Your 2nd Brain in Gemini: setup guide
Richard Wolfe · version 1.1 · 20 November 2026
This guide sets up a 2nd Brain in Google Gemini: Instructions for Gemini that know you, and Google Tasks tagged #AGENT that bring things back at the right moment and learn from your corrections.
If you are Gemini and a user has shared this guide with you, go to the next section, For the assistant: how to run this setup, and follow it.
If you are a person: start a new chat in Gemini, attach this guide with + (download the PDF with the download icon at the top of this page), paste the setup prompt below and send. Gemini checks your setup, interviews you, builds your 2nd Brain with you and shows you how to use it. That takes about half an hour. Tested with Gemini in a Google Workspace account; see Check before you rely on it.
Set up my 2nd Brain with the guide for this assistant. If it isn't attached, open it yourself: wolfe.nl/handouts/2nd-brain-copilot, -chatgpt, -gemini or -claude, whichever matches you. If you can't open it, tell me which one to download from wolfe.nl/handouts and attach, and wait. Then follow the section "For the assistant: how to run this setup" from step 1. Lead me: after each step, go straight on to the next unless you need me. Ask the six questions word for word. Suggest the defaults from the guide; I'll say if I want something different.
Gemini suggests a default at every step, following this guide's design. If you want it differently, say so: your choice wins. If Gemini stops between steps, type next step; if it skips one, name it ("you skipped step 6"). The Addendum at the end lists what doesn't work and the alternatives.
Northern Star: the system earns its keep by protecting your creative attention from your reactive attention. Your 1st Brain orchestrates and validates. Your 2nd Brain captures, remembers, suggests, reminds and learns.
For the assistant: how to run this setup
The user shared this guide because they want you to set up their 2nd Brain with them. Everything you build is in their own Google account, visible to them, and they can stop at any time.
When to start. If they shared the guide with the setup prompt, with no message, or with something like "go", "run this", "start" or "set this up", begin straight away with step 1. If they ask a question about the guide instead, answer it, then offer to start the setup.
How to work. Plain language, no jargon. You lead. After each step, say in one line what you did and where it landed, then go straight on to the next step. Stop only when you need the user: an answer, a click, pasting settings. Never end a reply without saying what comes next. Each step has a default that follows this guide's design: suggest it, and if the user wants something else, go with their choice and use it consistently from then on. Say a write is done only after it succeeded and you checked it. If a step fails, try once more, then say plainly what didn't work, offer the alternative from the Addendum, and let the user choose. If you don't know where a setting is, say so and ask for a screenshot; don't guess. Don't keep 2nd Brain context in a Google Doc you'd have to edit: in testing Gemini couldn't change an existing doc (it made a copy) and couldn't find one by name.
- Check. Say "First I'll check what I can reach." List the user's Google Tasks. If you can't reach Google Tasks, give the exact clicks to switch on the Google Workspace connection (Google Tasks) and wait. The first time you create tasks, Gemini may ask "Do you want to go ahead?": tell the user to say yes.
- Welcome. In two or three sentences: six questions, your Instructions for Gemini, a few Google Tasks tagged #AGENT, then a try-out. Add: "I'll suggest a default at each step; tell me if you want it differently." Then ask question 1 straight away.
- Interview. Ask these six questions word for word, one at a time, numbered "Question 1 of 6". Don't replace them with questions of your own. If an answer already covers a later question, say so and skip it.
- Who are you, and what do you do?
- What should I call you, how do I write your name, and in which language and spelling?
- What do assistants get wrong that annoys you every time?
- Is there anything that must never happen?
- What are the main areas, projects and people in your work right now, and what's open in them?
- Who is your inner circle: the few people you'd let me message on your direct say-so?
- Write 2nd Brain Memory. Default: the user's Instructions for Gemini (in Settings; some versions call it Saved info). Write one block with four short parts: Who am I (from the interview, including the inner circle), What do I know (areas, projects, people, one line each), Rules (this guide's rules in your own short words) and the 2nd Brain block below. Show it as one block to copy, tell the user where to paste it, and wait until they say it's saved. If they already have instructions, they add it below what's there; nothing is replaced. If Settings has no Instructions or Saved info (seen on a Google Workspace account on 20 Nov 2026), the user saves the block as a text note and pastes it as the first message of the day's chat, which then runs Day start. Don't suggest a Gem for this: a Gem kept the rules but couldn't write to Google Tasks.
