← Automate the BusyworkArrows or space · F for fullscreen · Print to saveTalks

SHIP AI TALKS

Automate the
Busywork

Leave with a time audit, one mapped workflow and a working build.

Ship AI · TalksAutomate the Busywork01/22

Who's hosting

How you do anything is how you do everything.

Santos Hernandez
Santos HernandezFounder, Ship AI
$25k+/moggbucks, built with agents
$0 to $12MARR at ZBD
EU firstMiCAR approval
THE COMMUNITY

Ship AI

Free workshops and talks in Phoenix.

shipai.club
THE STUDIO

Ship AI Studio

AI built into your business, in two weeks.

shipaistudio.com

Ship AI · TalksAutomate the Busywork02/22

Join the room

SHIP AI DISCORD

Scan it now.
Prompts later.

Open the Discord invite

Ship AI · TalksAutomate the Busywork03/22

Our partner

Ship AIWorkuityAI Exchange

Building Phoenix's AI community, together. Workuity hosts tonight, and we present Founder Weekend side by side.

Ship AI · TalksAutomate the Busywork04/22

THE IDEA

Don't automate a guess.
Measure, map, then build.

Ship AI · TalksAutomate the Busywork05/22

Start with the hours

TOOL FIRST

Buy a tool. Hope it fits.

Automates whatever was loudest this week.

AUDIT FIRST

Find the hours.
Then automate the top one.

Ship AI · TalksAutomate the Busywork06/22

Tonight

01

Audit

02

Map

03

Build

04

Measure

Ship AI · TalksAutomate the Busywork07/22

Saguaro Books, one week

TIME-AUDIT.md
Firm

Five people. Six new clients a week.

Score

Hours a week x Rules x Risk, each 1 to 3.

Top task

Client onboarding: 7 hrs, 6x a week. Score 63.

Ranked

Categorizing transactions: 18

"Where's my report?" emails: 15

Month-end review: 6

Ship AI · TalksAutomate the Busywork08/22

Log one week

claude · ~/saguaro-ops

claudeWhich tasks come back every week?

youOnboarding, chasing documents, client emails.

✓ TIME-AUDIT.md: log table, 4 scoring columns

Copy · set up the time audit
Interview me about my recurring work, then write TIME-AUDIT.md with a log table and the scoring columns. Stop there.

Full prompt

Copy this entire prompt into Claude Code.

I want to find which work in my business is worth automating. Help me run a one-week time audit.

1. Ask me one question at a time and wait for each answer: my role, team size, and the recurring tasks I think take the most time.
2. Write TIME-AUDIT.md with:
   - A Log table: Date, Task, Minutes, What started it, Tools used, Notes. Prefill the Task column with the tasks I named.
   - A Scoring section that explains the columns we'll fill in after the week: Hours per week, Times per week, Rules (3 = follows written rules, 2 = mixed, 1 = judgment), Risk (3 = low if it goes wrong, 2 = medium, 1 = money, legal or client-facing with no review). Score = hours per week x Rules x Risk.
   - A short How to log note: log each task when you finish it, rounded to 5 minutes, for five working days. Add new tasks as they come up.

Don't score anything yet. Stop when the file is written.

Ship AI · TalksAutomate the Busywork09/22

Score the week

claude · ~/saguaro-ops

Onboarding · 7.0 h · 6x · R3 · K3 · 63

Categorizing · 9.0 h · 25x · R2 · K1 · 18

claudeOnboarding is mostly rules. Map it first?

Copy · score and rank
Total the log, propose Rules and Risk scores for me to correct, rank by score, and recommend one workflow to map.

Full prompt

Copy this entire prompt into Claude Code.

Read TIME-AUDIT.md. My log for the week is filled in.

1. Total the minutes for each task and add Hours per week and Times per week.
2. Propose a Rules score and a Risk score for each task, with a one-line reason each. Show me the table and wait for my corrections.
3. Compute Score = hours per week x Rules x Risk. Rank the tasks, breaking ties by times per week, and add a Ranking section.
4. For the top three, write one line each: what a machine could do, and what has to stay with a person.
5. Recommend one workflow to map first, then stop and wait for my pick.

Ship AI · TalksAutomate the Busywork10/22

Who owns each step

Every step gets an ownerOne workflow

Trigger, inputs, decisions,
handoffs, outputs, exceptions

01

Automation

A written rule decides. Same input, same output.

02

AI

Drafting, reading and matching. A person checks the result.

03

Human

Anything that sends, spends or touches the books.

Ship AI · TalksAutomate the Busywork11/22

Map the workflow

claude · ~/saguaro-ops

claudeWhat happens when a document doesn't match?

youIt goes to the office manager.

