// salesforce & ai tooling

Tools that streamline and accelerate work.

A personal AI platform with its own software factory, a native Salesforce data dictionary, and a release pipeline that deploys only what changed.

03 projects 03 vscode extensions 01 native salesforce app

Projects

01 LIVE

Fulltrace

A personal AI platform

Fulltrace puts AI to work in three ways. A software factory builds its roadmap day and night, task runs check and fix projects, and a chat in the editor answers quick questions. The coding assistants share one memory, plain code checks the work, and every step leaves a record.

MCP Claude Codex Cursor OpenRouter VSCode API Memory
details → view demo →

On a phone, turn it sideways to watch.

02 BETA

Salesforce Data Dictionary

Up-to-date documentation for your Salesforce org

Reads your org's setup from your Git repository and turns it into searchable documentation, relationship diagrams and dependency maps inside Salesforce. It rebuilds on demand or on a schedule, so the documentation keeps up with the code.

Apex LWC SOQL Named Credentials Queueable Apex
details → view demo →

On a phone, turn it sideways to watch.

03 DEV

CI/CD Pipeline Blueprint

Safer, faster Salesforce releases

A release pipeline for Salesforce with templates for five CI platforms, plus two VSCode extensions for setup and daily work. Each release deploys only what changed, runs the Apex tests, and rolls back to a backup if anything fails.

TypeScript VSCode API sfdx-git-delta Node.js Bash

How the Projects Fit Together

The three projects are parts of one system. Fulltrace is the AI platform. It gives Claude, Codex and Cursor one shared memory. It builds itself from its own roadmap, and its task runs audit Studio (its VSCode extension) and the CI/CD tooling, calling other models through OpenRouter. Each piece of work the factory finishes writes what it learned back into the shared memory.

Both Salesforce tools work from one Git repository that holds an org's metadata. The CI/CD pipeline and its editor tooling deploy that metadata to Salesforce. The Data Dictionary reads the same repository and turns it into documentation. Confluence pages reach the repository through the editor tooling.

Purple is the AI side: Claude, Codex and Cursor, plus OpenRouter, which reaches many other models.

Amber is Fulltrace: the shared memory, and the factory and task runs that do the work. Each finished piece of work adds to the memory, so the next session starts from there.

Green is the other work: this site and the two Salesforce tools.

flowchart TD
    CL["Claude"] --> AOSC
    CX["Codex"] --> AOSC
    CR["Cursor"] --> AOSC
    OR["OpenRouter"] --> AOSR
    subgraph AOS["Fulltrace"]
      AOSC["Shared memory
notes and commands
every assistant reads"] AOSR["Factory and task runs
build, check and fix"] end AOSC --> AOSR AOSR -->|"updates memory"| AOSC AOSR --> WEB["This website"] AOSR --> CI["CI/CD Pipeline
+ VSCode tooling"] CI -->|"deploys"| SRC[("Git repo +
Salesforce metadata")] SRC -->|"documentation"| DD["Salesforce Data Dictionary"] CONF["Confluence"] --> CI %% Blueprint tokens as literal hex (Mermaid cannot parse CSS vars or color-mix) classDef model fill:#8b93e81f,stroke:#8b93e8,stroke-width:1.5px; classDef entry fill:#e0be621f,stroke:#e0be62,stroke-width:1.5px; classDef code fill:#62d99a1f,stroke:#62d99a,stroke-width:1.5px; classDef docs fill:#8a8f9b14,stroke:#8a8f9b,stroke-width:1.2px,stroke-dasharray:4 3; class CL,CX,CR,OR model; class AOSC,AOSR entry; class WEB,DD,CI code; class CONF docs; %% Fulltrace grouping box: dashed amber outline, no fill, matching the amber nodes it holds style AOS fill:transparent,stroke:#e0be62,stroke-width:1.5px,stroke-dasharray:5 4;