Skip to content
View shmindmaster's full-sized avatar

Highlights

  • Pro

Block or report shmindmaster

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
shmindmaster/README.md

Sarosh Hussain

I lead engineering teams that take AI products from a customer's problem to production, and I stay close to the code while they do.

  • CTO and Partner at Pendoah, leading a 20-person software and AI engineering group split across onshore and offshore teams
  • Fractional CTO for multiple venture-stage startups, each past $1M ARR, including serving as Head of Product Engineering and Forward Deployed Engineering at one of them
  • Formerly CIO of Perry Homes (45-person organization, revenue from $800M to $1.71B) and a practice leader at Hitachi Consulting, Accenture, PwC and Credera

Houston, TX.


What I build

Fieldbook is a web application I designed and built to run a forward-deployed engineering and solutions-architecture organization as a system of record. Each engagement is tied to the production outcome it promised, the evidence that proves it, its cost and what it left behind. It has stage exit gates, a milestone ladder that will not advance without linked evidence, capacity and staffing, field requests with duplicate detection and a named merge-back owner, reusable assets and plays, handoffs, and rule-based weekly status drafting and evidence auditing. Vite, React 19, Tailwind, shadcn/ui, Hono on Node, Postgres and Drizzle. MVP; demo on request.

Open source

  • CrewScore: offline linter that finds missing written safeguards in AI-agent system prompts (23 controls, no API key).
  • GitPin: local evidence MCP that ties agent-authored claims to exact committed source before merge.

Portfolio | LinkedIn

Popular repositories Loading

  1. crewscore crewscore Public

    Find the safety rules your AI agent prompt forgot. Offline linter — 23 controls, CLI + Action + browser. No API key.

    Python 1

  2. gitpin gitpin Public

    Require exact PR evidence before agent-authored changes merge. Local evidence MCP + base-trusted gate.

    TypeScript

  3. awesome-mcp-servers awesome-mcp-servers Public

    Forked from punkpeye/awesome-mcp-servers

    A collection of MCP servers.

  4. agenthub agenthub Public

    Portable control plane for skills, plugins, MCP servers, and policy across coding agents — with drift detection and a local personal overlay.

    PowerShell

  5. assay assay Public

    The agent drafts. Software decides. A runnable reference implementation of the deterministic control layer for AI agents: typed decisions, externalized policy, a fail-closed effect broker, hash-cha…

    JavaScript

  6. shmindmaster shmindmaster Public

    Profile README