2. Set up and personalize your assistant [GA]
Enable APIs - this is something the bumble admin would do. Lets address that this is not for a participants, since the participants may not have access to google cloud console.
Need to add this as a pre-req to the workshop for cloud admin to complete
Configure Personalization
“Consumer Software & Mobile App Development” is not in the drop down, so they need to select custom then add this
Then they have to close that pop up
3. Configure data connectors [GA]
This is done by the gemini enterprise admin not by the participant. So mention this as a pre-req for the workshop.
4. Basic Interactions with Jira Connector [GA]
First is to authozie the connectors for each participants needs to complete for them to use the jira and github connector, below is the screenshots for that
image-1-jira-authozie.png
image-2-jira-authoziation-page.png
image-3-after-jira-authoziation.png
Do the same for github
Also ask to disable google search when working on Jira or github connectors
image-4-disable-google-search.png
1. Find your Jira Project Key - give guidance on how to open the chat to ask gemini, below is the screenshot for reference
Image-5-jira-list-projects.png
Do the same for other tests as well, like create tasks, comments, update status ect. Also updated relevant screenshots for that accordingly
image-6-jira-create-projects-1.png
image-7-jira-create-projects-2.png
image-8-jira-create-projects-3.png
image-9-jira-comment-1.png
image-10-jira-comment-2.png
image-11-jira-comment-3.png
image-12-jira-status-1.png
image-13-jira-status-2.png
image-14-jira-status-3.png
5. Basic Interactions with GitHub Connector [GA]
To do list commits you need to know the repo name. So lets have a prompt like below to get the repo name.
Before running this need to tell the praticipatn to disable other connectors and have only github.
For all the test get the relevant images and add it accordicnlgy. Below are the screenshots files names.
image-15-github-enable-1.png
image-16-github-list-repo-2.png
image-17-github-list-commit-3.png
image-18-github-list-pull-request-4.png
image-19-github-list-pull-request-summary-5.png
6. Cross-reference documentation with execution [GA]
Under Upload Requirements Document step 2 should be done first “Upload a file named requirements.txt with the following content” so the participant will have the file created in their laptop so they can had it. To create a .txt file on a Mac, use the built-in TextEdit app. Open TextEdit, go to the top menu, click Format > Make Plain Text. Type your text, click File > Save, name your file (ensure it ends in .txt), choose a location, and click. Provide similar instructions for other laptops
Also “In the Gemini Enterprise chat interface, click the + (plus) icon or drag and drop a file to upload.” not relanvat at this stage
After creating the requirement text then open a new chat window, disable other connectors and enable only jira, then Create Sample Data using Gemini then Run the Analysis, that’s when they need to upload the txt file to gemini app. Refer the screenshots of this test below are the file names of the screenshots in order.
image-20-jira-req-txt-1.png
Images for Create Sample Data using Gemini
image-21-jira-create-ticket-2.png
image-22-jira-create-ticket-confirmation-3.png
image-23-jira-create-ticket-done-status-confirmation-4.png
image-24-jira-create-ticket-confirmation-5.png
image-25-jira-create-ticket-inprogress-status-confirmation-6.png
image-26-jira-create-ticket-created-6.png
image-27-jira-create-tinjira-portal-7.png
Images for Run the Analysis
image-28-jira-run-analysis-1.png
image-29-jira-run-analysis-output-2.png
Note “Click on the citations provided in the response to verify which part of the file or Jira ticket Gemini is referencing.” I don’t actually see the citations
7. Analyze sprint backlogs with NotebookLM [GA]
Similarly in this first create the txt file, give instructions for that, then Click Create a new Notebook. Then Upload a file named retro.txt with these mock notes:
Give instructions for generate insights on what to click.
