Case study
Zappi's implementation redesign
What I inherited

A delivery motion built around heroics and tribal knowledge. Each implementation ran differently depending on who owned it. Time-to-value was slow, quality was inconsistent, and AI tooling was being bolted onto a process that had never been clearly designed. The technology wasn't the problem — the foundation was.

What changed

I rebuilt the implementation methodology from the customer outcome back. Defined what each phase was responsible for delivering. Shifted from "customer builds, team reviews" to "team recommends, customer validates." Removed steps that only existed because a better approach hadn't been available. Established ownership at every handoff.

Where AI came in

Only after the process was clear. AI was applied to specific synthesis inflection points — pre-kickoff briefing, account update generation, audience analysis, handover documentation. Each tool targets a real friction point in a defined phase. None of them are compensating for unclear process design.

15 days Time to first value — down from 30. The gain came from design discipline, not automation alone.
~30% Reduction in time to live across implementations, with stable satisfaction and increased team capacity.
The framework
Three principles, in order
01
Start with customer outcomes

What is each step in the process actually responsible for delivering — and does the customer know that too?

02
Lead with expertise

Shift from "customer builds, team reviews" to "team recommends, customer validates." The team should be the expert in the room, not a facilitator.

03
Let automation follow clarity

Remove unnecessary steps first. Then apply AI at the points where synthesis is genuinely the bottleneck — not to mask process problems.

Where the line belongs
Stays human
Relationship building and trust Complex training and enablement Account and customer management Opportunity identification Strategic brainstorming Final decision making Contextual judgment — reading the room, the relationship, the moment
Built for AI
Research and synthesis Pattern recognition Assumption validation Idea stress-testing Iterative problem solving Repetitive and readable tasks Documentation and summarization Information synthesis across sources
The line isn't always a handoff. Sometimes AI runs alongside the human work without replacing it.
AI in practice
What's running, what's being built
Active — What's running
Synthesis
Pre-kickoff Intelligence Brief

AI ingests account notes and call recordings to produce a structured customer brief before every kickoff. Replaces manual document hunting.

Documentation
Account Update Generator

Takes call summaries and produces formatted stakeholder updates after every implementation touchpoint.

Pattern Recognition
Audience Auditor

Accepts multiple audience files, identifies overlap and redundancy, produces a consolidation recommendation.

Summarization
Handover Documentation

AI drafts the end-of-implementation record for clean handoff — platform config, decisions made, training status, research pipeline.

Generation
Custom Spreadsheet Builder

Produces customer-specific structured spreadsheets built around their platform setup and program design.

In Progress — Being built
Synthesis + Project Intelligence
Per-Customer AI Agents

Custom agents that connect call recordings, manage project trackers, and surface to-dos — giving each implementation its own persistent AI layer that knows the account.

Analysis
Training Gap Assessor

Identifies coverage gaps across training sessions and surfaces what still needs to be addressed before handoff.

Generation
Kickoff Deck Personalization

Customer-specific deck generation from a templated base.

What I'm building
Updated as work ships
Apr 2026 Built merlinkomenda.com via Claude Code. Full site architecture, deployment pipeline, serverless functions, and ongoing infrastructure — no agency, no developer. Claude Code as the build partner throughout.
Apr 2026 Deployed interactive leadership reporting suite. Live dashboards connected directly to data sources — giving senior leadership self-serve access to annual, quarterly, and monthly performance data. Replaced static reporting with an always-available analysis layer.
Mar 2026 Built autonomous multi-agent system. A network of AI agents that communicate and operate independently without human triggering. Always running. Built to explore the boundaries of agent autonomy and inter-agent coordination.
Ongoing Per-customer AI agents in development. Building account-specific agents that synthesize call recordings, manage project trackers, and surface next steps — giving each implementation its own persistent AI layer.
What I'm still working out

Most AI adoption asks: how do we support this process with AI? That's the wrong place to stop. The better question: which of our current practices only exist because a better approach was too expensive to build? AI doesn't just make existing processes faster. Sometimes it makes them avoidable. I'm working out which defaults that invalidates — and I want to think through it with people doing this work.

I think out loud on LinkedIn — follow the thinking there.

← Back to home