Founder Runbook

Ask first

• Which sources may it read? (default your inbox, your texts, and notes from meetings if you keep them; ignore newsletters and automated mail)
• Who counts as someone you owe or who owes you? (default anyone who wrote to you personally in the last 60 days)
• When is a promise stale? (default 30 days, or 60 days if it has no date)
• Where should the list live? (default one page you open each morning)

Needs

• Read access to the sources
• One saved list with these fields for every item: title, who, direction (mine or theirs), source and link, date captured, due date if any, confidence (high or low), status (open, done or dropped) and why it closed
• A scheduler that can run every 15 minutes
• If your assistant cannot read one of these, paste it when it asks. A thinner version still works
• Any password or token is entered by you into your device's secure store, never pasted into a chat or saved in a plain file

Build

1. Every 15 minutes, read messages and notes added since the last run. Pick out sentences where someone commits to do something: "I will", "I'll send", "we'll have it by", "can you send me".
2. Save each as one item with every field above. Mark confidence low if the commitment is vague or the date is a guess.
3. When a later message in the same thread contains the promised thing (an attachment, a link, the words "here it is"), close the item and write why. Never close an item on silence.
4. Mark an item stale after the stale limit and move it to a dropped list, never delete it.
5. Show the list with days waiting, oldest first, amber after seven days. This one list is the source for every other run that needs promises: the morning brief reads its Due from you section from it, and the follow-up run adds each commitment it drafts to it.

Check

• Seed three promises in a test thread; confirm all three appear with the right direction and date
• Send the promised thing; confirm the item closes and says why
• Confirm a vague promise is marked low confidence and a stale one moves to the list of dropped items
• Say whether the writing step ran for real or on sample text. Check that every figure, quote and link matches its source, and drop any that does not

In my version

• Claude Code on a 15-minute schedule, one list I open each morning; my morning brief and my follow-up run both read and write it

Ask first

• What time should it arrive? (default 7am on weekdays, your time zone)
• Which calendars and inboxes count? (default your work calendar and work inbox)
• Which accounts or customers should it watch? (default any that wrote to you in the last 30 days)
• Where should it land? (default a page you open, or a message from your assistant)

Needs

• Read access to your calendar and inbox
• A short list of accounts to watch, or a way to infer them from recent mail
• The promises list, if you keep one. If you have none, build it by pulling "I will" and "I'll send" lines from your last 14 days of sent mail, or paste one in
• If your assistant cannot read one of these, paste it when it asks. A thinner version still works
• Any password or token is entered by you into your device's secure store, never pasted into a chat or saved in a plain file

Build

1. Each weekday before the set time, read today's events, unanswered mail from the last three days, and any change in the watched accounts since yesterday.
2. Write one page with four parts: Today, Needs you, Moved overnight, Due from you. Read Due from you straight from the promises list; do not rebuild it from mail. Keep each part to at most five lines.
3. If a part is empty, leave it out.
4. Put the page where you read it. Never send anything on your behalf.

Check

• Run it once now and confirm each line names a person or an account, not a general remark
• Confirm nothing on the page is more than three days old unless it is a promise
• Confirm Due from you matches the promises list
• Say whether the writing step ran for real or on sample text. Check that every figure, quote and link matches its source, and drop any that does not

In my version

• Claude Code on a weekday schedule at 7am, written to one page I open in the browser

Ask first

• Which accounts and contacts should it watch? (default anyone you emailed in the last 90 days with an open deal)
• How long is quiet? (default 10 working days)
• Where should it reach you? (default a message from your assistant)

Needs

• Any password or token is entered by you into your device's secure store, never pasted into a chat or saved in a plain file
• Read access to your inbox, calendar and an account list
• Permission to read public profiles; never to contact anyone
• If your assistant cannot read one of these, paste it into the chat when it asks. A thinner version still works

Build

1. Each morning, check each watched contact for a reply, a meeting, a job change and a public post.
2. List those quiet longer than the limit, and any job change or relevant post. Count a clear rise or fall in activity as a change of 25% or more against the 60-day average.
3. Add one suggested next step to each line, and leave it as a draft on that contact's existing thread. Never send it.
4. Send nothing on a day with no change. Save each flagged contact with the date, and do not flag the same contact for the same reason again within 14 days.