Here are images files of those screenshots
image-30-notebook-lm-output.png
image-31-notebook-lm-mindmap.png
8. Conduct deep research on market trends [Public Preview]
Review the screenshot of the actual test run and update the instruction if anything missing. File name for the screesnhtos image are. Also mention that these take some time to complete so trigger and move to next lab until it’s ready. Also provide details on what to review in the report, review about the
deep-research-1.png
deep-research-2.png
deep-research-3.png
9. Brainstorm with idea generation [Public Preview]
Review the screenshot of the actual test run and update the instruction if anything missing. File name for the screesnhtos image are. Also mention that these take some time to complete so trigger and move to next lab until it’s ready. Also provide details on what to review in the report, review about the
idea-agent-1
idea-agent-2
idea-agent-3
idea-agent-4
idea-agent-5
10. Build the Multi-Step Scrum Master Assistant [Public Preview]
First step is to click on the “Chat Agent”when selecting “New Agent”, since we have a preview option under New Agent for “Workflow Agent” which we are not covering in this section.
Refer to the image scrum-master-1.png
To rename the agent, need to click on the middle box to open the side panel, refer to the image scrum-master-3.png & scrum-master-4.png
Refer image for next step to provide the prompt - scrum-master-5.png
For the step 3 Give it these instructions: it actually creates the agent with google search enabled, also it renamed the agent to “Lead Scrum Master” refer the image scrum-master-6.png. So let’s remove the step 2 to rename the agent to “Bumble-Lead-Scrum-Master” since the prompt renames it, but make sure it always names it “Lead Scrum Master”.
Also inthe prompt ask it to use only jira and github connector not use google search.
Also update rest of the instructions with current agent name instead of “Bumble-Lead-Scrum-Master”
Add Specialized Sub-agents
Step 1
In the instructions mention that the project key was previously searched in the 4. Basic Interactions with Jira Connector [GA] lab step 1
Uncheck the google search and only keep jira
Refer below images for and mae sure to update inthe instructions accordingly
scrum-master-7.png
Scrum-master-8.png
Step 2
In the instructions mention that the repo name was previously searched in the 5. Basic Interactions with GitHub Connector [GA] step 1
Uncheck the google search and only keep github
Refer below images for and mae sure to update inthe instructions accordingly
scrum-master-9.png
scrum-master-10.png
scrum-master-11.png
This prompt is actually searching the public git hub and getting results “Generate the high-priority update for the Bumble project for the past 24 hours.” this is totally wrong. The agent should only look for data from the jira project and github repo i gave. Not sure why.
Refer this screenshot for the output i got - scrum-master-12.png. Below is the actual output
Make sure to update the instructions correctly so that it only search the jira project and github report that was configured in the agent
Generate the high-priority update for the Bumble project for the past 24 hours.
Response complete
Gemini replied
Here is the high-priority daily update for the Bumble project ecosystem over the past 24 hours. [107, 109, 928, 934]
-
🚀 Overall Progress Summary
The past 24 hours saw significant progress in integrating Google’s Bumble Bluetooth stack across downstream tools, notably introducing native Windows support for NXBT
and adding optional BLE pairing transports to smpclient [107]. Additionally, core refactoring in Bumble's AVDTP (Audio/Video Distribution) layers has successfully eliminated resource-locking bugs [928]. Meanwhile, the community is actively tackling high-priority Classic Bluetooth pairing failures and Windows boot-up driver issues [59, 934].
-
✨ Key Achievements & Code Progress (GitHub)
Repository / Project
Contribution
Details
intercreate/smpclient
BLE Transport with Pairing (PR #107)
Added an optional bumble extra (smpclient[bumble]) providing SMPBumbleTransport [107]. This BLE transport drives external HCI USB controllers, supporting secure scanning, pairing PIN flows, and stored LTK encryption [107].
google/bumble
AVDTP In-Use Management (PR #928)
Merged! Avoids explicit stream in_use flag management by delegating to a dynamic property checking if stream state is IDLE [928]. This resolves previous edge-case resource leaks [923].
typenoob/nxbt
Native Windows Support (Issue #4)
Announced a major integration with Bumble enabling native Windows support for NXBT controllers via hci-socket and usb (WinUSB) transports
.
badoo/codeisok
Security Hardening (PR #109)
Enabled the secure flag for authentication cookies in the Login controller to prevent unencrypted session token transmission [109].
