I build practical AI-assisted workflow tools that help small and mid-sized businesses improve operations visibility, sales execution, recruiting workflows, CRM discipline, process documentation, training consistency, client workflow diagnostics, and manager decision-making.
My background combines operations leadership, revenue management, field-sales execution, KPI reporting, recruiting, onboarding, CRM workflows, process improvement, and AI-assisted workflow automation.
This GitHub profile highlights my growing portfolio of lightweight AI operations tools built with Python, Streamlit, GitHub, and practical business logic.
A portfolio of AI-assisted workflow tools for small and mid-sized businesses.
Portfolio Hub:
Launch Practical AI Ops Toolkit
OpsPilot AI converts field-sales activity data into KPI reporting, rep performance insights, lead source analysis, operations diagnosis, executive scorecards, coaching recommendations, weekly sales meeting agendas, and downloadable manager reports.
Problem Solved: Managers often have activity data but lack a clear action plan.
Built With: Python, Streamlit, Pandas, CSV workflow, Markdown report export
Links:
Live Demo
GitHub Repo
FollowUpPilot AI helps sales teams generate next-best actions, customer follow-up texts, emails, voicemail scripts, CRM-ready notes, call scripts, objection-handling guidance, manager coaching notes, follow-up timelines, and downloadable follow-up plans.
Problem Solved: Sales opportunities are often lost because follow-up is slow, inconsistent, or poorly documented.
Built With: Python, Streamlit, rules-based workflow logic, Markdown report export
Links:
Live Demo
GitHub Repo
RecruitPilot AI helps hiring managers organize job descriptions and resume text into human-review packets, match signals, missing-information checks, follow-up questions, manager summaries, candidate emails, and candidate tracker CSV exports.
Problem Solved: Small businesses often review applicants from scattered resumes, job descriptions, and inconsistent notes.
Built With: Python, Streamlit, rules-based workflow logic, keyword extraction, Markdown and CSV export
Links:
Live Demo
GitHub Repo
SOPPilot AI helps managers turn rough process notes into standard operating procedures, process checklists, missing-information checks, readiness scores, version-control blocks, risk diagnoses, training plans, quality control guides, implementation plans, and downloadable SOP packages.
Problem Solved: Small businesses often rely on tribal knowledge, verbal instructions, scattered notes, and inconsistent training instead of repeatable process documentation.
Built With: Python, Streamlit, rules-based workflow logic, Markdown report export
Links:
Live Demo
GitHub Repo
ClientOps Intake AI is the planned front-door diagnostic app for the toolkit. It will help small-business operators identify workflow bottlenecks, score operational maturity, recommend automation opportunities, route users to the right tool in the portfolio, and generate a 30-day improvement roadmap.
Problem Solved: Small businesses often know operations feel messy, but do not know which workflow to fix first.
Planned Stack: Python, Streamlit, rules-based diagnostic logic, Markdown report export
- KPI reporting
- Sales operations
- Revenue operations
- CRM workflow improvement
- Manager reporting
- Process improvement
- Recruiting and onboarding
- Performance management
- SOP and training documentation
- Client workflow diagnostics
- Rules-based AI-style logic
- Workflow automation
- Decision-support tools
- Prompt-style output design
- Manager-ready report generation
- Business process mapping
- Practical AI implementation
- Process documentation automation
- Diagnostic intake workflows
- Python
- Streamlit
- Pandas
- GitHub
- Streamlit Community Cloud
- Markdown reporting
- CSV-based workflows
I am building a practical AI operations portfolio focused on tools that help businesses:
- Improve visibility into performance
- Standardize sales follow-up
- Strengthen CRM discipline
- Improve hiring consistency
- Document repeatable processes
- Improve training and quality control
- Diagnose workflow bottlenecks
- Reduce repetitive admin work
- Turn scattered data and notes into action-ready outputs
- Support better manager decision-making
The focus is simple:
AI tools that solve real operational problems.
All sample data, names, companies, and scenarios used in these projects are fictional and created for public portfolio demonstration purposes.