OpenClaw

Enter passcode to access materials

Contact the instructor for access

OpenClaw Workshop 1 / 17

Connect & Automate

Session 3 — Google Channels, Search, & Real Workflows

Google Channels Brave Search Zoom Transcripts Sub-Agents TODO Automation
press arrow to begin
Block 1: Recap — Where We Are 2 / 17
01 — Quick Recap

Sessions 1 & 2 Recap

Session 1: Foundations

  • What OpenClaw is and why it matters
  • Context-privacy tradeoff & CIA Triad
  • Chatbots → Copilots → Agents continuum
  • Emergent cloud deploy demo

Session 2: Launch Your Agent

  • Cloud deploy on Render
  • Local install with Ollama
  • Telegram bot connection
  • Model selection (cloud vs local)
Having trouble launching OpenClaw? If you get permission errors, try: sudo ollama launch openclaw — the sudo gives admin access. Use qwen3.5:9b when it asks which model.
Today: We move from setup to real workflows. You'll build a pipeline that turns any meeting transcript into action items — automatically.
Block 1: Today's Plan 3 / 17
02 — Today's Plan

3 Tools, 3 Use Cases

Today we go from setup to real workflows. First we connect your tools, then build three practical pipelines you can use immediately.

Foundation

Connect Google channels (Drive, Gmail, Calendar, Docs) to your OpenClaw agent

+ Brave Search API

Add web search for real-time research. Combine with your Drive memos for personalized analysis.

+ Zoom / Local Files

Upload transcripts, memos, and docs that give your agent your personal context.

Three Use Cases We'll Build

#Use CaseTools Used
1Meeting notes → parse → delegate tasks to sub-agentsZoom + Google Docs + Gmail
2Digital Twin deal analysis — research Lovable from your perspectiveBrave Search + Google Drive + Docs
3Auto-generate & post to LinkedIn from meeting insightsGoogle Docs + LinkedIn
Block 2: Foundation — Google Channels 4 / 17
03 — Foundation

Connecting Google Channels

Before we build anything, we need to give your agent access to the tools it'll use. We'll use gog — an open-source CLI that connects OpenClaw to Google services.

Google Docs & Drive

Create, read, and edit documents. Upload and download files from Drive. Used for meeting summaries, TODO checklists, and reports.

Gmail & Calendar

Send follow-up emails, share summaries, create calendar events for deadlines, and set reminders automatically.

Setup: Paste This Into Your OpenClaw Chat

download and set up this repo: https://github.com/steipete/gogcli

That's it. Your OpenClaw agent will clone the repo, install gog, and walk you through Google OAuth setup automatically.

Why gog? It's open-source, runs locally, and your credentials never leave your machine. Your agent calls gog commands — gog handles the Google API auth. No third-party middleware.
Block 2: Foundation — Test Connections 5 / 17
04 — OAuth Setup

Google OAuth Credentials

Before gog can access your Google account, you need OAuth2 credentials from Google Cloud Console. This is a one-time setup.

Step 1: Create a Google Cloud Project

Go to console.cloud.google.com/projectcreate — name it anything (e.g. "OpenClaw") and click Create.

Google Cloud — New Project page

Step 2: Enable APIs

Before enabling APIs, make sure your project is selected in the top bar. You should see your project name (e.g. "Demo-OpenClaw") next to the Google Cloud logo.

Google Cloud — verify project is selected in top bar

Then enable each API from the list below. Click each link → click Enable.

Gmail API page — click the blue Enable button

Click each link below to enable that API:

Step 3: Configure OAuth Consent Screen

Go to console.cloud.google.com/auth/branding — enter an app name (e.g. "Demo-OpenClaw"), select your email, and click through all 4 steps then Create.

Google OAuth consent screen — App Information setup

Step 2 (Audience): select External, then click Next.

Google OAuth — select External audience type

Step 3 (Contact Information): enter your own email address, then click Next and Create.

Google OAuth — enter your email in Contact Information

Once complete, you should see the OAuth Overview page. Next: click Create OAuth client.

