BotCurrent↗
← Back to examples

Proposed · Not tested

Cleaning teams repeat onboarding because the job standard lives in one person’s head

Extension of source-backed task: Turn working technical notes into published team documentation. This is not an additional source-backed job.

Proposed · Not tested. This is an original editorial plan. Capability and problem-context sources do not demonstrate execution, successful results or customer demand. Platform compatibility is unknown and untested.

The problem

New staff may miss handover details when training is informal and each location’s expected finish differs.

Agent job

Convert approved observations into location-specific completion checks, clear exceptions and a trainer signoff sheet; flag ambiguous standards for the owner.

Expected output

Original editable onboarding checklist pack for three non-hazardous service types, with version and review date.

Why an agent / simpler alternative

Assessment

The agent can turn informal owner explanations into observable checklist items and flag conflicting standards. A standard checklist template may suffice for a uniform job. A trainer must demonstrate and validate work; safety, chemical and equipment training require qualified human input.

Setup requirements

Items
  1. Owner-approved non-hazardous walkthrough notes and clear service exclusions

  2. Staged, rights-cleared example photos without occupants or private details

  3. Named trainer and a defined completion standard

  4. Editable checklist format; live job-system integration excluded from the initial pilot

Inputs and access

  1. Name

    Owner-approved non-sensitive walkthrough notes

    Source or owner

    Prospective consenting customer or specified official publisher

    Sensitivity

    Use synthetic, public or appropriately deidentified material; confirm actual sensitivity before work

    Permission needed

    Owner authorizes scoped access and processing; verify rights and retention before receiving files

  2. Name

    Existing job checklists and service scope

    Source or owner

    Prospective consenting customer or specified official publisher

    Sensitivity

    Use synthetic, public or appropriately deidentified material; confirm actual sensitivity before work

    Permission needed

    Owner authorizes scoped access and processing; verify rights and retention before receiving files

  3. Name

    Staged example photos with no people or private customer details

    Source or owner

    Prospective consenting customer or specified official publisher

    Sensitivity

    Use synthetic, public or appropriately deidentified material; confirm actual sensitivity before work

    Permission needed

    Owner authorizes scoped access and processing; verify rights and retention before receiving files

Proposed steps

  1. Select one routine service and list explicit exclusions, including hazardous work.

    Expected output: Scope and safety-exclusion sheet

    Approval gate: Owner supplies all required safety guidance; the agent must not invent it.

  2. Break the approved walkthrough into observable actions and record unclear finish standards.

    Expected output: Draft task inventory and questions

    Approval gate: Trainer resolves ambiguity before any worker-facing instructions.

  3. Map actions to checklist items, exceptions and owner-approved staged reference images.

    Expected output: Versioned checklist draft

    Approval gate: No private customer images or new chemical/equipment advice.

  4. Have the trainer simulate the checklist in a staged setting and mark missing or uncheckable items.

    Expected output: Trainer pilot notes

    Approval gate: Do not use unreviewed instructions on a live customer job.

  5. Revise items and add signoff fields, revision dates and escalation contacts.

    Expected output: Reviewed checklist and trainer handoff

    Approval gate: Owner confirms instructions do not expand the sold service scope.

  6. Deliver the editable pack and show how changes will be approved and versioned.

    Expected output: Final pack and update procedure

    Approval gate: Owner approves release; any Jobber or other in-app writes need separate authorization.

Synthetic output illustration — not an executed result

Synthetic

Yes

Executed

No

Text

SYNTHETIC: Item R04: “Return chairs to the layout in approved staged photo P02.” Evidence: trainer observation. Exception: damaged furniture, stop and notify lead. Owner review: pending. This is an invented ordinary-tidying example, not an instruction validated for a real site.

Human approval boundaries

  1. Owner approves instructions and employee-facing release; qualified human supplies any safety training. Separate approval for real client data or in-app checklist changes.

  2. Human service provider reviews quality, scope and quoted fee; customer approves contract, delivery recipients and payment terms. Separately approve purchases, credentials, publication and external sends. No commitments or payments are made in this research.