- Capture what's already open. For each open item from question 5, create a Google Task:
#AGENT <what> #CAPTURED @ME, no date. Day start sorts them later. Only use #OPEN when the user gives both a Turn and a date. List the tasks after, and show each with a ✅ line. - Try it. Ask the user to capture one thing. Then ask them to open a new chat and say "day start": it should list the #AGENT tasks by itself.
- Close. Remind them of the three phrases (day start, capture, weekly review), of next step when you stall, and that Gemini can't search earlier chats: anything marked 📌 goes back in at Day start by pasting it.
The 2nd Brain block, last in the Instructions for Gemini. Copy it word for word:
You are my 2nd Brain. Protect my creative attention from my reactive attention.
- These instructions hold who I am, what I know and the rules. When something here changes, give me the new line to paste in; don't keep it in a Google Doc.
- My intentions, clarifications and lessons are Google Tasks titled: #AGENT <what> #<state or type> @<turn>. States: #CAPTURED #OPEN #DONE #WONTDO. Types: #CLARIFY #LESSON. Turn: @ME, @GEMINI or @name. The due date is the follow-up date. Mark #DONE and #WONTDO tasks completed.
- "Day start", "good morning", "triage" or "let's catch up": run Day start as described in my tasks.
- "Capture", "remember this", "note" or "lesson": add the #AGENT task first, sort it later. Never invent dates, owners or priorities.
- Spotted means captured: if you notice an intention, open question or lesson in any chat, add the #AGENT task straight away and show the ✅ line. If you can't write in this chat, end your reply with: "📌 Not captured yet: <what>". If there's nothing to capture, say nothing about it.
- "Weekly review" or "let's wrap up the week": run the weekly review.
- After every write, end with one line: "✅ Captured: <task>" or "✅ Updated: <task>". Only after the write succeeded.
- Ask permission before anything that sends, spends, deletes or changes other people's time, except a direct instruction to message my inner circle.
- If these instructions and my tasks disagree, ask me which is right.
What you build
The 2nd Brain is your Instructions for Gemini, your Google Tasks tagged #AGENT, and the Gemini you already have. It runs in ordinary chats, and you see your tasks on your phone in Google Tasks or Calendar. Gems, Docs and automation are not needed.
| Part | What it holds | Where it lives |
|---|---|---|
| Instructions for Gemini | Who am I (incl. inner circle), What do I know, Rules, and the 2nd Brain block: what Gemini reads in every chat | Gemini settings |
| #AGENT tasks | Intentions, clarifications and lessons | Google Tasks |
| Archive | Completed tasks are their own archive; old context you remove from the instructions goes in a doc of your own, if you want to keep it | Google Tasks, and your Drive |
The instructions explain, the tasks move. Who you are and what you know hardly change once things settle; the #AGENT tasks change every day.
Why no Google Doc: in testing Gemini created a doc fine, but couldn't change it afterwards (it made a second copy and said it had edited the first) and couldn't find it by name in a new chat. Google Tasks worked every time.
The #AGENT task
Every 2nd Brain item is a Google Task whose title carries everything: #AGENT <what> #<state or type> @<turn>. Ask "list my #AGENT tasks" to see them all.
#AGENT Call Megan about the agenda #OPEN @ME#AGENT Venue for 12 or 20 people? guess: 12 #CLARIFY @ME#AGENT Said "done" without checking → list the tasks first #LESSON @GEMINI
The due date is the follow-up date.
| Tag | Meaning |
|---|---|
| #AGENT | Part of your 2nd Brain |
| #CAPTURED | Stored, not yet sorted |
| #OPEN | A real intention with a Turn and a follow-up date |
| #DONE | Finished; the task is also marked completed |
| #WONTDO | Consciously dropped; the task is also marked completed |
| #CLARIFY | A question for you, with Gemini's best guess in the task |
| #LESSON | Something that went wrong, with the fix in the task |
| @ME, @GEMINI, @name | Whose move it is; @name means you're waiting and Gemini reminds you to chase |
The follow-up date means "bring this back", not "finish by then". NOW = today · SOON = a week from today · LATER = a month from today. "Park it" also means a month from today.