Google OAuth Overview — consent screen configured, ready to create client

Step 4: Add Yourself as a Test User

Go to console.cloud.google.com/auth/audience — click + Add users and enter the Google account email you want your agent to access. This is the most important step — this is the actual account you're granting the app permission to read and write to.

Google OAuth — add yourself as test user with your email

Step 5: Create OAuth Client

Go to console.cloud.google.com/auth/clients — this is the gateway that lets your desktop app (gog) access your Google account. Click + Create client.

Google OAuth Clients page — click + Create client

Select Desktop app as the application type, give it a name (e.g. "OpenClaw Demo App"), and click Create.

Create OAuth client — select Desktop app and name it

Step 6: Download JSON & Connect gog

After creating, you'll see this dialog. Click Download JSON — this file contains your client credentials. Don't close this dialog before downloading!

OAuth client created — click Download JSON

It should appear like this in your downloads — click Save.

Browser download dialog for client_secret JSON file

Finally, paste this into your OpenClaw chat — it will find the JSON and set everything up for you:

I have downloaded the Google OAuth client credentials JSON file to my Downloads folder. Can you help me find the client_secret JSON file and run gog auth add --client-credentials with it?

Step 7: Connect Your Google Account

Now tell OpenClaw to add your email. Type "can you add [your-email@gmail.com]" in the chat. It will start the Google OAuth flow — a browser window will open for you to sign in and grant access.

OpenClaw — adding email triggers Google OAuth sign-in flow

can you add my-email@gmail.com

A Google sign-in page will open in your browser. Click Continue to grant access.

Google Sign in — click Continue to grant Demo-OpenClaw access

Next you'll see the permissions screen. Check Select all to enable all the APIs you set up earlier, then click Continue.

Google permissions — Select all to grant access to Gmail, Calendar, Drive, Docs

Once successful, you'll see this — gog is now authorized to access your Google Workspace. You're connected!

Success — You're connected. gog is now authorized to access Google Workspace.
You're done! Your OpenClaw agent can now access Gmail, Calendar, Drive, and Docs. Close this browser tab and head back to OpenClaw.
Block 2: Test & Breakout 1 6 / 17
05 — Test Your Connections

Test & Breakout

Let's verify everything works. Copy these test prompts into your agent. Help each other troubleshoot.

Test: Google via gog

Paste this into OpenClaw to verify your Google connection works:

List my next 3 calendar events and summarize any emails I received today about meetings.

What is Brave Search?

Brave Search is a privacy-focused search engine — like Google, but independent. It has an API that lets your OpenClaw agent search the web in real time. This is what powers Use Case 2 (Digital Twin deal analysis).

Step 1: Get a Brave Search API Key

Go to brave.com/search/api and create an account with your email and password.

Brave Search API — create account with email and password
  1. In the dashboard, choose the Search plan (comes with $5/month free credit — about 1,000 searches)
  2. Go to api-dashboard.search.brave.com and generate an API key
  3. Copy the API key — you'll need it in the next step

Step 2: Add Brave Search to OpenClaw

Run openclaw configure in your terminal → select Web tools → enable web_search → choose Brave Search → paste your API key when prompted.

openclaw configure — select Web tools, enable web_search, choose Brave Search

Step 3: Test Brave Search

Paste this into OpenClaw to verify it works:

Search the web for "Lovable dev AI" and give me a brief summary of what the company does.

Follow along: Run both test prompts now. If one fails, raise your hand — we'll troubleshoot together before moving on.
Block 3: Use Case 1 — Meeting Notes 7 / 17
Use Case 1

Meeting Notes → Task Delegation

Take a Zoom transcript, have OpenClaw parse it into structured action items, then delegate each task to sub-agents that handle email, calendar, and docs.

