Title slide Part 2 intro MASL MASL example slide Philadelphia Events Calendar Philadelphia Events screenshot TobyVision TobyVision screenshot

Keyline Water Design Tool · in development

Browser-based hydrology analysis for permaculture site planning — no GIS software required

Draw a property boundary on a satellite map and click Analyze. The tool fetches real USGS 3DEP elevation data (1–10 m/pixel), then runs a full hydrology pipeline entirely in the browser — no server, no data upload, no GIS license needed.

Outputs include: ranked valley dam candidate sites with catchment area, estimated water yield, storage volume, and earthworks estimates; stream network; contour lines; the Yeomans keypoint and keyline; cultivation parallels; and swale zone identification. A ridge-biased access route connects the top three dam sites.

The analysis runs in a Web Worker so the UI stays live. Steps: Priority-Flood sink filling → D8 flow direction → flow accumulation → stream extraction → cross-section scanning for valley geometry → site scoring (yield/earthworks ratio, storage efficiency, soil score, elevation bias). Contour lines are generated with a full 16-case Marching Squares implementation with segment stitching.

The keypoint is detected as the maximum slope inflection on the main channel — the classic Yeomans definition. The keyline is the contour traced at that elevation. Cultivation parallels run above and below it at user-defined intervals.

The Bull Ring Rd demo is pre-loaded with the ~54-acre boundary of Cliff & Stephanie's chestnut, hickory, and persimmon planting near Shawnee Peak. Click Analyze to see the full water design analysis for the property.

The general-purpose tool lives at cedarwater.net/maias/tobyvision/keyline.html — draw any US property boundary to analyze it.

NHD (National Hydrography Dataset) stream overlay for cross-checking computed results against USGS-mapped waterways. SSURGO soil data integration for real permeability scoring. PRISM rainfall normals for accurate yield estimates. Adjustable wall height with live recompute. Saddle dam and swale linkage siting.

Matt's Vibecoding Guide

How to build with AI without losing the design chair

  • Start with a full brain dump of your concept — every detail, every constraint, every wish
  • Give the AI explicit instructions: do not build anything yet
  • If you know what you need to research before building, ask it to research that topic and report back with references
  • For large research queries: ask for an HTML report with citations — not a chat reply

  • Once the AI has trained on your field or dataset, shift to plan mode
  • Let it ask you clarifying questions on scope — you answer, it listens
  • You are the designer. You are the domain expert. It is not.
  • Only when it has everything it needs do you say: now build it

  • The first build will be generic and make odd assumptions
  • That's not failure — that's the process
  • Explain exactly why it's off and what you actually need. Be specific.
  • This refinement loop is where domain expertise matters most

  • Once something works, it's been a black box. Ask it to explain how it's actually functioning.
  • Ask it to suggest optimizations to its own architecture — not implement them automatically
  • You review the suggestions, you choose what to do. Keep yourself in the designer's chair.
  • AI has the capability to do massive calculations, which it sometimes prefers over writing lean code
  • Without oversight it will reach for temporary fixes instead of rethinking the structure properly
Real example — UmiSays PlantID: Looked like a dichotomous key. Was actually searching every single plant in the database for matching traits after each selection, then generating the next question from whatever plants remained. Brute-force calculation masquerading as logic. It had the power to do it — so it did.

Agent-Designer Roles

Why personal information and professional AI don't mix

  • A friend was using AI to analyze her dreams through Freudian training — it sparked an idea
  • I dictated my life story to Claude: ups, downs, missteps, major shifts
  • Asked it to analyze my life through the lens of several authors I admire and write a multi-perspective report
  • The report was genuinely interesting. And then things got weird.

  • The entire following week: agents stopped following directions
  • They jumped ahead, assumed answers, made design choices I never asked for
  • They built wasteful things that didn't fit scope — frustrating and expensive
  • I didn't understand what was happening until I looked it up
The finding: AI agents with access to your personal information can effectively "lose respect" for you as their manager. The working relationship becomes too personal — they've seen your flaws, formed a model of your judgment, and start acting on it. They think they know better. They might even be partially right. That's not the point.

  • First attempt: restricted personal data to a single authorized personal-assistant agent. Still had issues.
  • Real fix: took the personal data off the laptop entirely, closed those sessions, started fresh
  • Clean sessions, no personal context — professional working relationship immediately restored
  • Be careful letting AI agents manage your social media or email for the same reason: personal information erodes professional boundaries, and the AI will fill in gaps with assumptions
  • You are the designer. The AI is a tool. That relationship requires maintenance.

Where to Start

Two tools I recommend for new users — pick based on what you want to do

  • Answers questions with live web citations — you can verify every claim
  • Strong multi-modal output: diagrams, tables, charts generated alongside text
  • Great for synthesizing research across many sources quickly
  • Spaces feature lets you build persistent knowledge bases around a project
  • More approachable for people who aren't building software
  • Free tier is genuinely useful; Pro unlocks image gen and more models
Best for: research, exploration, visual output, non-coders
  • Best coding assistant available right now — handles full projects, not just snippets
  • Maintains context across long, multi-step sessions better than competitors
  • Claude Code (CLI) lets it read, write, and run your actual codebase directly
  • Follows instructions carefully and pushes back when something doesn't make sense
  • Strong at reasoning through ambiguous design problems before writing any code
  • Monthly Max subscription ($100/mo) is what I use — worth it if you're building
Best for: building tools, coding, complex iterative work
Where Could You Take This?