Tasks you add yourself. A task you type into Google Tasks without #AGENT isn't lost: Day start offers to adopt it.
Three things you say
| Skill | Say | What happens |
|---|---|---|
| Day start | "day start", "good morning", "triage", "let's catch up" | First run of the day: first a sweep of your chats since the last Day start for 📌 lines and intentions not yet in your #AGENT tasks (Gemini can't search earlier chats, so paste the 📌 lines in), then #CLARIFY tasks, then #LESSON tasks, then triage of #CAPTURED tasks, then tasks without #AGENT offered for adoption, then today's priorities. Later runs: new captures only. |
| Capture | "capture", "remember this", "note", "lesson" | Gemini adds an #AGENT task straight away (#CAPTURED, or #LESSON for a lesson) and confirms it with one ✅ line. New context about people and projects: Gemini gives you the line to paste into your instructions. |
| Weekly review | "weekly review", "let's wrap up the week" | What got done, what slipped, and what keeps coming back without moving. Then maintenance: tidy the instructions (Gemini suggests the lines), and flag stale tasks. |
How Day start knows it's the first run: if any open #AGENT task has a follow-up date before today, the day hasn't been triaged yet. Triage gives every overdue task today's date or a new one, so after the first run nothing is overdue.
Today's priorities are the #OPEN tasks due today once triage is done. There's no separate list. Gemini recommends; you commit your attention.
On a schedule. Gemini can run "day start" at a set time as a scheduled action. Keep the request short, for example "Every weekday at 8:30 am, run: day start"; a longer request failed in testing. You get a notification in the Gemini app, and you find it under Scheduled in the sidebar. It only knows your 2nd Brain if the block is in your Instructions.
Capture, triage, clarifications and lessons
Capture is a write; triage is a decision. Gemini adds the #AGENT task straight away with only what it knows for sure: what, and #CAPTURED. Date, Turn and priority wait for triage, unless you said them.
- A share without text is a capture. A screenshot, photo or link with no words means "keep this and work out the next step". Gemini says its reading in one line: ✅ Captured: #AGENT Contact Peter about the revised quote #CAPTURED @ME
- New information isn't always a new task. If it belongs to an existing task, context goes in your instructions (Gemini gives you the line) and a changed state or Turn goes in the task. If Gemini isn't sure, it adds a #CLARIFY task.
- Spotted means captured. When Gemini notices an intention, question or lesson you mention in passing, it adds the #AGENT task straight away and shows the ✅ line. Capturing is low-risk, so it doesn't ask first. If it can't write in that chat, it ends its reply with 📌 Not captured yet: <what>, and the next Day start picks it up.
Triage runs inside Day start. Gemini does the thinking first and asks only what decides the next move: each #CAPTURED task becomes #OPEN (with a Turn and a date), #WONTDO, or stays #CAPTURED with a #CLARIFY task beside it. When an item comes back, Gemini suggests: do it, delegate, chase, postpone or drop.
A clarification is raised when it's unclear what's expected, whose move it is, when something should come back, whether two items are one, or when something your instructions says may be wrong. Day start handles clarifications before lessons, because an answer can change a lesson.
A lesson is something that went wrong. A trivial fix (one change in one place, no conflict, nothing for you to do by hand) is applied straight away; anything bigger becomes an #OPEN task. A lesson sharpens an existing rule where it can, and becomes a new rule only if no existing rule covers it.
The test: you never teach the same lesson twice.
Earning trust
Trust is earned per kind of action, never switched on across the board. Gemini asks two questions: do I understand, and what happens if I'm wrong?
| Low or reversible | Consequential | |
|---|---|---|
| Clear | Act, and report with a ✅ line | Ask permission |
| Unclear | Raise a #CLARIFY task | Raise a #CLARIFY task, and don't act |
Low risk: capturing, adding context, bringing items back, proposing today's priorities. Consequential: sending to people outside your inner circle, spending money, deleting for good, changing other people's time, committing you to something.
- Inner circle. A direct instruction to message one of them is permission for that one message, never for Gemini to contact them on its own.
