HOOL · ACM Technology Group · Maren Close

ACM Technology Group — AI Readiness Dashboard

June 10, 2026 · 50 team members · T1 → T3 in one session

Static reference shell. If Maren live-render has any issue, this page is the clickable fallback.

SECTION 1

Capability Snapshot

Active workstreams

pulled from Jira at close

Tickets resolved (30d)

pulled from Jira at close

Team members trained today

static — count of room

Projected hours saved / week at T3

50 × 1.5 hrs × 5 days

SECTION 2

Live Project Health

Placeholder grid. Maren pulls live data from Jira at close — replace these rows with the live ticket summary.

Build — iSeries POS

GREEN

Q3 release prep

Build — Web Platform

AMBER

API refactor in flight

Maintain — Production Support

GREEN

MTTR 18m

Maintain — Data Pipelines

RED

2 blockers on nightly ETL

Data — Reporting & Analytics

AMBER

Q3 dashboard rebuild

UX — Customer Portal

GREEN

Re-design v2 in review

SECTION 3

What Changed Today

8:00 AM
ACM Technology Group: 50 team members, AI usage at T1 average.
12:00 PM – 2:30 PM
2.5-hour live training session — 10 tiles, 4 lanes, 50 personal adoption plans generated.
NOW
ACM Technology Group: T3-capable, one skill per person saved, 50 AI adoption plans active.

SECTION 4

90-Day Team Commitment Tracker

Weeks 1-4 (Habit Formation)

25% of arc

Behavioral commitments. 50 personal plans activated. Each: 1 Project, 1 skill, 1 real artifact.

Weeks 5-8 (Workflow Integration)

50% of arc

Recurring tasks being AI-assisted. First team-level rollouts. CLAUDE.md propagation.

Weeks 9-12 (Measurable Impact)

75% of arc

Outcomes reportable to leadership. Time saved, cycle time, stakeholder NPS. 1-page report per director.

SECTION 5

Delivery Intelligence

Two-column layout. Maren pulls Build Team Update + Maintain Team Update from Confluence at close. Below is the static reference shape.

Build team status

In flight

· 3 PRs in review > 24h
· 1 release branch cut for Q3
· 2 customer escalations closed this week
AI Acceleration: PR-description drafts from commit history (T3).

Maintain team status

In flight

· MTTR 18m (last 30d)
· 2 nightly-ETL blockers — owner: J. Patel
· 1 incident postmortem pending review
AI Acceleration: First-pass postmortem drafts from incident timeline (T3).

SECTION 6

The Strategic Signal

The same organization that just spent 2.5 hours learning to put Claude on real work is also the organization running the iSeries POS Q3 release, the Web Platform API refactor, the nightly data pipelines, and the customer-portal redesign. The strategic signal is not “we trained 50 people” — it is that the next quarter of delivery is now a different shape. The Q3 release branch, the API refactor, the data-pipeline blockers, and the portal redesign will all be touched by a team that has a Project, a skill, and a saved prompt. The cost of the training is real and paid. The compounding return shows up the first time someone opens Claude before opening a runbook, a dashboard, or a PR.

SECTION 7

One Risk / One Next Step

The risk

Plans decay. 50 plans on a Friday become 8 plans on the next Friday if the environment does not reward the new behavior. The risk is not that the team forgot the prompt patterns — it is that the on-call rotation, the PR review queue, and the standup format all still reward the old workflow.

The next step

In the next 30 days, leadership picks one recurring workflow per team and makes “Claude-assisted” the default — PR description, postmortem draft, runbook edit, dashboard mockup. Naming the default is the lock-in. Training is the spark.

PROMPT

Maren close prompt

Verbatim from S027 v4 spec §"The Maren Close" (lines 690-795). Paste this into an active Maren session (sm_activate.py + MCP tools loaded + Maren memory).

You are Maren, my AI operating system at America's Car-Mart. You have
access to live Jira via MCP, live Confluence via MCP, and your memory
of this organization's technology strategy, active projects, and team
structure.

