← Replace the SpreadsheetArrows or space · F for fullscreen · Print to saveTalks

SHIP AI TALKS

Replace the
spreadsheet.

Leave with a spec, eight prompts and an app your team signs in to.

Ship AI · TalksReplace the Spreadsheet01/22

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 · TalksReplace the Spreadsheet02/22

Join the room

SHIP AI DISCORD

Scan it now.
Prompts later.

Open the Discord invite

Ship AI · TalksReplace the Spreadsheet03/22

Our partner

Ship AIWorkuityAI Exchange

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

Ship AI · TalksReplace the Spreadsheet04/22

THE IDEA

Every team runs on a sheet and an inbox.
Give it one small app.

Ship AI · TalksReplace the Spreadsheet05/22

Out of the inbox

SHEET + EMAIL

"Did anyone approve this?"

ONE APP

One queue, one status.
Every decision on the record.

Ship AI · TalksReplace the Spreadsheet06/22

Tonight

01

Spec

02

Build

03

Protect

04

Ship

Ship AI · TalksReplace the Spreadsheet07/22

Tonight's example

TOOL-SPEC.md
Desert Bloom Landscaping

Purchase requests, out of a spreadsheet and an inbox.

Roles

requester, approver, admin. No public sign-up.

Rules

The server decides. Every change leaves a record.

Done when

The sheet's rows are in the app

A requester can't see anyone else's

Ship AI · TalksReplace the Spreadsheet08/22

Write TOOL-SPEC.md first

claude · ~/requests

claudeWhat happens to a request today?

youCrew lead emails Dana. She logs it. Marco replies yes.

claudeWho should see a crew lead's requests?

✓ Wrote TOOL-SPEC.md: 3 roles, 7 statuses, 5 screens

Copy · the TOOL-SPEC.md interview
Interview me about the process, roles, workflow, columns and permissions, then write TOOL-SPEC.md with rules and Done when. Wait for my OK.

Full prompt

Copy this entire prompt into Claude Code.

I want to replace one spreadsheet-and-email process at work with a small internal app. Interview me one question at a time and wait for each answer:
- What happens today: who sends what to whom, and where is it tracked?
- Who uses it, and what roles do they need? Three at most.
- What is the one workflow, from request to done, with every status and who moves each one?
- What are the spreadsheet's columns? I'll paste the header row.
- Who can see which rows, and who can change what?
- What should anyone be able to find out later: who decided what, when and why?
- Where would one AI helper save time, with a person approving what it writes?

Then write TOOL-SPEC.md with these sections: Today, Users and roles, The workflow (a table: from, to, who, note required), Screens, Data, Permissions (a table of actions by role), Rules, Audit trail, AI helper, Import, Out of scope, Done when.

The Rules section must say: the server checks the session and role on every page, action and route; requesters only ever load their own rows; every status change writes an audit row in the same transaction; there is no public sign-up, admins add people; the AI drafts and a person decides; no secrets in the browser.

Stop and wait for my OK before writing any code.

Ship AI · TalksReplace the Spreadsheet09/22

Set up the project

claude · ~/requests

✓ Next.js app created

✓ TOOL-SPEC.md moved into requests

claudeRun neon init in requests, then restart me there.

Copy · set up the project
Create the Next.js app, move TOOL-SPEC.md into it, then stop so I can run neon init there and restart Claude Code.

Full prompt

Copy this entire prompt into Claude Code.

Read TOOL-SPEC.md. Set up the project one step at a time and stop after each step.

1. Create a Next.js app with TypeScript, Tailwind CSS and the App Router:
npx create-next-app@latest requests --ts --tailwind --app --eslint --use-npm --yes
2. Move TOOL-SPEC.md into requests.
3. Stop and tell me to do three things myself, then wait until I tell you it's done:
   - cd requests
   - run npx neon@latest init, which sets up Neon's agent tooling for this folder, links a project and writes DATABASE_URL to .env.local. If it asks me to log in or link, I run the commands it prints
   - start Claude Code again inside requests

Do not build any features yet.

neon.com/docs/reference/cli-init

Ship AI · TalksReplace the Spreadsheet10/22

Sign-in with roles

claude · ~/requests

✓ Drizzle on Neon, transactions on

✓ Better Auth: email and password, sign-up off

✓ Roles: requester, approver, admin

claudeYour turn: create the first admin in your terminal.

Copy · database, auth and roles
Add Drizzle on Neon, Better Auth with sign-up off, and the admin plugin with three custom roles. Then stop so I can create the first admin.

Full prompt

Copy this entire prompt into Claude Code.

Read TOOL-SPEC.md. Add the database and sign-in with roles. Read the current docs before writing code: better-auth.com/docs/plugins/admin and better-auth.com/docs/adapters/drizzle. Stop after each step.