Check

• Run it against a contact you know changed jobs; confirm it is caught with a source link
• Confirm a quiet contact is listed once, not every day
• Say whether the writing step ran for real or on sample text. Check that every quote and link on the page matches its source, and drop any that does not

In my version

• Claude Code on a daily 8am schedule, a message only when something changed

Ask first

• Which accounts and channels should I watch? (default: only those you name)
• What deserves an alert? (default: a direct ask, decision or blocker needing you)
• When should I check? (default: four daytime sweeps in your time zone)
• Where should alerts arrive? (default: a private channel you choose)
• May I reply for you? (default: no; show the recipient and final words first)

Needs

• Readable work messages and threads
• History of previous alerts
• Evidence that a request was completed
• An agreed private alert channel
• If your assistant can only chat: paste unread messages and recent replies; ask for an action-only list and unsent drafts

Build

1. Read new mail, direct messages, mentions and relevant thread replies since the last sweep.
2. Decide (ask): an ask is a direct request, decision or blocker that names you or reaches you directly. Broadcasts, FYIs and threads where you are only copied stay quiet unless they ask you to act.
3. Decide (outstanding): an ask is open only if no later reply from you or completed action answers it.
4. Decide (repeat): an ask already texted and unchanged is not texted again; one that changed (new deadline, new chaser) is.
5. Deliver qualifying asks privately with the source, the deadline and the next move; show the final recipient and words for approval before any reply is sent.

Check

• Paste a fictional FYI, a direct ask and an already-answered thread; request a dry run that surfaces only the unanswered ask.
• Run the same dry run again: the ask is not repeated.
• Quiet run: a sweep with no qualifying ask sends nothing.

In my version

• Work Gmail and Slack; iMessage alerts
• Texts only when action is needed; sweeps start at 6:10am, 11:35am, 3:10pm and 7:35pm Pacific, aiming at roughly 7am, noon, 4pm and 8pm

Ask first

• How late before a chase? (default 3 days past due)
• What tone? (default warm and short)
• Who must approve? (default you)

Needs

• Read access to invoices and permission to create drafts, never to send
• If your assistant cannot read one of these, paste it when it asks. A thinner version still works
• Any password or token is entered by you into your device's secure store, never pasted into a chat or saved in a plain file

Build

1. Each weekday, list invoices past due by more than the limit.
2. Skip any chased in the last seven days.
3. Write a short chase for each with the number, amount and due date.
4. Leave drafts. Never send.

Check

• Run it on a test invoice; the amount and date match
• Confirm drafts exist and nothing was sent
• Say whether the writing step ran for real or on sample text. Check that every figure, quote and link matches its source, and drop any that does not

In my version

• Claude Code on a weekday schedule, drafts in my mail

Ask first

• Which metrics do you own? (default the five you look at most)
• What counts as unusual? (default beyond 15% of the four-week average)
• Where do the numbers live and what changed log should it read? (a sheet, an analytics tool; a launch or campaign calendar)

Needs

• Any password or token is entered by you into your device's secure store, never pasted into a chat or saved in a plain file
• Read access to the numbers, and a record of what shipped or ran each day
• If your assistant cannot read one of these, paste it into the chat when it asks. A thinner version still works

Build

1. Each Monday, pull the last week and the four-week average for each metric.
2. Flag any beyond the limit. For each, look at what else changed that week and name the most likely cause, marking it a guess.
3. For each likely cause you guessed, write one line saying what would show the guess was wrong, and by when, so the guess can be checked later. Do this only for a metric beyond the limit, never on a quiet week.
4. End with one thing to check. If nothing moved, say so in one line.