Zoom .vtt
Transcript file
OpenClaw
Parse & extract
Sub-Agents
Email, Calendar, Docs
Done
Tasks delegated

The Parsing Prompt

You are a meeting analyst. I'm going to give you a Zoom meeting transcript. Extract the following in a structured format:

1. Summary (3-5 sentences)
2. Key Decisions (what was decided, not what was discussed)
3. Action Items (format: [Owner] — [Task] — [Deadline if mentioned])
4. Open Questions (things that need follow-up)
5. Follow-ups (who needs to talk to whom about what)

Be specific with names. If no deadline, mark as "TBD". Group action items by owner.

Getting the transcript: Enable "Audio Transcript" in Zoom settings → download the .vtt file after. Or upload any audio to ElevenLabs/Whisper for transcription.
Block 3: Live Demo — Parse & Delegate 8 / 17
Live Demo

Parse & Delegate in Real Time

Here's a sample transcript from a fictional meeting. We'll paste this into OpenClaw and watch the pipeline work.

Sample Transcript (preview)

# 4-minute startup team standup — 4 speakers, 12+ action items WEBVTT 00:00:03.200 --> 00:00:08.100 Alex: Hey everyone, thanks for jumping on. Let's do a quick status check on three things: the landing page, the demo video, and the investor outreach. 00:00:09.400 --> 00:00:16.800 Priya: Landing page is almost done. I'm waiting on the final copy from Marcus — specifically the headline and the pricing section. Marcus, can you get that to me by Wednesday? ... continues for 4 minutes (pilot expansion, dashboard redesign, hiring, conference prep) ... 00:04:04.000 --> 00:04:09.200 Alex: And I'll update the financials by tomorrow, record the voiceover Thursday afternoon, and block the seventeenth for interviews. Let's regroup Friday. Thanks everyone!
  1. Copy the transcript above into your OpenClaw agent
  2. Paste the parsing prompt from the previous slide before it
  3. Review the structured output — did it catch all action items?
  4. Now run the delegation prompt to route tasks to Google Docs + Gmail

The Delegation Prompt

Take these action items and for each one:

1. Add it to a Google Doc checklist with owner and deadline
2. Draft a brief email to each owner summarizing their tasks
3. Create a calendar event for any meetings that need scheduling
4. Flag anything that needs my review before sending

Show me the plan first — don't send anything yet.

Human in the loop: Always review before the agent sends emails or creates calendar events. You want to catch mistakes before they go out.
Breakout 2: Try the Meeting Notes Pipeline 9 / 17
Breakout Room

Try parsing a transcript on your own

Use the sample transcript or bring your own. Parse it, review the output, and try delegating at least one action item.

Open Shared Google Doc Share what worked and what didn't
Block 4: Use Case 2 — Digital Twin Analysis 10 / 17
Use Case 2

Your Digital Twin Analyzes a Deal

Many of you said you want a "digital twin" — an agent that thinks like you. The secret? Give it your past decisions. Load your memos from Google Drive, then the agent researches AND analyzes from your perspective.

Your Memos
Google Drive
Brave Search
Live research
Digital Twin
Your perspective
Report
Personalized

Step 1: Load Your Context

Upload decision memos, past deal notes, or investment criteria to a Google Drive folder. These teach the agent how you think.

Step 2: Analyze as You

The agent reads your memos, researches the company live, then writes the analysis through your lens — not a generic template.

Block 4: Live Demo — Digital Twin 11 / 17
Live Demo

Researching Lovable as Me

I'll show you how I loaded my own decision memos into Google Drive, then asked the agent to analyze Lovable from my perspective.

The Digital Twin Prompt

I'm evaluating a potential partnership with Lovable (lovable.dev — AI-powered app builder). One of our community members works there.

First, read my past decision memos from Google Drive (folder: "Decision Memos"). These show how I evaluate deals — what I care about, what red flags I watch for, and how I weigh trade-offs.

Then, research Lovable using Brave Search and produce a personalized analysis:

1. Company Overview — what they do, size, traction
2. Partnership Fit — how does this align with MY goals and priorities?
3. What I'd Like — based on my past decisions, what would excite me about this?
4. What I'd Worry About — based on my patterns, what concerns would I raise?
5. Comparable Decisions — reference any similar deals from my memos
6. Recommendation — what would I likely decide, and why?