1. Database: install drizzle-orm and @neondatabase/serverless, and drizzle-kit as a dev dependency. Connect with DATABASE_URL from .env.local, using Drizzle's neon-serverless driver so transactions work. Never print the connection string.
2. Auth: install better-auth and the Drizzle adapter its docs name. Turn on email and password with disableSignUp: true, so nobody can create their own account. Generate BETTER_AUTH_SECRET with a command that writes it to .env.local without printing it, and set BETTER_AUTH_URL to http://localhost:3000.
3. Roles: add the admin plugin with the custom roles from TOOL-SPEC.md, using createAccessControl. Add a request resource with create, read_own, read_all, decide and fulfill. Keep the default admin statements for admin. Set defaultRole to requester. Pass the same ac and roles to adminClient().
4. Generate the auth schema with npx auth@latest generate, then the Drizzle migration. Show me the changes before applying them.
5. Tell me to create the first admin myself in my terminal with:
   npx auth@latest create-admin --email <my email> --name "<my name>" --role admin
   Wait until I tell you it's done.

Don't build screens yet. Never print a secret or put one in tracked files or chat.

better-auth.com/docs/plugins/admin

Ship AI · TalksReplace the Spreadsheet11/22

Three roles, one check

ON THE SERVERlib/requests.ts

Every page and action
asks the same module.

01

Requester

Creates requests. Only ever loads their own.

02

Approver

Sees the queue. Approves up to $2,500.

03

Admin

Adds people, imports the sheet, marks ordered.

Ship AI · TalksReplace the Spreadsheet12/22

Build the one workflow

claude · ~/requests

youApprove the $3,100 trencher as Marco.

claudeBlocked: over $2,500 needs an admin.

youApprove it as Dana.

✓ submitted → approved · 1 event logged

Copy · the workflow and screens
Create requests and request_events, one server-only module that scopes every query, one moveRequest() that logs every change, then the five screens.

Full prompt

Copy this entire prompt into Claude Code.

Read TOOL-SPEC.md. Build the one workflow. Stop after each step.

1. Create the requests and request_events tables from the Data section. Nothing in the code may update or delete a request_events row.
2. Write one server-only module, lib/requests.ts, that every page and server action goes through. Each function reads the session from the request headers, checks the role with auth.api.userHasPermission, and scopes the query: for a requester, every query includes requester_id = their own id. No page or component queries the requests table directly.
3. Write one function, moveRequest(), that checks the move against the workflow table in TOOL-SPEC.md for this person's role, enforces the $2,500 rule and "nobody approves their own request", then updates the status and inserts a request_events row in the same transaction. Rejecting and asking for info require a note.
4. Build the screens from TOOL-SPEC.md: New request, My requests, Queue, the request page with its timeline, and People (admin only: add a person with the admin plugin's createUser, set their role with setRole, ban someone who left).
5. Add two test people from People, a requester and an approver. Then show me the queue and one request's timeline after I submit, approve and mark it ordered.

Ship AI · TalksReplace the Spreadsheet13/22

Import the spreadsheet

claude · ~/requests

Dry run: 412 rows · 397 ok · 15 skipped

claude"J. Ortiz" matches no one. Who is it?

youJorge Ortiz, crew 4. I added him.

✓ 412 imported · counts match the CSV

Copy · import the CSV
Parse the CSV with Papa Parse, match names to people, dry run with a skip report, then import in one transaction with an imported event per row.

Full prompt

Copy this entire prompt into Claude Code.

Read TOOL-SPEC.md, section Import. First add data/ to .gitignore. I'll export the sheet to data/requests.csv myself; wait until I tell you it's there. Never commit it.

1. Install papaparse and @types/papaparse. Write scripts/import-requests.ts that parses the CSV with its header row and maps each column to the requests table the way the Import section says, including the status mapping.
2. Match Requested by and Approved by to people by name or email. List every name that doesn't match and stop. I'll add those people in the app or tell you how to map them.
3. Run a dry run first with npx tsx: total rows, rows by status, and every row it would skip and why (missing item, bad date, unknown status). Wait for my OK.
4. Then import inside one transaction. Each imported request gets one request_events row with action imported and the status it had in the sheet. Running the script twice must not create duplicates.
5. Show me the counts by status in the app next to the counts in the CSV.

papaparse.com

Ship AI · TalksReplace the Spreadsheet14/22

One AI helper

requests · Request #388

youSummarize and draft

claudeTwo hedge trimmers for crew 2. No vendor quote yet.

claudeDraft: "Can you attach the Ewing quote?"

✓ Edited and posted by Marco · ai.draft_used

Copy · summarize and draft
Add Summarize and draft: a server action sends the request, minus personal data, to Claude through AI Gateway. A person edits and posts the draft.

Full prompt

Copy this entire prompt into Claude Code.

Read TOOL-SPEC.md, section AI helper. Add a Summarize and draft button to the request page for approvers and admins. Stop after each step.