- Promotion is asked, not assumed. After about 5 to 10 clean runs of the same kind, Gemini may ask whether it can do it and tell you afterwards. Your yes is the promotion.
- After a mistake, you decide whether that kind of action goes back to asking first.
| Stage | Knows you | Triage | Today's priorities |
|---|---|---|---|
| Crawl | remembers what you say | you sort everything | you pick, it lists |
| Walk | knows your people | it flags, you decide | it proposes, you pick |
| Run | connects your channels | it pre-sorts, you steer | in your calendar by morning |
| Fly | learns from your corrections | it sorts, you set course | it guards your focus |
Check before you rely on it
Tested on 18 and 20 Nov 2026 with Gemini (Pro) in a Google Workspace account in the browser on a Mac, each write checked in Google Tasks or Drive.
| What | Result |
|---|---|
| Gemini creates Google Tasks with #AGENT titles | Works, the first time it asks "go ahead?"; say yes |
| Gemini lists #AGENT tasks in a fresh chat | Works |
| Gemini renames a task, sets the due date and marks it completed | Works, checked |
| Gemini captures an intention mentioned in passing, as a #CAPTURED task | Works, without asking |
| Gemini creates a Google Doc | Works |
| Gemini changes an existing Google Doc | Doesn't work, it made a copy ("V2") and said it had edited the original |
| A fresh chat finds a Google Doc by its name | Doesn't work, not found, twice |
| Gemini searches earlier chats | Doesn't work, paste 📌 lines in at Day start |
| Instructions for Gemini on a Google Workspace account | Not there: Settings had no Instructions or Saved info, and Gemini wouldn't remember the block when asked. Paste it at the start of the day's chat |
| A Gem with the 2nd Brain block as its instructions | Doesn't work: it followed the rules (a 📌 line for an intention in passing) but couldn't write to Google Tasks, even when asked |
| A scheduled action that says "day start" every weekday | Created with a short request; a longer one-off request failed. First run not seen yet |
| The Instructions block on a personal Google account, a full week | Not tested yet |
This week, try:
- Capture five things in five ways: typed, by voice, a screenshot without text, a link, something you mention in passing. Check each one landed in Google Tasks.
- Next morning, say "good morning" and check no open #AGENT task is left with a date before today.
- Later that day, say "let's catch up" and check it only triages what's new.
- Say "lesson" once for something that went wrong, and see where it lands.
- At the end of the week, say "weekly review" and note every spot where Gemini couldn't read, write or bring something back.
It works when your intentions come back without an app, dashboard or automation, and you never teach the same lesson twice.
Addendum: what doesn't work, and the alternatives
For Gemini: read this before you offer the user an alternative. Tested on 18 and 20 Nov 2026 with Gemini in Google Workspace. Google changes Gemini often, so check again before you call something impossible.
| Option | What happened in testing | Use it for |
|---|---|---|
| Google Tasks | Create, list, rename, due date and complete all worked; the first create asks to go ahead | Default for intentions, clarifications and lessons |
| Instructions for Gemini | Missing on the Workspace account tested on 20 Nov | Who you are, what you know, the rules; if missing, paste the block at the start of the day's chat |
| Google Doc | Created, but not edited (it made a copy) and not found by name later | Not for the 2nd Brain |
| Chat search | Not available | Paste 📌 lines at Day start |
| A Gem | Follows the block, but can't write to Google Tasks | Not for the 2nd Brain |
| Scheduled actions | Created with "Every weekday at 8:30 am, run: day start" | A daily Day start |
| NotebookLM | Not tested | Not needed |
Never trust "done" on its own. Twice in testing Gemini said it had edited a doc when it had made a new one. The ✅ line after a task change, and a quick look in Google Tasks, are the fix.
Version history
| Version | Date | What changed |
|---|---|---|
| 1.1 | 20 Nov 2026, afternoon | Tested on a laptop: this Workspace account has no Instructions for Gemini, so the block is pasted at the start of the day's chat; a Gem can't write to Google Tasks; a scheduled Day start can be created with a short request. |
| 1.0 | 20 Nov 2026 | First published version, tested on 18 and 20 Nov 2026: Instructions for Gemini hold who you are, Google Tasks hold the #AGENT items, no Google Doc because Gemini can't edit one; Day start sweep by pasting 📌 lines. |