-
⚠️ Current Blockers & High-Priority Issues
While no tracking issues were found in Jira for "Bumble", the following high-priority issues are currently impeding progress in the GitHub ecosystem:
Classic Bluetooth Pairing Failures (Issue #59 - kindle-hid-passthrough) [59]
Status: Active / Investigation [59]
Impact: Classic-only Bluetooth HID devices (such as the Logitech K811 keyboard) fail during Simple Secure Pairing (SSP) with an AUTHENTICATION_FAILURE_ERROR (0x05) [59]. Bumble appears to bypass the user pairing delegate entirely [59].
Next Steps: Testing a speculative fix on feature/brcm-bt-support that relaxes pairing config constraints for BR/EDR [59].
Windows Startup Power-On Failures (Issue #934 - google/bumble) [934]
Status: Open [934]
Impact: Bluetooth USB dongles fail to power on during the very first boot on Windows systems [934]. The Intel driver receives a disallowed error (HCI_COMMAND_DISALLOWED_ERROR) during the initial HCI_RESET_COMMAND [934].
-
Would you like me to draft any replies to these active issues or prepare a Confluence summary document of the Windows workarounds?
give me the link for this repo intercreate/smpclient
Response complete
Gemini replied
The link for the intercreate/smpclient repository is:
👉 https://github.com/intercreate/smpclient
intercreate/smpclient repo is not in my repo in mumanoha/gemini-code-review-agent-demo. intercreate/smpclient is a public repo why are you getting me all the public repo
Response complete
Gemini replied
I retrieved results from public repositories because the search query for "Bumble" was executed globally across all of GitHub rather than being restricted to your specific repository (mumanoha/gemini-code-review-agent-demo).
When I initially searched your internal Jira projects and repositories for the project "Bumble", it returned no matches. To ensure I didn't miss any relevant information, my search query broadened its scope to look for any active issues or pull requests containing the keyword "Bumble" globally, which pulled in these public repositories (like Google's bumble library and intercreate/smpclient).
-
🔍 Filtering to Your Specific Repository
If "Bumble" is a branch, a specific folder, or a topic within your repository, I can narrow down the search.
Would you like me to run a targeted analysis specifically on mumanoha/gemini-code-review-agent-demo for any updates or commits made in the past 24 hours instead?
If I use this prompt “Generate the high-priority update for the my projects for the past 24 hours.” I get below output
Refer image scrum-master-13.png
Generate the high-priority update for the my projects for the past 24 hours.
Response complete
Gemini replied
📊 Daily Project Status Report (Past 24 Hours)
-
🚀 Overall Progress Overview
Currently, the projects are focused on resolving critical infrastructure blockers on Google Cloud Platform while maintaining a steady baseline on application services. While there has been no new code merged or committed in the last 24 hours, the active development continues to center around service integration, and the infrastructure pipeline is currently held back by two newly updated high-priority Jira issues
.
-
🛠️ Code Progress & Achievements (GitHub)
There are no new commits or merged pull requests to report for the past 24 hours. The primary active work-in-progress remains:
Repository / PR
Status
Description
mumanoha/gemini-code-review-agent-demo PR #1: feat: Add menu-service application
🟡 Open
This pull request introduces the core menu-service application to the repository.
-
⚠️ Blockers & High-Priority Issues (Jira)
The following high-priority infrastructure issues were updated in the past 24 hours under the ge-bugs project and require immediate attention to prevent further deployment delays on the GCP Migration Strategy
:
Key
Priority
Status
Summary
Impact
GB-5
🔴 High
To Do
IAM permission shadowing in VPC
Conflicting IAM policies between the VPC and GKE cluster are causing intermittent permission denied errors for active services
.