I've just completed a 2.5-hour AI training session for the full
ACM Technology Group — approximately 50 people across application
development, data and analytics, product management, UX, QA, help
desk, infrastructure, and security. Every participant produced a real
work artifact during the session and generated their personal 90-day
AI adoption plan.

Do the following:

STEP 1 — Pull live data:
Search Jira for active and recently completed work across our key
projects. Note the work types, statuses, and breadth of what's
in flight right now.

Search Confluence for the most recent Build Team Update and Maintain
Team Update. Extract the delivery summary, active workstream count,
and any notable blockers or milestones.

Search your memory for what you know about the ACM technology org
structure, active programs, and the strategic context around AI
adoption.

STEP 2 — Build the output:
Generate a complete, self-contained interactive HTML dashboard titled
"ACM Technology Group — AI Readiness Dashboard" dated June 10, 2026.

The dashboard must include all of the following:

SECTION 1 — CAPABILITY SNAPSHOT
Four stat cards with animated count-up on load:
- Active workstreams (pull from Jira)
- Tickets resolved in the last 30 days (pull from Jira)
- Team members trained today: 50
- Projected hours saved per week at T3 adoption: calculate this as
  (50 people × 1.5 hours/day × 5 days) and display it

SECTION 2 — LIVE PROJECT HEALTH GRID
A visual grid showing each active Jira project with:
- Project name
- Status indicator (green / amber / red based on in-progress vs
  blocked ticket ratio)
- A one-line summary of current focus from Jira data
- Trend arrow based on recent activity

SECTION 3 — WHAT CHANGED TODAY
A timeline visualization with three nodes:
- 8:00 AM: "ACM Technology Group: 50 team members, AI usage at T1 average"
- 12:00 PM – 2:30 PM: "2.5-hour live training session — 10 tiles,
  4 lanes, 50 personal adoption plans generated"
- NOW: "ACM Technology Group: T3-capable, one skill per person saved,
  50 AI adoption plans active"

SECTION 4 — 90-DAY TEAM COMMITMENT TRACKER
A visual breakdown of what the team collectively committed to, organized
by phase:
- Weeks 1-4 (Habit Formation): behavioral commitments
- Weeks 5-8 (Workflow Integration): recurring tasks being AI-assisted
- Weeks 9-12 (Measurable Impact): outcomes reportable to leadership

Display these as horizontal progress bars or phase cards — not bullets.

SECTION 5 — DELIVERY INTELLIGENCE
Pull from the most recent Build Team Update and Maintain Team Update.
Display:
- A two-column layout: Build team status | Maintain team status
- Key milestones from the last 30 days
- One-line current blocker if any exist
- "AI Acceleration Opportunity" — for each team, one specific task
  type from their recent work where T3 Claude usage would reduce
  cycle time

SECTION 6 — THE STRATEGIC SIGNAL
One paragraph — not bullets — written as if for the CTO. What does
it mean that this team spent today learning to use AI on their real
work, against the backdrop of the actual projects they're running?
Name the programs. Be specific. No generic AI-adoption boilerplate.

SECTION 7 — ONE RISK / ONE NEXT STEP
Two cards side by side:
- Left card (amber): The single biggest risk to AI adoption at this
  stage in a technology organization like this one. Real answer, no
  softening.
- Right card (navy): The one action leadership should take in the
  next 30 days to lock in what happened today.

DESIGN REQUIREMENTS:
- Fully self-contained HTML with inline CSS — no external dependencies
- America's Car-Mart brand colors throughout: navy #002855, red #D50032,
  with white and light gray for backgrounds
- Stat cards animate count-up on page load using vanilla JavaScript
- Project health grid uses color-coded status indicators
- Timeline in Section 3 is a visual horizontal flow, not a list
- Phase tracker in Section 4 uses styled cards or bars, not bullets
- The dashboard should feel like a designed product — not generated text
- Readable on a large screen. This is a presentation artifact.
- Footer: "Generated by Maren — ACM Technology AI Operating System —
  June 10, 2026"