Write this as if you ARE me — use my voice, my frameworks, my priorities. Save to Google Docs.

Try it yourself: Upload 2-3 of your own decision docs or emails to a Drive folder. Then ask the agent to analyze any company through your lens. The more context you give, the more it sounds like you.
Privacy note: Your memos contain your real thinking. Use a local agent for sensitive documents, or create a Drive folder with sanitized examples for the demo.
Block 5: Use Case 3 — LinkedIn Posting 12 / 17
Use Case 3

Auto-generate & Post to LinkedIn

Anna, Geoff, and several of you asked for this in Session 1. Your agent reads your meeting notes, conversations, or ideas — extracts the interesting insights — and drafts a LinkedIn post. Then it actually posts it.

Your Notes
Meetings, ideas, links
OpenClaw
Draft post
You Review
Edit & approve
LinkedIn
Published!

Input Ideas

  • Meeting takeaways & lessons learned
  • Articles or links you found interesting
  • A theme or topic you care about
  • A raw voice memo or rough draft

What the Agent Produces

  • A polished LinkedIn post in your voice
  • Relevant hashtags and formatting
  • A hook that grabs attention
  • Actually posts it to your LinkedIn

The LinkedIn Prompt

I want to write a LinkedIn post based on the following notes from a recent meeting/conversation:

[paste your notes or key takeaways here]

Write a LinkedIn post that:
1. Opens with a hook — something surprising, contrarian, or relatable
2. Shares the insight — what I learned or realized (be specific, not generic)
3. Makes it personal — use "I" voice, include a real detail from the conversation
4. Ends with a question or call-to-action — invite engagement
5. Keep it under 200 words — short posts perform better
6. Add 3-5 relevant hashtags

Show me the draft first. Once I approve, post it to my LinkedIn.

Power move: Chain all three use cases. After a meeting: parse the transcript (UC1), research any companies mentioned through your lens (UC2), and turn the best insight into a LinkedIn post (UC3).
Breakout 3: Build Your Own Pipeline 13 / 17
Breakout Room

Pick a use case and build it

Choose one of the three use cases (or design your own) and run it end-to-end on your agent. Help each other troubleshoot.

Open Shared Google Doc Document what you built and what you learned
Block 6: Key Concepts 14 / 17
07 — Key Concepts

What You Learned Today

ConceptWhat It Means
Channel connectionsGiving your agent access to real tools (Google, Search, files)
Pipeline thinkingBreak any workflow into Input → Process → Output
Structured promptsTemplates that produce consistent, usable output
Digital TwinLoad your memos into Drive so the agent analyzes like you
Real outputDon't just generate text — post to LinkedIn, send emails, create events
Human-in-the-loopAlways review before the agent acts on your behalf
The tools are the same for everyone. The power comes from knowing which ones to connect and how to prompt them.
Block 6: Homework & Next Steps 15 / 17
08 — Homework

Homework & Next Week

This Week's Homework

  1. Record your next real meeting with Zoom transcription on
  2. Run the full meeting notes pipeline (parse → delegate)
  3. Upload 2-3 decision memos to Drive and run a Digital Twin analysis
  4. Turn a meeting insight into a LinkedIn post and publish it
  5. Share your results in the WhatsApp group

Session 4 Preview

  • Voice agents — talk to your AI, not just type
  • Automation triggers — agents that run on schedule
  • Chaining pipelines — output of one feeds the next
  • Your capstone project — build something real
The best AI agents aren't the smartest — they're the ones embedded in your actual workflow.
Q&A 16 / 17
Open Floor

Questions, ideas, show & tell?

Share what you built today. Ask anything. Help each other troubleshoot.

Drop questions in the Zoom chat or unmute
Feedback 17 / 17
Your Feedback

How Was Session 3?

05:00
Breakout Timer
05:00

Have any questions? Drop them in the Zoom chat.