WEEK 8 · THE H3 EXAMPLE · THE ADVANCED LANE

Ship
It.

The deep version: one production build, taken apart. DC CAP's financial_modeling tool as a Stage 4 orchestration — three data streams, eleven agents, four verification layers. Read it to see where the ladder ends.

Preston Magouirk · DC CAP Enterprise AI Leadership Pilot · The advanced example.

The 60-day arc

Eight weeks. Four phases. One thing your team inherits.

Each phase built on the prior. Foundation → Delegation → Description → Discernment → Identify & Design → Diligence → Build Your Own → Ship It. The phases were strict containers; promotion happened when the work demanded it.

Phase 1 · W1–2

Foundation + Delegation

Onboarding. The 4D framework. Automation / Augmentation / Agency. The kickoff that named what each modality is for.

Phase 2 · W3–4

Description + Identify

Prompt patterns. The three-horizons frame. The build filter (five criteria). Three real builds you could steal.

Phase 3 · W5–6

Under the Hood + Diligence

How the model actually works. Where it gets confidently wrong. The verification stack — five danger zones, three gates, the source-loaded rewrite.

Phase 4 · W7–8

Build Your Own + Ship It

Designer to agent. The four-stage ladder. The eight build-questions. The Skill and Project you make available.

Where this deck sits

This is a Stage 4 build. Most of you will not build one.

Your assignment is a Skill and a Project — the team-level containers. This deck walks the far end of the ladder so you can see what Stage 4 looks like and why almost no first build needs to go there. Read it for the pattern, at a larger scale than your own work.

01

What you're looking at

DC CAP's financial_modeling tool. One surface that combines three live data streams into a board-grade view of the org's finances through FY35.

02

Why it went to Stage 4

The work crossed several roles and needed an audit trail. That is the signal to orchestrate. Most work never crosses that line, and should not.

03

What you build instead

A Skill and a Project. The same five layers, at team scale. Stage 4 is here so you can see the whole ladder, not so you climb it.

The H3 worked example

DC CAP's financial modeling tool.
One surface. Three streams. Eleven agents.

A Stage 4 orchestration started life as a smaller container that outgrew its bounds. The financial_modeling tool is exactly that arc. DC CAP needed one surface that combined three live data streams into a single audit-trail-grade view of the organization's financial position now and projected through FY35.

The orchestration is a process the designer authored. The agents have no expertise. The designer has the expertise.

Step 1 · The Goal

Three live data streams. One reconciled model.

Three refresh cadences, three source systems, three sets of business rules. Combining them into one audit-trail-grade surface is what crossed every threshold on the four-stage ladder.

Stream 1 · Development

Raise targets & estimates

Goals and expected close estimates across individual, corporate, and philanthropic sources. Sourced from the AI Development Office pipeline and Eric's active funder conversations. Refreshes weekly.

Stream 2 · Finance

Costs & revenues, full arc

Historical actuals (FY12–FY26), current-year tracking, and forward projections. Sourced from the canonical Finance + Development merged Budget Preview workbook. Refreshes on each Finance cycle.

Stream 3 · Investment

Pathstone market projections

Best-estimate market trajectories from Pathstone, DC CAP's investment partner. Drives endowment performance modeling and the implied draw path. Refreshes quarterly.

Step 2 · The Roles

Eleven Opus agents. One job each.

Stage 4 means the work is too big for one role. The dispatch protocol splits it into eleven, each with one job and an explicit handoff to the next.

fpa-lead
Orchestrator. Dispatches lanes. Lead never does domain work; Lead routes.
fpa-architect
Methodology, ADRs, scope rule.
fpa-data-engineer
Parser intake. Per-cell provenance. L1/L2 gates.
fpa-quant
Math layer. Hyndman prediction intervals. L3 gates.
fpa-insight-hunter
Pareto. Damodaran bias diagnostic. Three numbers that matter.
fpa-analyst
Drift classification. Bridgespan PWIT. Cost-per-outcome.
fpa-strategist
Damodaran 3P test. Big Idea drafting. McKinsey ROIC matrix.
fpa-modeler
AFP driver-based budgeting. Rolling forecasts. Variance bridges.
fpa-viz
Tufte · Knaflic · Few applied to chart design.
fpa-storyteller
Knaflic Big Idea. Preston voice. Audience-first.
fpa-frontend
React + Recharts + TypeScript. WCAG 2.2 AA. Brand tokens.
Step 3 · The Skills

Each agent loads named skills at session start.

Skills live at three layers — plugin (shared across DC CAP), BRAIN-shared (the named expertise patterns), and references (project-local canonical sources). The dispatch protocol controls which layer loads on which agent.

Plugin layer

finance:* · data:*

Shared organizational plugin skills. finance:reconciliation + data:validate-data in fpa-data-engineer. data:statistical-analysis in fpa-quant. Each agent declares exactly what it loads.

BRAIN-shared skills

preston-writing · funder-framing · dccap-brand

DC CAP-wide skills loaded by name from inside the agents that need them. fpa-storyteller loads four (preston-writing, dc-cap-org-intelligence, executive-summary-formatter, funder-framing). dccap-brand loads in both fpa-frontend and fpa-viz — same SKILL.md, two lanes.

