I talked about the soft launch of Tight Code during Brandon Hancock’s developer call last night. Tight Code reviews your code every time you run git push. It works directly with Claude Code, so there’s no new editor or workflow to learn. Here’s what happens:​ 1. You push your code normally. 2. Tight Code scans the changes for secrets and redacts anything sensitive. 3. Multiple AI reviewers check security, code quality, performance, documentation, and release readiness. 4. One verdict and a clear list of findings appear in the dashboard. 5. Claude Code helps you work through each finding—but you approve every decision. It can run quietly in the background or stop a push when it finds something critical. If an AI provider is unavailable, it fails open so your work isn’t trapped. What makes it different:​ - It reviews at push time, not only when you open a pull request. - It uses Anthropic and OpenAI models for independent perspectives. - Secrets are removed before any AI model sees the code. - Your source code is never stored in the dashboard. - It remembers why you dismissed something as a false positive, so the same bad recommendation doesn’t keep returning. - It works with the Claude Code and Codex subscriptions you already have. So far, Tight Code has run 1,176 real reviews across 19 repositories, raised 2,157 findings, and caught 96 critical issues. About 92% of its findings were fixed, while only 8% were judged to be noise. The stack, for anyone interested:​ - A local Homebrew-installed Git hook and CLI - Claude Code with optional OpenAI Codex reviewers - A Next.js and TypeScript dashboard hosted on Vercel - Supabase for review history and reporting - Stripe for subscriptions - No source code or unredacted secrets stored in the cloud See the video, sign up, and install it:​ https://tightcode.dev Tight Code is normally $39/month. Brandon’s community can use code BRANDON20 to take $20 off each of the first three months, making it $19/month for those three months.

📝 SUMMARY This was a long, wide-ranging call that opened with OpenAI Dev Day excitement (GPT-6.1 Sol, the "Dots" ambient agent, GPT Space, a Decision API, and a $500/month Cerebras tier) and closed hours later with casual banter. In between, Brandon Hancock demoed his agentic software-development workflow and shared a startup update, while other members — Daniel Zivkovic, Shakur Abdullah, Andrew Nanton, Tom Welsh, and Patrick Chouinard — showed parallel workflows and tools (Fable, Herder, T3 Code, CMUX) and business updates, including Tom's Asset MS product sold to farmers and Ty Wells' rapidly scaling ERP business. A major throughline was the OpenAI-vs-Anthropic competitive debate, with Patrick predicting Anthropic's response to Dev Day and the group debating whether Anthropic's enterprise-first posture will cost it long-term. Scott Rippey demoed CC Blackbox and Tight Code plus his AI video pipeline, drawing go-to-market advice from Brandon. The back half shifted into hands-on coaching: Patrick's home-lab "Agent Operated Environment," Brandon's cold-outreach and data-pipeline tactics, and heavy group coaching for Juan Torres on his AI photo booth business — pricing, seasonal launches, and sales targeting. Paul Miller added SaaS-founder perspective on VC dynamics and rapid prototyping, and Brandon closed with candid reflections on financial strain and gratitude for the group. 💡 KEY INSIGHTS Model releases and strategy OpenAI Dev Day shipped GPT-6.1 Sol (same price as 5.6 Sol, ~4x cheaper than Astra/Fable-class), "Dots" (a proactive ambient agent across chat platforms and phone, paired with a cheap/fast Decision API), GPT Space (a ChatGPT-native Microsoft 365 competitor), and a $500/month ultra-fast Cerebras tier at ~3,000 tokens/sec. All major labs are compressing frontier intelligence into cheaper/faster models rather than shipping new capability jumps. Sonnet is positioned as the workhorse for tool/computer use and autonomous agents, while Opus/Fable remain the "brain."

