$ cat ccai.md | head
OPERATOR_AVAILABLE

I build the AI that lets contact center agents focus on the customer.

// 15 years running contact center operations, including Director of Operations over 400+ agents. The last year spent as the business owner for AI in a live customer operation: virtual agents, agent assist, real-time NLU and sentiment scoring, and human-in-the-loop handoff. I speak both the operational metrics and the AI that moves them.

[ EMAIL_WILL ] [ DOWNLOAD_RESUME.PDF ]
> ./status --credibility
  • 15 YRS
    [ CONTACT CENTER OPERATIONS ]
  • 400+
    [ AGENTS LED AS DIRECTOR OF OPERATIONS ]
  • -194s
    [ AHT CUT / COMPANY ALL-TIME RECORD ]
  • +8 PTS
    [ FIRST-CALL RESOLUTION LIFT / COMPANY RECORD ]
> ./build --map=ccai

// WHAT I'VE BUILT, MAPPED TO CCAI

// The open-stack systems I run at Mac Septic map directly onto Google CCAI's product surface.

Conversational Voice Agent

maps to: CCAI virtual agent (Dialogflow CX)

  • Sub-2-second end-to-end latency with a custom voice clone.
  • Handles appointment confirmation, status checks, and after-hours intake.
  • Graceful human-in-the-loop handoff to a live agent when escalation is needed.
Pipecat Deepgram nova-3 Claude ElevenLabs

Real-Time Interaction Analyzer

maps to: CCAI Agent Assist + Conversational Insights

  • Live NLU, sentiment, and intent scoring of every call, SMS, email, and chat.
  • Structured disposition written automatically.
  • Under $0.005 per scored interaction with prompt caching, 90 days production uptime.
Deepgram Claude Haiku NLU Sentiment Bounded JSON

Agent-Focused Dialer Mode

maps to: Agent Assist real-time guidance

  • Transcribes the call in real time, writes the notes and the disposition, and surfaces the next step (dispatch needed? new customer?).
  • The agent clicks go and does nothing but listen to the customer and solve the problem.
  • Better for the customer, better for the agent.
Real-time STT Auto-disposition Next-best-action
> ./history --years=15

// 15 YEARS IN THE CONTACT CENTER

> ./narrative

I rose from frontline DSL technician to Director of Operations at OneSupport, a multi-LOB BPO running outsourced ISP technical support for 14 multi-state clients, including the Google WiFi program. I spent two years on the phones myself early in my career, before ever managing anyone, so I know exactly what good agent tooling does for both sides of the call.

[ TELEPHONY ]

Five9, Avaya, Mitel, Dialpad, Nextiva, RingCentral. The CCaaS and telephony layer a contact center AI program plugs into.

Reduced staffing 295 to 137 agents (-54%)
Cut AHT by 194 seconds (fastest in the company's 25-year history)
Raised FCR by 8 points to 78.3% (highest in the company's 25-year history)
Lifted adherence from 90.3% to 95.7%
$2M+ in annual staffing savings
$1.7M / year saved for one client via truck-roll reduction
Onboarded 137 agents in 3 months during COVID surge
Telephony and CCaaS managed: Five9, Avaya, Mitel, Dialpad, Nextiva, RingCentral
> ./why --this-role

// WHY THIS ROLE

> ./statement

For a decade as a director I carried a goal I could never quite reach: to build the tools my own operation needed instead of waiting on someone else to build them. Learning to code well enough never fit alongside the day job.

AI finally closed that gap. Over the past year I built the things I had spent ten years describing in meetings.

Doing that work at GFiber's scale, with a real platform and a team behind it, for a company I once oversaw support for as a director, is exactly the work I want next.

> ./contact --open

Let's build the contact center experience your agents and customers deserve.

// Available for the CCAI Operations Specialist role.

[ EMAIL_WILL ]