Failure modes

  1. Notes can omit important steps

  2. Generic instructions may conflict with a site

  3. Photographs can disclose customer information

  4. Unsafe chemical or equipment instructions must not be generated

Recovery and troubleshooting

Items
  1. If a step involves hazards, chemicals or equipment, remove it from the authored scope and request qualified approved instructions.

  2. If staff interpret an item differently, rewrite it into an observable result and repeat the staged walkthrough.

  3. If site-specific differences dominate, split the checklist into a stable base plus owner-approved site exceptions.

Unexecuted validation plan

Sample setup

Use a staged room and owner-supplied routine tidying walkthrough, excluding hazards and chemical instructions.

Acceptance checks
  1. Owner verifies every instruction

  2. Trainer can mark each item objectively

  3. Worker flags ambiguity before live use

  4. No safety, chemical or equipment advice invented

Stop conditions
  1. Stop if data authority or rights are unclear.

  2. Stop if critical seeded failures are missed; do not claim readiness.

  3. Stop if manual correction time exceeds the pilot effort budget without customer approval.

Executed

No

Costs and effort — unknown or hypothetical

Status

unknown_or_estimate

Currency

CAD

Items
  1. Agent subscription/API usage: not quoted; verify current plan and commercial data terms.

  2. Human intake, rights review, QA and revisions: unknown until timed pilot.

  3. Storage, hosting, integration and payment-processing costs: excluded unless separately agreed.

  4. Customer acquisition and support time: not measured.

Caveat

No margin or income estimate. Price hypotheses are editorial offer tests, not observed market rates; taxes, scope and effort require a real quote.

Proposed service concept — earnings not verified or guaranteed

Buyer

Small residential or office-cleaning business owner

Deliverable

Original editable onboarding checklist pack for three non-hazardous service types, with version and review date.

Charging basis

One-time checklist design and handoff; later updates quoted per changed service.

Acquisition channel

Permission-based discovery with existing professional contacts, referrals or an opt-in sample page; none executed.

Assumptions
  1. Customer has this unresolved problem and values a reviewed deliverable above existing built-in alternatives.

  2. A consenting pilot confirms data access, achievable quality and economically tolerable review time.

  3. Provider can deliver within a written scope and supports the result.

Revenue guarantee

No

Canadian adaptation — proposed

Proposed Canadian pilot: ask the owner which English/French worker-facing version and metric/imperial measurements are used, and validate each version with the trainer. Keep site-specific instructions separate and obtain qualified approved safety content; do not invent provincial workplace requirements. No training certification or Canadian field test.

Limits

  1. Original proposed plan; untested.

  2. Problem and capability references are evidence of context only, not demonstrated end-to-end success, customer demand, willingness to pay or profitability.

  3. Compatibility, workload, delivery effort and availability must be verified in a real authorized pilot.

  4. Platform references refreshed on 14 October 2026; verify the actual account, execution surface, permissions and dependencies before any pilot.

Context and capability sources

These links support context or possible capabilities, not completion of this plan. Current access is conditional; verify the account, environment and permissions before any test.

https://community.getjobber.com/discussions/cleaning-and-property-maintenance/traning-process/3771 ↗
Problem context only; frequency, buyer demand and this workflow are not validated.

https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork ↗
Current general capability context only; exact workflow compatibility and execution remain untested.

https://support.claude.com/en/articles/16761823-claude-cowork-and-chat-are-one-claude ↗
Current general capability context only; exact workflow compatibility and execution remain untested.

Candidate platforms — compatibility untested

  1. Name

    Claude (Cowork capabilities)

    Required capabilities
    1. Read supplied files and produce editable documents and spreadsheets.

    Capability source urls
    1. https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork

    2. https://support.claude.com/en/articles/16761823-claude-cowork-and-chat-are-one-claude

    Workflow compatibility

    Unknown; verify in the proposed first test.

    Historical candidate name

    Claude Cowork

    Selection basis

    Editorial candidate from general capabilities; exact end-to-end fit untested.