GB-4
🔴 High
To Do
GKE node pool auto-scaling timeout
The GKE node pool is failing to auto-scale automatically, leading to pod scheduling failures under load
.
-
Let me know if you would like me to help assign these blockers or draft a follow-up message to the infrastructure team!
Also not sure if the connectors as to be added in the root agent. I removed the connectors in the root agent and tested it below is the output. Which is the correct congufiration? I am not sure I will let you decided on the correct config
Refer to image - scrum-master-14.png
Generate the high-priority update for the my projects for the past 24 hours.
Response complete
Gemini replied
High-Priority Update: Project GB (ge-bugs)
Here is the summary of P0/P1 (Highest/High priority) issues and blocked tickets in Project GB (ge-bugs) along with their current impact:
1. P0/P1 Issues (High Priority)
GB-4: GKE node pool auto-scaling timeout
Priority: High (P1)
Impact: The GKE node pool is failing to auto-scale dynamically under load. This results directly in pod scheduling failures, threatening application reliability and performance during high traffic
.
GB-5: IAM permission shadowing in VPC
Priority: High (P1)
Impact: Conflicting IAM policies between the VPC and the GKE cluster are causing intermittent "permission denied" errors for services, leading to unstable internal communication
.
2. Blocked Tickets
GB-7: Fix database latency issues
Priority: Medium
Status: Blocked
Impact: Progress on resolving database latency is halted. The ticket is currently blocked while waiting for the infrastructure team to increase IOPS
.
-
I will now hand control back to the root agent to synthesize this update into your unified daily report. Let's make sure this progress is tracked.
I have checked the open Pull Requests in the mumanoha/gemini-code-review-agent-demo repository:
Open Pull Requests:
PR #1: feat: Add menu-service application
State: Open
Review Status: There is currently one review submitted by gemini-code-assist[bot], which has a status of COMMENTED (not CHANGES_REQUESTED). The reviewer provided general code quality, testing, and dependency cleanup suggestions but did not block the PR with an explicit changes-requested status.
Therefore, there are no Pull Requests currently in the "Changes Requested" state.
I will now transfer control back to the root_agent to compile the complete update. Here is your unified daily report for the past 24 hours, highlighting the high-priority Jira blockers and active code progress on GitHub.
I, Gemini Enterprise, have analyzed your active projects and compiled the most critical updates to keep you and your team aligned.
-
🚨 High-Priority Jira Issues & Blockers
There are currently two high-priority bugs active in Project GB (ge-bugs), along with one blocked issue that requires infrastructure intervention.
Issue
Priority
Status
Description & Impact
GB-4: GKE node pool auto-scaling timeout
High
To Do
The GKE node pool is failing to auto-scale under load, resulting in active pod scheduling failures.
GB-5: IAM permission shadowing in VPC
High
To Do
Conflicting IAM policies between the VPC and GKE cluster are causing intermittent service permission errors.
GB-7: Fix database latency issues
Medium
🛑 Blocked
Progress is currently halted. The team is waiting on the infrastructure team to increase IOPS.
-
💻 GitHub Code Progress
Active progress continues on the gemini-code-review-agent-demo repository with one open pull request. There are currently no PRs blocked under a "Changes Requested" status.
PR # & Title
State
Review Status
Key Highlights
#1: feat: Add menu-service application
Open
Commented
Adds the menu-service Quarkus application. gemini-code-assist[bot] provided recommendations to clean up pom.xml, improve JPA mapping, utilize Panache's active record pattern, and expand test coverage.
-
Would you like me to help you draft a follow-up message to the infrastructure team to expedite the IOPS increase for GB-7, or would you like to dive deeper into any of these updates?
11. Build the Resource Impact Analyzer agent [Public Preview]
First step is to click on the “Chat Agent”when selecting “New Agent”, since we have a preview option under New Agent for “Workflow Agent” which we are not covering in this section.