1. Install the AI SDK with npm install ai. Ask me to create an AI Gateway API key in the Vercel dashboard and add it to .env.local as AI_GATEWAY_API_KEY myself. Wait until I tell you it's done.
2. Write a server action that checks the role through lib/requests.ts, loads the request and its timeline, and calls generateText through AI Gateway with a "provider/model" string. Check the AI Gateway model list for the current Claude Sonnet model ID instead of guessing. Send only the request fields and notes: no emails, no user IDs.
3. Ask for a three-line summary (what, why, what's missing) and a short, friendly draft reply to the requester. It must not invent anything that isn't in the request.
4. Show the draft in an editable box. Nothing is saved until a person clicks Post reply, which saves it as a comment event in request_events. Log ai.draft_used or ai.draft_discarded. The AI never changes a status.
5. Use a 15-second timeout and a plain error message on failure. Show me a draft for one imported request.

vercel.com/docs/ai-gateway

Ship AI · TalksReplace the Spreadsheet15/22

The AI drafts. You decide.

AI SENDS IT

A reply nobody read.

AI DRAFTS IT

A person edits, then posts.
The decision stays human.

Ship AI · TalksReplace the Spreadsheet16/22

Protect it on the server

claude · ~/requests

youAs a crew lead, open request 12. It's someone else's.

404 from the page and the server action

✓ e2e/access.spec.ts · 7 passed

claudeEvery route goes through lib/requests.ts.

Copy · server checks and the access test
Check every page, action and route for a server-side role check, prove row-level access and the Permissions table with a Playwright test.

Full prompt

Copy this entire prompt into Claude Code.

Read TOOL-SPEC.md, sections Permissions, Rules and Done when. Review the app like a curious person on the team would. Stop after each step.

1. List every page, server action and route handler. Confirm each one checks the session and role on the server, through lib/requests.ts, before loading or changing data. Hiding a button doesn't count. Fix any that don't.
2. Confirm row-level access: a requester asking for someone else's request by ID gets a 404, from the page and from every server action.
3. Confirm the Permissions table: a requester can't approve, an approver can't approve over $2,500, add people or import, and nobody can approve their own request.
4. Check for playwright.config.ts. If it's missing, tell me to run npm init playwright@latest myself and wait until I tell you it's done. Write e2e/access.spec.ts covering steps 2 and 3, plus a signed-out visitor. Read test account emails and passwords from environment variables I'll add to .env.local myself. Never write real credentials into the test.
5. Run npx playwright test and show me the result.

playwright.dev/docs/auth

Ship AI · TalksReplace the Spreadsheet17/22

Only the team gets in

Vercel · Settings · Deployment Protection
STANDARD PROTECTIONVercel Authentication: on
Previews: your Vercel team only
Production: the app's own sign-in

Available on every Vercel plan.

01

Previews

Locked to your Vercel team by Vercel Authentication.

02

Production

Better Auth sign-in. Sign-up off. Admins add people.

03

All on Vercel?

All Deployments puts Vercel's login in front of everything.

Ship AI · TalksReplace the Spreadsheet18/22

Ship it to the team

claude · ~/requests

✓ 6 of 6 checks under Done when

✓ Pushed · deployed on Vercel

Signed out → sign-in page only

claudeLive. Previews locked to your Vercel team.

Copy · check and ship
Run the checks and tests, push, have me set env vars and Deployment Protection in Vercel, then deploy and check each role on the live URL.

Full prompt

Copy this entire prompt into Claude Code.

Read TOOL-SPEC.md. Get it live for the team only. Stop after each step.

1. Run every check under Done when and npx playwright test. Fix what fails.
2. Create a GitHub repo and push. Confirm .env.local and data/ are not committed.
3. Tell me to connect the repo to a new Vercel project in the dashboard, or run vercel link in my terminal. Wait until I tell you it's done.
4. List the environment variables production needs (DATABASE_URL, BETTER_AUTH_SECRET, BETTER_AUTH_URL set to the live URL, AI_GATEWAY_API_KEY). Tell me to add each one myself with vercel env add <NAME> --environment production, or in the dashboard. Don't print any values. Wait until I tell you it's done.
5. Tell me to open the project's Settings, Deployment Protection, and turn on Vercel Authentication with Standard Protection, so preview deployments are only visible to our Vercel team. Production stays behind the app's own sign-in with sign-up off. Wait until I tell you it's done.
6. Deploy, then help me check the live URL: a signed-out visitor sees only the sign-in page, and each role sees only what the Permissions table says. Give me the live URL.

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

Ship AI · TalksReplace the Spreadsheet19/22

Take it home

THE TALK PAGE

Every prompt,
and this deck.

Open the talk page

Ship AI · TalksReplace the Spreadsheet20/22

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 · TalksReplace the Spreadsheet21/22

SHIP AI DISCORD

Free and open.
Build with us.

Scan to join

Ship AI · TalksReplace the Spreadsheet22/22
01/22