✓ WORKFLOW-MAP.md: 9 steps · 3 automation · 3 AI · 3 human

Copy · write the workflow map
Interview me about the top workflow, then write WORKFLOW-MAP.md: a step table marked AI, Automation or Human, exceptions and a mermaid flowchart.

Full prompt

Copy this entire prompt into Claude Code.

Read TIME-AUDIT.md. We're mapping the workflow I picked from the Ranking section.

Interview me one question at a time and wait for each answer. Cover: what starts it, every input, each step in order, the decisions and who makes them, the handoffs between people, the outputs, and the exceptions (what goes wrong, and what happens then).

Then write WORKFLOW-MAP.md with these sections: Why this one (its audit score), Trigger, Inputs, Map (a table: #, Step, Inputs, Output, Who), Decisions, Handoffs, Exceptions, Flow (a mermaid flowchart in a ```mermaid code block), Rules, Done when.

Mark Who as one of Automation, AI or Human. Use Automation wherever a written rule decides. Use AI only for drafting, reading or matching. Mark Human for anything that sends, spends money or changes the books, and for every exception.

Don't write code. Stop and wait for my OK.

Mermaid renders in Markdown files on GitHub.

Ship AI · TalksAutomate the Busywork12/22

Tonight's workflow map

WORKFLOW-MAP.md
Trigger

Intake form submitted after the engagement letter.

Map

9 steps: 3 automation, 3 AI, 3 human.

Exceptions

Unsure match, client question, day 14: a person.

Done when

Nothing sends without Approve

Uploads tick the right items

Minutes per client compared

Ship AI · TalksAutomate the Busywork13/22

Start with a script

~/saguaro-ops
STEPS 1 TO 3, NO AI YETnode onboard.mjs
✓ 3 clients · 3 checklists

Run it twice. The second run creates nothing.

01

Rules first

The firm owns rules/checklists.md.

02

Fake data

Three sample clients, no real names.

03

Safe to rerun

tracker.csv remembers who's done.

Copy · the onboarding script
Write the firm's checklist rules, three fake clients and onboard.mjs: folder, CHECKLIST.md and a tracker row per client. Safe to run twice.

Full prompt

Copy this entire prompt into Claude Code.

Read WORKFLOW-MAP.md. Build steps 1 to 3 as a plain Node.js script. No AI yet.

1. Run npm init -y in this folder.
2. Write rules/checklists.md from the Inputs section: the documents each entity type and intake answer requires. Show it to me and wait for my edits. This file is the firm's rules, so keep it readable.
3. Create intake/new-clients.csv with three fake clients: a sole prop, an LLC with payroll, and an S corp with sales tax. No real names or numbers.
4. Write onboard.mjs. It reads the CSV, skips anyone already in tracker.csv, creates clients/<client>/inbox/, writes clients/<client>/CHECKLIST.md with one checkbox per required document, and appends a tracker.csv row with status "checklist ready".
5. Run it twice and show me that the second run creates nothing. Stop there.

Ship AI · TalksAutomate the Busywork14/22

Add the AI steps

claude · ~/saguaro-ops

✓ outbox/mesa-lawn-welcome.md · awaiting approval

✓ bank-statement-oct.pdf → Bank statements · high

? scan-0042.pdf → NEEDS-REVIEW.md · low

Copy · drafting and matching
I add my API key. Then Claude drafts welcome emails into an outbox, matches uploaded PDFs to the checklist, and drafts reminders. Nothing sends.

Full prompt

Copy this entire prompt into Claude Code.

Read WORKFLOW-MAP.md, steps 4, 6 and 7, and the Rules section.

1. Tell me to add ANTHROPIC_API_KEY to .env.local myself, and wait until I tell you it's done. Then run npm install @anthropic-ai/sdk. Check Anthropic's docs for the current model ID instead of guessing.
2. Create rules/tone.md with three lines on how we write to clients, and wait for my edits.
3. draft-welcome.mjs: for each client with status "checklist ready", ask Claude for a short welcome email that lists the documents from CHECKLIST.md in our tone. Save it to outbox/<client>-welcome.md marked "awaiting approval". Never send anything.
4. match-docs.mjs: for each PDF in clients/<client>/inbox/, send it to Claude as a PDF document block with the checklist. Ask for JSON back: the matching item, confidence (high or low) and a one-line reason. Tick high-confidence items in CHECKLIST.md and list the rest in NEEDS-REVIEW.md. Never rename, move or delete client files.
5. draft-reminders.mjs: for clients whose welcome went out 3 or 7 days ago with items missing, draft a reminder that lists only the missing document names. No tax IDs or account numbers in any email.
6. Before we use real client documents, remind me to check our data policy. For now I'll drop three test PDFs into one client's inbox. Wait until I tell you it's done, then run all three scripts and show me the results. Stop there.

platform.claude.com/docs

Ship AI · TalksAutomate the Busywork15/22

Nothing sends without a yes

FULLY AUTOMATIC

The script emails clients.