Last week, one agent ran autonomously for 17 hours building a website — and another member launched a platform that replaces $50k of subscriptions, live on the call. If you missed it, your agent stack is officially out of date. 😄 📞 HOW THE CALLS WORK The calls can run 2+ hours. We want to make sure we're respecting everyone's time. Especially those of you who actually show up. Here's the structure: 👉 Reply to this post with your questions before the call 👉 If you submit a question and you're on the call, you go first 👉 We work through questions in the order they came in 👉 Then we open it up for everyone else If you can't make the call but want your question answered, drop it in the comments. We'll get to it. But priority goes to people who are there. The goal is simple: if you're taking the time to show up, you shouldn't have to wait behind questions from people who aren't even on the call. There's plenty still in motion: Rod is running comparative benchmarks on GLM 5.3 vs. Claude, Juan's gearing up for his image-to-image venue outreach, and Lisa promised a report back on her harness evaluation (T3, Hermes, OpenRouter). If you've got follow-ups of your own — or questions sparked by last week's personal infrastructure round-robin — drop them below and we'll dig in. 🔗 ZOOM LINK (save this) https://us06web.zoom.us/j/81995207847?pwd=Xe6u6LmIQOmCP5VTnOwWYjDBfZNKGB.1 📅 WHEN Tuesday September 22nd at 6PM ET Looking forward to seeing you on the call!

📝 SUMMARY This week's builder/founder coaching call, led by Brandon Hancock, packed in cost-optimization strategy, agentic architecture patterns, and hands-on go-to-market playbooks. Brandon shared updates on EMS SOAP (slow enterprise sales, active fundraising, aggressive LLM cost-cutting) and his new 30-day challenge project Listio, while Patrick Chouinard gave a deep tour of his personal "agentic OS" built on Proxmox, Hermes, and a markdown-based knowledge graph. The rest of the call was hands-on peer coaching: architecture advice for Hemal's e-commerce AI co-pilot, a full GTM and fundraising playbook for Juan's AI photo booth, cold-outreach troubleshooting for Shakur, and career-positioning strategy for Varun. 💡 KEY INSIGHTS • Treat falling model costs as a strategic weapon: when a model gets 10x cheaper, reinvest the savings into 10x more product value (integrity checks, live QA) rather than pocketing margin. Expect this reset cycle every 6–8 months. • Model swaps can deliver 100x savings: Brandon ran the same classification task on DeepSeek v4 Flash for $3 vs. $350 on a frontier model — same intelligence, fraction of the cost. • A true agent reasons and acts in a loop; a pipeline of sequential LLM calls that just streams an answer is not "agentic." The distinction matters for architecture decisions. • Adversarial test sets first: before building any conversational system, generate ~100 adversarial synthetic conversations (easy, confusing, prompt-injection) with expected outcomes. Hemal lost two weeks skipping this step. • Start with the simplest architecture (one agent, many tools), measure failure modes, and only add orchestrators/sub-agents when failure data justifies the complexity. • Loop engineering: run agents through repeated cycles of hypothesis → experiment → analyze → fix → retest, journaling every experiment to a markdown file so context survives compaction. Review early cycles yourself, then let it run autonomously overnight. • Use cheap Chinese models (GLM, DeepSeek, Qwen) for internal experimentation; reserve American models (GPT-5.5, Gemini) for production-facing or HIPAA-regulated work.

📝 SUMMARY This week's call featured a rotating show-and-tell covering personal agent harnesses, enterprise AI adaptation strategies, and mobile deployment tactics. Members demoed custom tools for tracking AI model usage across projects, automating subscription management, and running agentic workflows from mobile devices. Discussions ranged from rebuilding Codex functionality on banned networks to hiring philosophies for the AI-augmented era, with deep dives into cross-platform mobile stacks and biometric verification services. 💡 KEY INSIGHTS Scott Rippey demonstrated that hybrid-scanning local project folders alongside provider APIs can create a "Model Radar" to track which AI models are active versus deprecated across multiple client apps. He also showed how machine-to-machine sync via Bonjour keeps session databases consistent across multiple Macs. Ty Wells revealed an automation setup that switches between Claude and Codex subscriptions based on remaining usage percentage, preventing work loss from hitting quotas. His "intent capsules" concept—self-contained context bundles—allows cold agent sessions to execute plans without prior conversation history, enabling remote work continuation from anywhere including mobile devices. Patrick Chouinard explained how to recreate Codex review mechanics on GitHub Copilot CLI when OpenAI tools are banned at work, satisfying security requirements while maintaining access to frontier models. He emphasized that fully autonomous AI development is a misnomer because human intent is always required, and that goal-based automation only works with hard, testable facts rather than opinions. He also highlighted that just-in-time training via composable skills beats static courses, which become obsolete before completion. Daniel Zivkovic shared that requirements elicitation works better as an iterative "optometry" process (showing prototypes and asking "this or that") rather than upfront specification. He noted that running multiple AI-generated implementations in parallel causes conflicts, while sequential overnight runs create a morning review queue without collisions.