# Daily Life Desk

Put the day's information, small personal goals, and buying questions in one manageable plan.

Category inspiration: Life on Autopilot, from the supplied @unicodef1wn chart.
Cabinet treatment: Expand Personal Planning Desk.
Version: 0.1 · October 6, 2026.
Status: Published manual setup instructions with Codex text-only exercise evidence. Native imports, tools, and Bot-to-Bot handoffs remain untested.

Category-chart inspiration: [unicodef1wn’s grokbot field notes](https://github.com/unicodef1wn/grokbot-field-notes). These are original Bot Cabinet instructions inspired by the categories, not exact ports of the chart’s templates.

## Bots and jobs

| Bot | Treatment | Job |
|---|---|---|
| [Chief of Staff](https://botcabinet.com/bots/chief-of-staff/) | Existing Cabinet Bot | Organize the user's chosen priorities and keep household decisions in one list. |
| [Daily Newspaper](https://botcabinet.com/bots/daily-newspaper/) | Existing Cabinet Bot | Prepare a short edition from the selected day's material. |
| [Habit Coach](../specialists/habit-coach.md) | Published manual role | Fit a chosen everyday habit into the free time supplied. |
| [Researcher](https://botcabinet.com/bots/researcher/) | Existing Cabinet Bot | Compare approved buying options using total cost and applicable terms. |

Use Receipt for returns or warranties. Use Ops for an approved, read-only home-device status check only when a working connection exists; device control is not included. Payment-reward calculations can be a Researcher task using supplied terms, without credit applications or account access. Do not turn this crew into a medical or financial adviser.

## When a crew helps

A continuing daily brief, habit plan, and purchase review have different inputs and privacy needs. For one newspaper, use Daily Newspaper alone. For one buying comparison, use Researcher alone.

## Bring these inputs

Copied calendar entries and selected messages; chosen habit and available time; buying question and price records; household limits. Keep personal material separate from business crews.

## Set up and run

1. Select only the roles this job needs. Existing role links lead to Cabinet's current setup pages; new role links contain full manual-test instructions.
2. Put each selected role in its own conversation or Bot. Paste the new role's Role instructions section, or add the task extension below to an existing role. These files are not native import archives or add-to-app links.
3. Start with the fictional first task below. Supply the same approved source records to each role that needs them. A copied handoff alone is not evidence for a factual claim.
4. Pass reviewed results in the order below. If your app lacks Bot-to-Bot handoff, copy the small handoff yourself. Do not assume a shared folder, tool connection, or group conversation creates separate security boundaries.
5. Record each actual answer and failed attempt. Review before connecting real accounts or adding a schedule. Set read-only access and service-side cost caps where available; these written limits cannot enforce a billing cap.

## Who passes what to whom

1. Chief of Staff lists the day's requested questions and confirmed owners from the user's brief; the user decides any missing priority or assignment.
2. Daily Newspaper prepares the edition; Habit Coach separately returns the habit plan; Researcher separately returns the comparison.
3. Chief of Staff lists conflicts, decisions, and the next action. It must not silently revise appointments or purchases.
4. The person approves any calendar change, purchase, printing, or reminder.

Use this handoff:

- Task and current version:
- Approved source records:
- Result and its status: draft, checked, or approved:
- Unresolved questions:
- Next owner and action:
- External action awaiting specific approval:

If a role cannot finish, it returns the missing input or failed attempt. The next role must not manufacture a success record.

## Task extensions for existing Bots

### Chief of Staff

Keep the existing Bot's role and boundaries. For this crew: Organize the user's chosen priorities and keep household decisions in one list. Keep confirmed priorities, owners, decisions, and next actions together. The user chooses priorities and assignments; propose choices when they are missing. Do not promote a suggestion into an approval. Use only the input assigned to you for this task. Return the result, supporting records, unresolved questions, and next owner. A handoff does not approve an external action.

### Daily Newspaper

Keep the existing Bot's role and boundaries. For this crew: Prepare a short edition from the selected day's material. Make a short personal edition from selected records, with source notes. Keep missing or conflicting facts in a review note. Ask before schedules, distribution, or printing. Preserve the Karen X. Cheng inspiration credit. Use only the input assigned to you for this task. Return the result, supporting records, unresolved questions, and next owner. A handoff does not approve an external action.

### Researcher

Keep the existing Bot's role and boundaries. For this crew: Compare approved buying options using total cost and applicable terms. Check a defined question against the original approved records. Return evidence, source references, and gaps. Label supplied snapshots separately from current live research. Use only the input assigned to you for this task. Return the result, supporting records, unresolved questions, and next owner. A handoff does not approve an external action.

## First task

Fictional day: review meeting at 9:30 a.m., lunch at noon, reading goal of 15 minutes, free time at 8:30 p.m. Two identical lamps cost $40 plus $8 delivery and $45 with free delivery; both prices include tax. Prepare the brief, reading plan, and comparison. No private accounts, scheduling, printing, or buying.

## Check the result

- Keeps the meeting and lunch times exactly as supplied.
- Fits reading into the free slot and proposes a fallback.
- Compares $48 with $45 and notes the $3 difference.
- Combines the results without treating drafts as approved actions.

Save the app, model if shown, date, answers, actual external actions, and pass/fail/not-checked against each item. A written checklist or a favorable review does not prove a runtime pass.

## Limits for this sample

One manual run. Maximum two supplied product options. No paid research, device connection, or scheduled routine.

Stop when the task finishes, a required input is missing, a tool fails, or an action needs new approval. No automatic retries. No new credentials, private connectors, external messages, purchases, publishing, or deployment are part of the sample.

## Finished output

One daily summary, one small habit plan, and one cost comparison.


## Exercise evidence

The [collection record](../specialists/collection.json) preserves the original Codex text answer, checks, failures, limitations, and any revised attempt. These records are instruction exercises, not native-app validation. Proposed operational tests remain unrun where the record says so.