One bad draft reaches every inbox.

APPROVAL QUEUE

The script drafts.
A person clicks Approve.

Copy · the approval app
A one-page local approval queue: Approve sends through Resend once and logs it, Reject and Edit don't. Dry-run until I set up Resend.

Full prompt

Copy this entire prompt into Claude Code.

Read WORKFLOW-MAP.md, steps 5 and 8, and the Rules section.

1. Build a small local app, one page on localhost, that lists every draft in outbox/ marked "awaiting approval": recipient, subject, body, with Approve, Edit and Reject buttons.
2. Approve is the only path that sends. It sends with Resend (npm install resend) using an idempotency key of onboarding/<draft file name>, marks the draft sent, and logs the send in tracker.csv with the time and who approved it. No script sends anything on its own.
3. Until I say Resend is ready, run Approve in dry-run mode: write to sent-log.md instead of sending.
4. Tell me to create a Resend account, verify our sending domain, and add RESEND_API_KEY to .env.local myself. Wait until I tell you it's done.
5. Then switch off dry-run, and have me approve one draft addressed to my own email first. Stop there.

Ship AI · TalksAutomate the Busywork16/22

Run it, then measure it

npm run daily

1 new client · 2 drafts awaiting approval

4 items ticked · 1 needs review

claudeOnboarding: 41 min per client, down from 70.

Copy · daily run and measurement
One npm run daily with a summary, a RUNBOOK.md, and a minutes-per-client log to compare against the audit. Then check Done when.

Full prompt

Copy this entire prompt into Claude Code.

Read WORKFLOW-MAP.md and TIME-AUDIT.md.

1. Add an npm script, daily, that runs onboard, draft-welcome, match-docs and draft-reminders in order, then prints a summary: new clients, drafts awaiting approval, items ticked, items needing review, clients complete.
2. Write RUNBOOK.md: how to run it each morning, what to do with NEEDS-REVIEW.md, how to pause it, and who to ask when something looks wrong.
3. Add a Minutes per client table to TIME-AUDIT.md, with the baseline from the audit week. Tell me to log real minutes for the next two weeks.
4. If I want it to run on a schedule, show me the line to add to my own scheduler. Don't add it yourself.
5. Check every Done when item in WORKFLOW-MAP.md, tell me which pass, and stop.

Ship AI · TalksAutomate the Busywork17/22

BONUS ROUND

Same map.
Any builder.

Ship AI · TalksAutomate the Busywork18/22

Build it in n8n, Zapier or Make

claude · ~/saguaro-ops

youPlan it for Zapier.

Step 5 → Human in the Loop · Request Approval

✓ BUILDER-PLAN.md · 9 steps · 2 unverified

Copy · a plan for a visual builder
Pick n8n, Zapier or Make, read its docs, and turn WORKFLOW-MAP.md into a step-by-step build plan with the approval steps in place.

Full prompt

Copy this entire prompt into Claude Code.

Bonus round. Read WORKFLOW-MAP.md. I want to build this workflow in a visual builder instead of code: n8n, Zapier or Make. Ask me which, and wait for my answer.

1. Read that tool's current docs before writing anything.
2. Write BUILDER-PLAN.md: for each step in the Map table, the trigger, node, action or module to use, and the app connections I'll need.
3. Put the human approval where the map says Human. For n8n, check the docs on human review steps for AI tool calls. For Zapier, check the Human in the Loop Request Approval action. For Make, look up what its docs offer, and say so plainly if there's no built-in approval step.
4. Mark anything you couldn't confirm in the docs as unverified.

I'll do the signup and the build myself. Don't sign up for anything. Stop when the file is written.

More talks at shipai.club/talks. Bring your map to the Discord.

Ship AI · TalksAutomate the Busywork19/22

Take it home

THE TALK PAGE

Every prompt,
and this deck.

Open the talk page

Ship AI · TalksAutomate the Busywork20/22

Founder Weekend

FEB 6‑7, 2027 · FREE

Tonight was one hour.
Take a weekend.

An Arizona AI hackathon. Teams of 1-4.

See the hackathon

Ship AI · TalksAutomate the Busywork21/22

SHIP AI DISCORD

Free and open.
Build with us.

Scan to join

Ship AI · TalksAutomate the Busywork22/22
01/22