Untethered Artifact Vault

Complete Field Examples

Illustrative teaching artifacts, from the first-week company brief to the month-12 board story. Northstar Field Services and the figures below are presented as worked examples, not a verified customer case study. Use them to understand the format; replace every assumption and result with your own evidence.

Day 7

Inherited Company Brief

Example First Week Commander Intake

Purpose: give the founder, operator, or advisor a single page that captures what was inherited before prescribing AI. This prevents tool-first theater.

Company Snapshot

CompanyNorthstar Field Services
Size78 employees, 3 locations, $18.4M annual revenue
Operating ModelField technicians, dispatcher team, sales reps, service managers, finance/admin office
SystemsQuickBooks, ServiceTitan, Microsoft 365, SharePoint, RingCentral, Excel reporting packs
Commander HypothesisThe company isn't short on effort. It's leaking time through status chasing, duplicate data entry, slow quoting, and unclear exception handling.

Top Outcomes

  1. Reduce quote-to-dispatch cycle time from 3.8 days to under 1.5 days.
  2. Cut manual reporting effort by 50% within 90 days.
  3. Improve first-response speed for inbound service requests.
  4. Lower dispatcher after-hours workload.
  5. Create reliable executive visibility without spreadsheet hunting.

Top Workflow Frictions

  • Service notes copied from calls into tickets by hand.
  • Sales quotes require context from three systems.
  • Dispatchers chase technicians for job status updates.
  • Finance rebuilds revenue reports every Friday.
  • Managers disagree about which number is current.

Top Trust Risks

  • Customer data scattered across inboxes and ticket notes.
  • No standard approval gate for refunds and discounts.
  • Shared passwords still exist for legacy vendor portals.
  • AI use already happening in personal accounts.
  • No documented prompt, model, or output review policy.

First Three AI Candidates

  • Call-summary to ticket-note draft.
  • Quote preparation brief for sales reps.
  • Weekly executive operating report from trusted data exports.
Commander note: don't start with autonomous customer replies or refund decisions. Start with draft, summarize, classify, and prepare. Earn trust before taking action.
Back to manual
Day 30

Operating Friction Map

Purpose: rank the operating pain by frequency, effort, risk, and fit for AI or automation.

FrictionFrequencyEffortRiskCandidate FixOwner
Manual call summaries into service ticketsDaily / 90+ callsHighMediumAI draft + human approvalService Ops
Quote research across inbox, CRM, and PDFsDaily / 15-20 quotesHighMediumRAG brief + quote checklistSales Ops
Friday revenue reportingWeeklyHighLowAutomated extract + commentary draftFinance
Customer status requestsDailyMediumHighInternal answer assist onlyCustomer Care
Technician ETA updatesDailyMediumMediumWorkflow automation + exception alertsDispatch
Refund approvalsWeeklyLowHighDo not automate yet; build decision briefGM

Highest-Leverage First Move

Call-summary to ticket-note draft. It's frequent, measurable, reviewable, and low enough risk if the human stays in the approval loop.

Do Not Touch Yet

Refund approvals and public customer commitments. These require governance, approval gates, and clean data before AI can safely participate.

Back to manual
Day 45

AI Workload One-Pager

Workload

NameService Call to Ticket Note Draft
TriggerCall recording/transcript lands after inbound customer call.
AI JobSummarize issue, urgency, customer sentiment, promised follow-ups, equipment references, and missing information.
Systems TouchedRingCentral transcript, ServiceTitan ticket, Microsoft 365 account context.
Human ReviewDispatcher reviews and edits before ticket note is saved.

Value Case

  • Baseline: 4.5 minutes average manual note per call.
  • Target: 90 seconds average review and save.
  • Volume: 90 calls per day, 22 business days.
  • Hard value: 99 hours/month reclaimed before quality improvements.
  • Soft value: faster handoff, fewer forgotten promises, less dispatcher fatigue.

Red Lines

  • AI may not promise a technician arrival time.
  • AI may not approve refunds, discounts, or credits.
  • AI may not classify legal threats without escalation.
  • AI may not save directly to the ticket without human review.

Pilot Decision

Proceed. The workload is frequent, bounded, measurable, and reviewable. Launch as supervised draft mode with daily quality sampling for the first two weeks.

Back to manual
Day 60

Pilot Charter

Pilot NameService Call to Ticket Note Draft
OwnerDirector of Service Operations
Executive SponsorGeneral Manager
Timeline14-day controlled pilot, 5 dispatchers, 1 location, inbound service calls only
In ScopeDrafting internal ticket notes from call transcripts; urgency flag; missing-information checklist.
Out of ScopeCustomer replies, refunds, scheduling commitments, technician performance commentary, legal/compliance classification.
Success Threshold40% reduction in note time, 90% dispatcher acceptance after edit, no high-severity hallucinations.
Test CasesRoutine request, angry customer, warranty question, missing equipment ID, refund demand, emergency request, unclear audio.
Kill CriteriaTwo high-severity errors, review time exceeds manual time for three consecutive days, dispatcher trust score below 3/5.
Failure plan: disable draft insertion, keep transcript summaries in sandbox, review failures, update prompt and retrieval rules, relaunch only after sponsor approval.
Back to manual
Day 90

Value Readout

Time

Manual note time fell from 4.5 minutes to 1.7 minutes average. Estimated 92 hours/month reclaimed.