Check

• Run it on a past week where you know why a number moved; the likely cause matches
• Confirm a guess is labelled as a guess
• Say whether the writing step ran for real or on sample text. Check that every quote and link on the page matches its source, and drop any that does not

In my version

• Claude Code on a Monday schedule, a note in my docs and a message

Ask first

• What numbers do investors expect? (default revenue, cash, runway, headcount)
• Where do they live?
• Who receives it? (the draft stays with you)

Needs

• Read access to your numbers and notes, or paste them in
• If your assistant cannot read one of these, paste it when it asks. A thinner version still works
• Any password or token is entered by you into your device's secure store, never pasted into a chat or saved in a plain file

Build

1. On the first of the month, pull last month's numbers and the previous update.
2. Write in your voice using last month's structure.
3. State what went well, what did not and the asks, using notes only.
4. Leave it as a draft. Never send it.

Check

• Run it on last month; every number matches
• Confirm the draft says what did not go well
• Say whether the writing step ran for real or on sample text. Check that every figure, quote and link matches its source, and drop any that does not

In my version

• Claude Code on a monthly schedule, a draft in my mail

Ask first

• Which bank accounts count? (default every business account)
• Where do you keep your books?

Needs

• Read access to bank balances and your books, or a pasted summary
• If your assistant cannot read one of these, paste it when it asks. A thinner version still works
• Any password or token is entered by you into your device's secure store, never pasted into a chat or saved in a plain file

Build

1. Each Monday, pull balances and the last 90 days of spend.
2. Work out monthly spend and runway.
3. List what is due in 30 days and what is owed to you.
4. Show the arithmetic so it can be checked.

Check

• Run it on last Monday; figures match your bank
• Confirm it shows the working
• Say whether the writing step ran for real or on sample text. Check that every figure, quote and link matches its source, and drop any that does not

In my version

• Claude Code on a Monday schedule, a page and a message

Ask first

• Which roles are open?
• Where do candidate records live? (default your hiring tool, or the inbox for the role)

Needs

• Read access to the hiring tool and inbox, or paste a list
• If your assistant cannot read one of these, paste it when it asks. A thinner version still works
• Any password or token is entered by you into your device's secure store, never pasted into a chat or saved in a plain file

Build

1. Each Friday, list open roles with counts by stage.
2. List anyone waiting on you and for how long.
3. Flag candidates with no reply in nine days.
4. Never contact anyone.

Check

• Run it on last week; counts match your tool
• Confirm only stalled people are listed as quiet
• Say whether the writing step ran for real or on sample text. Check that every figure, quote and link matches its source, and drop any that does not

In my version

• Claude Code on a Friday schedule, a page in my notes

Ask first

• Which numbers matter most? (default revenue, signups, runway, margin, churn)
• Where do your numbers and notes live?

Needs

• Read access to your numbers and notes, or paste a weekly summary
• If your assistant cannot read one of these, paste it when it asks. A thinner version still works
• Any password or token is entered by you into your device's secure store, never pasted into a chat or saved in a plain file

Build

1. Each Sunday, compare this week's numbers with the last four weeks.
2. Pick the five that an investor would press on: a number that moved against its trend, a risk to runway, a loss, an unfilled role, a margin change.
3. For each, state the figure and your current answer from notes, or say you have none.
4. Never send it. It is for you to prepare.

Check

• Run it on a past week; at least three of the questions are ones you were actually asked
• Confirm an answer comes only from your notes, not invented
• Say whether the writing step ran for real or on sample text. Check that every figure, quote and link matches its source, and drop any that does not

In my version

• Claude Code on a Sunday schedule, a page in my notes

Ask first

• Where are notes from past board meetings?
• Which numbers do they care about most? (default revenue, runway, churn, margin)

Needs

• Read access to board notes and the numbers, or paste them in
• If your assistant cannot read one of these, paste it when it asks. A thinner version still works
• Any password or token is entered by you into your device's secure store, never pasted into a chat or saved in a plain file

Build

1. Three days before the meeting, read the last three meetings' questions.
2. Pull this month's numbers and compare with last month.
3. For each repeated question, draft an answer from the numbers. For each new move in a number, add the question it will raise.
4. Mark any question you cannot yet answer.

Check

• Run it on a past meeting; at least three questions match what was asked
• Confirm each answer's figure matches the source
• Say whether the writing step ran for real or on sample text. Check that every figure, quote and link matches its source, and drop any that does not

In my version

• Claude Code three days before each meeting, a page in my notes