A bit on why I keep building here; for anyone wondering whether Superhuman Coda has a place in an AI-first world. Most of the AI conversation right now is dominated by a real and reasonable fear: hallucination and non-determinism. Can you trust a system that might invent a fact, or behave differently each time you run it, to actually run your business? That’s the right question to ask — and I don’t think the answer is to keep AI at arm’s length. It is to orchestrate AI so it reliably achieves a business goal: not a clever demo, but a process a manager can trust day after day. That problem has two halves, and Superhuman Coda happens to be unusually good at both: - Deterministic work belongs in formulas. CFL, buttons, and automations give you reliable, auditable, repeatable execution — the same result every time, with nothing invented — for everything that doesn’t need judgment. - Judgment belongs in inference. Native AI blocks let you place a focused model call exactly where reasoning is genuinely required — and nowhere else, so the unpredictable part stays small and reviewable. And the Superhuman Go AI engine is excellent at taking a specification of the business workflow we want to automate and generating the Tables, Formulas, and AI prompts to implement it! Most of my experiments, a set of docs I called AgentixGo (see here) are really just probes into one question: where is the optimal line between the formula and the inference? Coda lets me move that line freely without ever leaving the document. I don’t know another platform where deterministic logic and AI judgment sit this close together, in a tool a business manager can actually read. Notion has recently launched their “Custom Agents” feature that goes part of the way along this path. But it falls short, and let’s face it; the Notion formula language, and their database model, are way inferior to Coda, and not quite fit for purpose in serious process automations.

Due to a family illnes, I must postpone the Workshop today. I will record the material offline and post it to Skool by the end of the week. Apologies. Max

I have uploaded the latest video into the CLASSROOM and on YouTube 🦀OPEN CLAW INNER WORKINGS→NOCODE DEMO🤖 We will build a working replica of the innermost loop of OpenClaw to illustrate how it operates. This innermost loop will take a prompt and generate an executable set of TOOL requests to implement that. The TOOLs will modify data in the document by executing Action Formula Language (CFL) commands that can add/delete/edit rows in tables, change control-values, bring up dialogs for the user to see and change, modify information stored in the document's pages, etc. This replicates the way Claude Code, Claude Coworker, OpenClaw, OpenAI Codex, Cursor, work. (What I call the 🦞Lobster-like Agentic Tools). This will build the core functionality that we will use in subsequent workshops to build a complete replica of OpenClaw or Claude Cowork that runs (safely) inside the no-code environment (but can take real-world actions via API integrations). I will be using Coda.io for these demonstrations because it has the most complete set of features needed. But the principles will be equally applicable to Notion, Excel, Airtable, and other no-code platforms.

How SYSTEMS THINKING will 10X your AI Results. (This is the edited recording from the live workshop) Max

Two of my largest clients operate in "regulated industries" where EVERYTHING they do must be audited and controlled. One is under the FDA regulations for Clinical Trials, and the other is in Financial Services, with a great many external regulatory auditors circling like vultures looking for 'innovations' to swoop down upon. So you can imagine that all the hype and hoopla about implementing AI Agents meets with a certain amount of resistance and reluctance to implement this in their "controlled" Standard Operating Processes (SOPs). But when I teach their non-technical managers how to use my Coda AI Agents, they can see how this technique produces an auditable record of all the inputs, prompts, responses, and results for EVERY agentic step in the process. So I have been asked to provide my training sessions to a cohort of middle managers who are experts in their respective SOPs and have extensive spreadsheet experience in the finance sector. They are new to the world of no-code, but have had some experience with Notion and Coda. This will provide me with a significant opportunity to try out my teaching methods and materials. And I will then be able to migrate those learnings to my next round of workshops here in this Skool community. The key messages remain the same as always: Managers with expertise in SOPs and spreadsheets have most of the skills needed to deploy Agentic Workflows without the need for coding skills: 1. They can automate SOPs using no-code tools that exploit their spreadsheet skills. 2. They can provide carefully curated Knowledge Documents to the AI Agent (they wrote them!) 3. They can structure the necessary transactional data in Tables with Formulas 4. They need to learn how to build effective Prompts to add the AI steps to the process Please comment below with your own experiences, reactions, and questions about this approach. (I need the feedback) Max