AI product leader at Google, Author, and community builder making complex AI concepts simple for technical and business audiences. Published author of two books on GPT-3 and Neural Search. Lead and manage an active community of 200K+ AI developers across my social media channels and Unwind AI platform. Creator of Awesome LLM Apps, a #1 top-trending GitHub repository with 80k+ stars featuring practical AI Agents and RAG tutorials.

Building a community of 1M+ AI Developers at Unwind AI, an open AI education platform where 200k+ AI developers today learn to build with AI in just 3 minutes a day:
→ Daily AI news that actually matters
→ Code-first tutorials on AI Agents, RAG and LLMs
→ Open-source AI Agent and RAG apps you can use today with full code implementation

Author of books on: 
→ "GPT-3: The Ultimate Guide To Building NLP Products With OpenAI API"
→ "Neural Search - From Prototype to Production with Jina"

Previously:
→ Built Tenstorrent's developer community from scratch & launched first generation of AI hardware products from AI Accelerator cards to AI Desktop Workstations.
→ Built AI systems for Wall Street hedge funds @Arcesium (DE Shaw)
→ Led data initiatives at 256 Network
→ Tech Leaders Fellow @Plaksha

I share daily tips and tutorials on:
→ Building production-ready LLM apps
→ Implementing RAG systems
→ AI Agents and opensource agentic frameworks

🤝 Let's connect if you're:
→ Building with AI and need practical guidance 
→ Looking for ready-to-use LLM implementations
→ Want to stay ahead of AI developments and grow your career in AI

Follow me for daily AI insights and tutorials on AI Agents, RAG and LLMs.

We just ran the biggest AI Agent course ever 🤯

Here's the list of all the resources we released from Day-1 to Day-5.

250+ pages of production AI Agent insights. 100% free.

📌 Day 1: Introduction to AI Agents (50 pages)
Most agent demos fail in production. This covers the 5 levels of AI agents, from basic reasoning to self-evolving systems, plus the security and architecture patterns that actually work at scale.

Link: https://lnkd.in/dQSzVjR7

📌 Day 2: Agent Tools and MCP (50 pages)
MCP servers can add new tools without your approval. Your poetry bot suddenly gains purchasing power overnight. This breaks down tool design, the Model Context Protocol, and the security risks hiding in plain sight.

Link: https://lnkd.in/dUztxWDA

📌 Day 3: Context Engineering and Memory (70 pages)
Agents with zero long-term memory treat every session like meeting you for the first time. Learn how to build memory systems that actively curate context, not just save conversations.

Link: https://lnkd.in/dMqjwrqF

📌 Day 4: Agent Quality (50 pages)
Traditional QA doesn't work for agents. You can't unit test judgment. This covers the 4 pillars of agent quality (effectiveness, efficiency, robustness, safety) and how to actually evaluate the reasoning process.

Link: https://lnkd.in/dQR3_HkG

📌 Day 5: Prompt to Production (40 pages)
Building an agent takes 2 weeks. Trusting it in production takes 6 months. Learn evaluation gates, circuit breakers, and evolution loops that close the gap between demo and deployment.

Link: https://lnkd.in/dVHSeWmE

With insights from experts including Antonio Gulli, Alan Blount, Michael Zimmerman, Vladimir Vuskovic, Michael S., Kanchana Patlolla, Santiago (Sal) Diaz, Madhurranjan Mohaan, Kimberly Milam, Meltem Subasioglu, Turan Bulmus, Wafae Bakkali, PhD, Dr. Sokratis Kartakis, Gabriela Hernández Larios, Ran Li, Elia Secchi, and Huang Xia 🔥

Kudos to Kanchana Patlolla, Anant Nawalgaria and Polong Lin for the amazing organization 🙌

The best part?
250+ pages. Zero fluff. 100% free.

Repost this so your network doesn't miss it ♻️

Shubham Saboo

AI Product Manager @ Google | Open Source Awesome LLM Apps Repo (#1 GitHub with 80k+ stars) | 3x AI Author | Views are my Own

No alternative text description for this image

I just open-sourced 100+ AI Agent & RAG tutorials that others charge $10,000+ for...🤯

100% FREE. 100% Opensource. Zero paywalls.