Refer to the image scrum-master-1.png
Instead of Create a New agent > Proceed to builder. Let’s provide the prompt in the chat itself. Refer this screenshot resource-impact-1.png
Once the agent creates the project, need to uncheck the google connector then click preview to test the prompt “Team member ‘Muthu' is out for 3 days. What is the impact?”
Refer to the images and make sure to update inthe instructions accordicngly
resource-impact-2.png & resource-impact-3.png
Once tested click create to publish the agent
12. Advanced: Build and Deploy with ADK [Public Preview]
I took screenshot of these steps, review the screenshot images to make sure the instructions are accutare and also update the screenshot for each steps so it clear
Step 1: Environment Setup
agent-cli-1.png
Step 2: Authentication and Setup
agent-cli-2.png
agent-cli-3.png - this steps a long time
agent-cli-4.png -
Mention in the instructions that cli will ask permission to run commands select “Allow once”
Option B: The Gemini CLI Way (Natural Language)
Refer to the images to update the instructions correctly based on what actually happened in the console. Update the codelab with these screenshots where appropriate and with reliant instructions
Images to review - agent-cli-5.png to agent-cli-9.png
Below is the output in the cli
I've built the Bumble-Ops-Assistant agent for you using the Agent Development Kit (ADK).
1. Agent Implementation
The agent is located in bumble-ops-assistant/app/agent.py. It includes the check_build_health tool which returns a hardcoded "GREEN" status for any environment.
1 def check\_build\_health(environment: str) \-\> str:
2 """Checks the build health for a given environment.
3
4 Args:
5 environment: The environment to check (e.g., 'prod', 'staging').
6
7 Returns:
8 The health status of the build.
9 """
10 return "GREEN"
11
12 root_agent = Agent(
13 name="Bumble_Ops_Assistant",
14 # ...
15 instruction="You are Bumble-Ops-Assistant, an operations assistant. You can check the build health for production and staging environments.",
16 tools=[check_build_health],
17 )
2. Smoke Tests
I performed two types of smoke tests:
* Unit Tests: I created and ran unit tests in bumble-ops-assistant/tests/unit/test_health_tool.py to verify the tool's logic directly.
* Result: 2 passed in 3.03s
* Evaluation Smoke Test: I scaffolded a simple evaluation set in bumble-ops-assistant/tests/eval/evalsets/smoke_test.evalset.json to test the agent's interaction.
* Note: The evaluation run encountered a PERMISSION_DENIED error because the aiplatform.googleapis.com API is not enabled in the cloudshell-gca project, and I do not
have permissions to enable it.
agent-cli-10.png - shows when clicked on open editor and ask the participants to review the files to see what agent cli created, and give explanation on each of the files create by agent cli refer to the documentation for details
Playground testing - provide those steps before deploy and publish.
Refer to thise images to find out the testing and create the instructions accordingly
Images - agent-cli-11.png to agent-cli-15.png
I tried to ask agent cli to create the playground and test it, but i am facing issues.
Session not found: f681747b-c55d-42d6-9324-77f394d0ecb8. The runner is configured with app name "bumble_ops_assistant", but the root agent was loaded from "/home/admin_/bumble-ops-assistant/app", which implies app name "app". Ensure the runner app_name matches that directory or pass app_name explicitly when constructing the runner. The mismatch prevents the runner from locating the session. To automatically create a session when missing, set auto_create_session=True when constructing the runner.
After asking the agent to fix it fixed the permission issues and thighs started working.
13. Deploy and Publish to Gemini Enterprise [Public Preview]
I want to use the natural language to deploy and publish to GE
So keep both the options manual way or natural lang way
I asked deploy the agent and it deployed it to agent engine. Refer to the images to understand the steps and create relevant instructions
Image - agent-cli-deploy-1.png to agent-cli-deploy-4.png
I aksed gemini cli to publish to ge app
I used - Publish to Gemini Enterprise App bumble-workshop-lab-test-1_1778167389086
Refer to images below to understand how this was doen and create the instructions accordingly
agent-cli-publish-1.png to agent-cli-publish-7.png