References

13 canonical sources

Damodaran, Tufte, Knaflic, Hyndman, McKinsey, Bridgespan, Few, NACUBO NCSE, AFP (Tier 1) plus BoardSource, CFA IPS, NFF, NACUBO Spending Policy (Tier 2). Each carries YAML frontmatter, verbatim quotes with inline attribution, methodology summary, routing notes.

Step 4 · The Verification Stack

Four layers. One audit trail.

The four verification layers run automatically. Nothing ships to a Board surface unless all four pass. Latest build: 53/53 checks green.

L1

Source-cell provenance

Every value tags to {sheet, cell, value, last_seen}. Untagged values are dropped.

L2

Parser hard-gate

Refuses to ingest if anchors, sheet names, or row labels have drifted from contract. Caught at intake.

L3

Runtime cross-foots

Computed totals cross-foot against the workbook's own totals inside fpa-quant. Mismatches halt the lane.

L4

Defaults alignment

Default assumptions reconcile against the IC-approved set before any surface renders. Lead consolidates the L4 result.

Step 5 · End to End

FY27 revenue-walk request — a worked dispatch.

A request lands at fpa-lead. Lead dispatches lanes in parallel where dependencies allow, sequentially where they do not. Each lane writes to its own state file. Lead consolidates. The Output Verification protocol runs before anything ships.

request fpa-lead fpa-data-engineer fpa-quant fpa-insight-hunter fpa-storyteller fpa-frontend · publish

fpa-data-engineer reconciles the three streams at intake (Development + Finance + Pathstone). Once L1 + L2 pass, fpa-quant runs the math with L3 cross-foots — the endowment draw recomputes from Pathstone bands, the operating gap recomputes from finance + development. In parallel, fpa-insight-hunter runs the Pareto. fpa-storyteller writes the Big Idea. fpa-frontend publishes after L4. Lead writes the consolidated audit trail.

The H3 takeaway

The agents have no expertise.
The designer has the expertise.

The orchestration is not "more AI." It is a process the designer authored. The failure mode lives in the spec the designer wrote. Most of us will stop at Stage 2 or Stage 3. That is the right call. Knowing when to stop is the discipline this pilot trains.

The measurement model

KPI cadence. Three tiers. Three decision gates.

The pilot measurement model carries forward. Three tiers track Engagement, Proficiency, and Impact. Three gates decide what scales, what pauses, what pivots. The cadence is what we use to measure how the cohort's builds hold up across the next twelve months.

Tier 1

Engagement

Office-hours attendance. Hub-page visits. Briefing reads. Surface metrics that tell us the cohort kept showing up.

Tier 2

Proficiency

Build artifacts shipped. The eight-question answers on file. Post-pilot assessment delta against your Week 1 baseline.

Tier 3

Impact

The build's effect on the work. Hours saved on the recurring task. Voice consistency across the team. The pattern that became how the unit operates.

Scale / Pause / Pivot gates decide what becomes a DC CAP-wide pattern. The KPI Framework page on the hub carries the gate definitions.

What carries forward

H1 personal. H2 team. H3 enterprise.

The three-horizons frame from Week 2 closes the loop. Each ship-it artifact lives at one horizon. Some will scale up; most stay where they are. That is the right answer.

H1 · Personal gain

Faster, better drafts on your own plate

Counselor quick-drafts. The Monday-morning prep. The prompt template that runs every week. Artifact A lives here. Most Stage 1 work stays here on purpose.

H2 · Team gain

Patterns your team inherits

The Skill the team loads. The Project the unit operates. Artifact B and Artifact C live here. Most pilot builds land at H2 — that is what the four-stage ladder makes accessible.

H3 · Enterprise gain

Moves that become how DC CAP operates

The financial_modeling orchestration. The AI Development Office pipeline. The Compensation Benchmarking flow. Artifact D points at this horizon. Rare; takes a year to mature.

The post-pilot check

Retake the assessment. Measure your own growth.

Same five-construct instrument from Week 1. Your pre-launch baseline is saved. The post-pilot delta is yours to see — and ours to read across the cohort. Twenty minutes, open whenever you're ready.

Five constructs covered: understanding (what AI is and is not), delegation (when and how to hand work to Claude), description (the prompt patterns), discernment (the data-tier judgment), diligence (the verification discipline). Same scale at both ends — your numbers move because the same instrument captures what changed.

The assessment is for you first. The cohort summary informs how we scale, what we extend, where the next pilot lands.

After the pilot

The build is the cohort's. The work is yours.

The pilot closes. The work continues. Three things to do the week after.

01
Run the build.

Open the artifact you shipped. Run it on the real task. Read the diligence block first. Edit. Send. That single rep is what makes the build stick.

02
Hand it to one teammate.

Pick one teammate who would use the same build. Walk them through it in five minutes. Watch where they stumble. That is the spec gap to fix next.

03
Schedule the next refresh.

Put the iteration cadence on your calendar. The build that survives twelve months is the build whose refresh date already lives in someone's schedule.