05-07 Your Hiring Process Is a Mirror I was approached for a senior Rails role through a staffing agency. The evaluation was three stages: a take-home coding test, a live coding test, and a shop talk. I’ve been building software for 30 years. I declined and told the recruiter exactly why. Two Negative Signals I understand agencies need margin, and I was willing to flex on comp to… ## [Case Study: Aurasell builds an 8B model for extracting information from websites outperforming Sonnet 4.5 by 8%](https://oumiai.substack.com/p/case-study-aurasell-outperforms-sonnet) _2026-05-01 · Stefan Webb · Oumi Blog_ With Oumi’s technology, Aurasell's custom AI beat Anthropic's Sonnet 4.5 at extracting information from webpages by 8% in coverage and 12% in groundedness ## [Case Study: DMG achieves 6% higher quality and 100x lower costs for invoice validation](https://oumiai.substack.com/p/case-study-dmg-achieves-6-higher) _2026-04-24 · Stefan Webb · Oumi Blog_ With Oumi’s technology, DMG’s custom AI beat GPT5.2 by 6% accuracy and 6% validity at 100x lower cost ## [The Gravity Between You and the 100X Dark Factory](http://www.brandoncasci.com/2026/04/07/the-gravity-between-you-and-the-100x-dark-factory.html) _2026-04-07 · Brandon Casci · Brandon Casci_ 2026-04-07 The Gravity Between You and the 100X Dark Factory I heard Nathan B Jones talking about the concept of a living resume and how he thought the current hiring model was toast. The idea stuck with me. I expanded it into a product called Profyle : a professional profile platform with three layers of depth. A scannable surface view, expandable stories behind each role, and an AI conversation… ## [How I Came to Understand the 100x Claim](http://www.brandoncasci.com/2026/02/24/how-i-came-to-understand-the-100x-claim.html) _2026-02-24 · Brandon Casci · Brandon Casci_ 2026-02-24 How I Came to Understand the 100x Claim First people bragged about 3-5x productivity gains from AI, then 10x, and now 100x. Usually without much clarity beyond references to parallelism and orchestration. I’d read these claims and think, OK, but what does that actually look like? What are you doing differently that gets you there? I was skeptical for a while. Then I lived through… ## [Composable Rules: How Small Teams Match Big Company Output Without the Bloat](http://www.brandoncasci.com/2025/12/24/composable-rules-getting-claude-code-to-honor-your-conventions.html) _2025-12-25 · Brandon Casci · Brandon Casci_ 2025-12-24 Composable Rules: How Small Teams Match Big Company Output Without the Bloat Small teams and solo developers compete with funded companies every day. Traditionally, small teams defended niches by being nimble. Now they can simulate the parts of bigger institutions that work without the overhead. Big companies have resources: Multiple developers QA teams DevOps Established processes They… ## [Building a Production App with AI: The Boswell Story](http://www.brandoncasci.com/2025/10/23/building-a-production-app-with-ai-the-boswell-story.html) _2025-10-24 · Brandon Casci · Brandon Casci_ 2025-10-23 Building a Production App with AI: The Boswell Story You see a lot of “AI-First” success stories floating around. Weekend builds that turn into six-figure SaaS products. Solo developers shipping faster than funded teams. Instant revenue from AI-generated apps. This isn’t that story. This is a breakdown of what AI-first product development actually looked like for me,… ## [Try Before You Buy, Risk-Free (Sponsored)](https://crawlproof.com/a/glMDrtOwsMZ7) _2025-10-24 · **Sponsored**_ Free trial hosting plus refunds processed in 12-24 hours, guaranteed. ## [My AI Organization Ships Like We're Funded, But It's Just Me (Part 1)](http://www.brandoncasci.com/2025/09/25/my-ai-organization-ships-like-we-re-funded-but-it-s-just-me.html) _2025-09-25 · Brandon Casci · Brandon Casci_ 2025-09-25 My AI Organization Ships Like We’re Funded, But It’s Just Me (Part 1) Part 1: The Knowledge Infrastructure I ship at the velocity of a funded startup, but it’s just me. The difference is giving AI assistants the same domain knowledge a human team member would have. I’m not working harder or using productivity hacks. I’m helping AI move from a coding intern… ## [How I Went From Dev Team to Engineering VP with Claude Code](http://www.brandoncasci.com/2025/09/23/how-i-went-from-dev-team-to-engineering-vp-with-claude-code.html) _2025-09-23 · Brandon Casci · Brandon Casci_ 2025-09-23 How I Went From Dev Team to Engineering VP with Claude Code I had a bug that only appeared during parallel processing. It was intermittent, timing-dependent, and the kind that makes you question your life choices. My issue-diagnosis agent found worthwhile improvements that would stave off issues like this, but couldn’t nail the root cause. After a few attempts I took a crack at… ## [How One Person Becomes a Dev Team with Claude Code](http://www.brandoncasci.com/2025/09/21/how-to-transform-yourself-into-a-dev-team-using-claude-codes-ai-agents.html) _2025-09-21 · Brandon Casci · Brandon Casci_ 2025-09-21 How One Person Becomes a Dev Team with Claude Code I wanted to augment my productivity. GitHub Copilot worked for single lines. Then Claude Code and Cursor promised a “pair programmer”, but out of the box they delivered an eager helper with a paintbrush in one hand and a sledgehammer in the other. I got Jackson Pollock and Gallagher rolled into one. I tried add-on… ## [How We Automated GitHub Issues with Free AI](http://www.brandoncasci.com/2025/08/24/we-gave-our-github-issues-an-ai-assistant.html) _2025-08-24 · Brandon Casci · Brandon Casci_ 2025-08-24 How We Automated GitHub Issues with Free AI Building on the foundation: This artist is an extention to teaching Claude Code to be consistent and turning prompts into reusable commands . If you’re new to CLAUDE.md files, start there. We’re a small team that runs everything through GitHub Issues. I’d already invested in Claude Code Pro and documented our patterns with… ## [Turn Your Best AI Prompts into Reusable Commands](http://www.brandoncasci.com/2025/08/04/turn-your-best-ai-prompts-into-reusable-commands.html) _2025-08-04 · Brandon Casci · Brandon Casci_ 2025-08-04 Turn Your Best AI Prompts into Reusable Commands You’ve documented your patterns with CLAUDE.md files . Claude checks them automatically. Your code is consistent now. But you’re still typing the same TDD instructions every time you implement something. What if that perfect prompt could be a simple command? What if we could express our intentions for work this way? /implement… ## [From Chaos to Control: How I Taught Claude Code to be Consistent and Accurate](http://www.brandoncasci.com/2025/07/30/from-chaos-to-control-teaching-claude-code-consistency.html) _2025-07-30 · Brandon Casci · Brandon Casci_ 2025-07-30 From Chaos to Control: How I Taught Claude Code to be Consistent and Accurate I started using Claude Code for Rails development with the same excitement everyone has when they first discover AI coding assistants. The promise was incredible: describe what you want, get working code instantly. Then reality hit. Suboptimal code. Inconsistent patterns. Going off on tangents when I asked for… ## [Vibe Coding Needs a Reality Check: Why AI-Generated Code Still Requires Engineering Discipline](http://www.brandoncasci.com/2025/02/14/vibe-coding.html) _2025-02-14 · Brandon Casci · Brandon Casci_ 2025-02-14 Vibe Coding Needs a Reality Check: Why AI-Generated Code Still Requires Engineering Discipline The term “vibe coding” has been making the rounds, painting a picture of a laid-back, intuitive way to write software with AI. The idea? You describe what you want, accept the AI-generated code, and move on. No stress, no deep dives, just code that vibes. Except… the way… ## [UI Unblocker: A CustomGPT for Breaking Through UI Design Roadblocks](http://www.brandoncasci.com/2025/02/13/ui-unblocker-a-customgpt.html) _2025-02-14 · Brandon Casci · Brandon Casci_ 2025-02-13 UI Unblocker: A CustomGPT for Breaking Through UI Design Roadblocks Sometimes, a UI just doesn’t feel right. You tweak layouts, adjust spacing, change colors, but something is still off. That’s when I started using AI as a UX auditor—not to replace design tools, but to help me break through creative blocks. I put together UI Unblocker , a CustomGPT designed for one-off UI… ## [🤖 Refactoring GraphQL with AI Coding Assistants: A Real-World Use Case](http://www.brandoncasci.com/2025/02/09/lessons-refactor-and-optimization.html) _2025-02-09 · Brandon Casci · Brandon Casci_ 2025-02-09 Refactoring GraphQL with AI Coding Assistants: A Real-World Use Case AI coding assistants are everywhere, but much of the content focuses on simplistic, contrived demos. “Hey AI, make me a to-do list app!” Of course, greenfield projects work like magic. The real test is applying AI to large, messy, real-world codebases that have evolved over time. That’s what I did… ## [Getting AI Coding Assistants From OK To Great](http://www.brandoncasci.com/2025/01/09/taking-ai-coding-assistants-from-ok-to-great.html) _2025-01-10 · Brandon Casci · Brandon Casci_ 2025-01-09 Getting AI Coding Assistants From OK To Great I’ve been experimenting with AI coding tools to see if I could improve their effectiveness. My focus has been on training Cursor AI for a specific project I’m working on at RiseKit. Here’s what I done so far: ✅ Rules and Templates I created a rules file with project-specific coding standards, architecture patterns, testing… ## [Home Internet From Space (Sponsored)](https://crawlproof.com/a/F0EvvPa1dsJS) _2025-01-10 · **Sponsored**_ Residential satellite internet that brings connectivity to homes beyond conventional networks ## [Bottoms-up engine vs. top-down taxonomy](https://sauce23.substack.com/p/bottoms-up-engine-vs-top-down-taxonomy) _2024-12-04 · Sauce AI · Sauce AI_ At Sauce, we're on a mission to 100x every product team's impact.