← BACK TO FIELD OFFICE DOWNLOAD PDF
Buni LLC
Amy Sullivan · AI Enablement Specialist
[email protected] · linkedin.com/in/amy-sullivan-320865141
luvbuniz.github.io/enterprise-portfolio1 · Florida · remote

I help teams stop experimenting with AI and start using it.

Working AI systems for business teams — not developers. Built with guardrails, human approval gates, and documentation your team owns. Every claim below is documented in full on the portfolio site, including a production pipeline with live public stats.

Receipts on File

What I Build

Bespoke AI Workflows

Agent pipelines for high-volume, quality-sensitive work: model routing by task value, hard guardrail gates, review queues — nothing irreversible without a human click.

Team Enablement & Training

Role-specific training and playbooks for non-technical teams — executives, marketing, operations — so adoption survives after I leave.

Model Evaluation & Stack Decisions

Discriminator-task benchmarking on your actual workload: which model, for which tasks, at what cost — evaluations that end in spending decisions.

Quick-start engagement: a deck & content production system — consistent, brand-locked presentations and documents on a prompt + rubric system your team keeps.

Receipts, Not Claims

  • Two-lane agent pipeline in production since May 2026 — human-approved submissions, hard guardrail gates, live public stats on the site
  • Weekly production time cut from 8 hours to 2 (75% reduction)
  • 78 weeks of curriculum across three programs — each 26-week program built in under 4 hours with AI workflows
  • 40+ presentation decks at consistent design standards via systematic prompt engineering
  • Stackadoo — shipped 3D educational math game with parent dashboard (stackadoo.com)
  • Claude, ChatGPT, Gemini & Grok used daily in production, 3+ years
  • AI data-quality evaluation for multiple enterprise AI training platforms (structured rubrics, 7-point scales)

How an Engagement Works

  1. Workflow audit (30 min).
    Bring one messy workflow. Leave with a one-page findings memo — no pitch.
  2. Build, gated.
    The system runs with hard quality gates and a human approval queue from day one. Value is instrumented, not asserted.
  3. Handoff.
    Templates, documentation, and training — your team owns and maintains it without me.

Workflows can run on the Claude subscription your team already pays for — no API keys, no per-token billing — or as a multi-model API build when volume demands it.