Quality

Dispatcher acceptance rate after edit reached 88%. Missed follow-up mentions fell by 31% in sampled tickets.

Adoption

Four of five dispatchers asked to keep the tool. One dispatcher requested more control over summary format.

QuestionFindingDecision
What changed?Notes are faster, more consistent, and less emotionally loaded after difficult calls.Graduate to second location.
What failed?Urgency labels were too aggressive for warranty language. Prompt revised.Keep urgency as recommendation only.
What value was created?92 hours/month reclaimed, fewer handoff misses, better dispatcher morale.Add to reusable workload library.
What comes next?Quote-prep brief is now the strongest adjacent workflow.Draft pilot charter.
Back to manual
Month 6

Governance Desk

A plain-English policy that lets the business scale AI without pretending probabilistic systems are ordinary software.

Agent May DoAgent May RecommendAgent May Never Do
Summarize, classify, draft internal notes, prepare briefs, flag missing information, propose next steps. Customer response language, quote assumptions, exception handling, escalation severity, workflow changes. Send public messages, approve refunds, delete records, change pricing, commit legal positions, bypass human review.

Who Decides What

Every request an agent submits carries its own routing authority. The route decides which human can act on it.

RouteWho Acts
Log onlyNobody. The record is the point.
Standard approvalA different human than the submitter. No self-approval, ever.
Manager approvalThe submitter's manager.
Team approvalAny member of the named team.
Admin approvalAny admin.

Logging Standard

  • User
  • Agent
  • Model
  • Prompt version
  • Inputs and retrieval sources
  • Output
  • Human decision
  • Cost

Review Cadence

  • Daily sampling during pilot
  • Weekly quality review
  • Monthly cost and risk review
  • Quarterly model/vendor review

Incident Response

  • Pause workload
  • Preserve logs
  • Notify owner and sponsor
  • Classify severity
  • Fix prompt/data/control
  • Approve relaunch
No undo. Once a decision fires, downstream systems fire. The two-step confirm is the safety mechanism; an undo that sometimes works is worse than none.
Back to manual
Month 9

Reusable Skills Library

Purpose: catalog proven capability as versioned skill packages an agent loads on demand. Each row is a folder in version control: a trigger description, a procedure, and any bundled scripts.

SkillFires WhenBundled ToolsControlsOwner / Version
Executive Summarizer"Summarize this," "give me talking points," or a long paste asking for a tighter versionNone; procedure onlyPreserves the author's stance; banned-word list for AI slop; flags unsupported claims instead of smoothing themContent desk / v2
Database Operations"Apply the migration," "run this SQL," or a pasted project referenceFour helper scripts; access token fetched from the OS keychain at runtimeNever echoes credentials; confirm before destructive statements; migrations additive by defaultEngineering / v3
Signal Curator"Review fresh signals," "promote signal," "list angles"Pipeline API scriptsAgent scores and stages; only a human promotes toward publishContent desk / v1
Ad Pre-ScreenNew paid creative lands in the queueModeration API callClean pass auto-approves; flagged waits for a human; payment held in escrow until decidedRevenue desk / v1

Approved Pattern

Prompt first, in draft mode. The third reuse, or the first credential, forces graduation into a package. Version it, name an owner, review every edit like code.

Known Failure Mode

Skill drift. An edit that skips review silently changes the behavior of every agent that loads the skill. Treat a skill edit like a schema change, not a wording tweak.

Back to manual
Month 12

Board-Ready Transformation Story

The Narrative

We inherited a hardworking operation with fragmented systems, spreadsheet-dependent reporting, and undocumented AI use. In year one, we stabilized the data flows, created an AI governance desk, piloted four supervised workloads, and promoted two into standard operating practice.

The result wasn't "AI magic." It was operating discipline: clearer ownership, faster handoffs, fewer missed follow-ups, and a reusable library of patterns that can now be applied across locations.

Board Metrics

  • 92 hours/month reclaimed from first graduated workload.
  • 31% reduction in sampled missed follow-ups.
  • Two AI workloads graduated, one revised, one killed.
  • AI usage moved from personal accounts into governed lanes.
  • Prompt, model, logging, and escalation standards established.

Risk Retired

Untracked AI use, shared prompts, unmanaged keys, missing approval gates, and unclear accountability.

Value Created

Time savings, quality consistency, operating visibility, reusable assets, and stronger employee trust.

Year-Two Roadmap

Expand workload library, add deeper retrieval, integrate CRM and finance reporting, and formalize vendor/model review.

Board line: the company didn't just adopt AI. It learned how to govern useful agency.
Back to manual