Collin Velarde
I spent 20 years reading the job from the field. Now I build source-backed AI systems that can read the job with me.
Source pass
drawings + code + field notesReview gate
public-safe summary onlyAgent surface
typed registry + site-indexRelease posture
operator approval requiredFeatured work
Three public-safe proof cards for the first version. The deeper details stay gated until screenshots, claims, and client boundaries are approved.
construction intelligence
A construction intelligence system that turns drawings, rooms, code, and field knowledge into source-backed operating context.
Field judgment can be encoded into retrieval, review, and structured workflows without pretending the model is the authority.
retrieval and ETL
A pipeline for transforming drawing sets into structured rooms, systems, tags, retrieval records, and reviewable job context.
The hard part is not parsing a PDF; it is preserving enough field context to know what should be held, verified, or released.
private AI systems
Sanitized CRM, evidence, and operator workflow systems for real business processes.
AI systems are useful when they reduce decision drag without leaking client data or bypassing human approval.
Field notes
The first version links out instead of mirroring essays locally. Substack is pending, so these cards are approved summaries until canonical URLs are locked.
A field note on using AI to run real operating loops instead of treating software as a demo trick.
Canonical link pending
Notes on why useful AI for operators starts with sources, caveats, and reviewable outputs.
Canonical link pending
A public teaching lane for turning drawing-family doctrine into apprentice-facing field guidance.
Canonical link pending
How I work
The work pattern is simple: identify the real operating pressure, preserve source truth, encode the review gate, and keep the release decision human-readable.
Start with how the work is actually run: drawings, rooms, releases, holds, and the early catch points that save the job.
Keep sources, caveats, and review state visible so an answer can be checked before it becomes action.
Structure the work so humans and agents can inspect the same proof, metadata, and release gates.
Release posture
The site is built around approval status, render policy, privacy labels, and machine-readable indexes so future agents can update it without accidentally promoting private proof.
Start with a workflow audit, private AI system, construction intelligence pilot, or technical collaboration.