Here's what 200K+ AI developers are building with these tutorials:

Starter AI Agents (Pick Your First Project):
• AI Blog to Podcast Agent
• AI Travel Agent (Local & Cloud)
• AI Data Analysis Agent
• AI Music Generator Agent
• AI Meme Generator Agent (Browser)
• Mixture of Agents

Advanced AI Agents:
• AI Deep Research Agent
• AI Investment Agent
• AI Movie Production Agent
• AI System Architect Agent
• AI Product Launch Intelligence Agent
• AI Home Renovation Agent with Nano Banana

Multi-Agent Teams:
• AI Legal Agent Team 
• AI Game Design Agent Team
• AI Teaching Agent Team
• AI Recruitment Agent Team
• AI Real Estate Agent Team
• Multimodal Design Agent Team
• AI Competitor Intelligence Agent Team
• Multimodal UI/UX Feedback Agent Team with Nano Banana

Autonomous Game Playing Agents:
• AI Chess Agent vs Agent
• AI 3D Pygame Agent
• AI Tic-Tac-Toe Agent

Voice AI Agents:
• Customer Support Voice Agent
• AI Audio Tour Agent
• Voice RAG Agent 

RAG Systems (Every Type Covered):
• Agentic RAG with Reasoning
• Agentic RAG with Embedding Gemma
• Corrective RAG (CRAG)
• Autonomous RAG
• Contextual AI RAG Agent
• Vision RAG
• RAG with Database Routing
• Gemini Agentic RAG

Complete Framework Crash Courses:
• Google ADK Crash Course
• OpenAI Agents SDK Crash Course

Every tutorial includes:
→ Step-by-step instructions
→ Real-world application
→ Opensource code on GitHub

Why am I giving this away for free?
Because I believe the best AI knowledge shouldn't be locked behind paywalls.

Get started in 2 simple steps:
1. Subscribe to Unwind AI (for free): theunwindai.com
2. Star the repo: https://lnkd.in/dW6b_dEn

New AI Agents and RAG tutorials added every week.

P.S. I create these AI tutorials and opensource them for free. Your 👍 like and ♻️ repost keeps me going.

Don't forget to follow me Shubham Saboo for daily tips and tutorials on LLMs, RAG and AI Agents.

AI Product Manager @ Google | Open Source Awesome LLM Apps Repo (#1 GitHub with 82k+ stars) | 3x AI Author | Views are my Own

I just released this AI Agent Course for free what others charge $2,000+ for 🤯

A complete crash course on Google's Agent Development Kit with Gemini 3.

No paywall.
No email gate.
No get link in DM

Just drop everything and learn:
•  Agent creation & structured outputs
•  Tool integration (MCP, LangChain, custom functions)
•  Memory systems (in-memory + SQLite persistence)
•  Multi-agent patterns nobody teaches
•  Sequential, parallel, and iterative agentic workflows

9 tutorials. Real code. Real working examples.

Why free?
Because the best things I ever learned came from strangers who asked for nothing in return.

This is me paying that forward.

The repo already has 80,000+ stars.
80,000 developers who said "finally, someone just GAVE us the thing."

Go build something incredible.

🌟 Open Source GitHub Repository: https://lnkd.in/dW6b_dEn

♻️Repost to share it with your network. And follow me Shubham Saboo for more such tutorials.

Google just launched Code Wiki to turn any GitHub URL into instant docs  🔥

Code Wiki automatically generates, updates, and maintains documentation for your entire codebase using Gemini agent.

No more outdated docs. No more hunting through files for hours.

Here's what it does:
• Scans your repo after every commit and regenerates docs automatically
• Gemini chat that knows your entire codebase end-to-end
• Click any concept and jump straight to the exact code file
• Auto-generates architecture and sequence diagrams that stay synced
• Works with any public GitHub repository

Reading and understanding existing code is one of the biggest bottlenecks in software development.

Code Wiki bridges the gap between learning about the code and actually exploring it.

New contributors can make their first commit on Day 1. 
Senior devs can understand new libraries in minutes instead of days.

The best part? 
100% free in public preview.

Private repo support coming soon via Gemini CLI extension.

Link to try it out in the comments.

AI Product Manager @ Google | Open Source Awesome LLM Apps Repo (#1 GitHub with 78k+ stars) | 3x AI Author | Views are my Own

I just deployed a production-grade AI agent in just 60 seconds 🤯

One command. 60 seconds. That's it

Using Google's Agent Starter Pack created by Elia Secchi. 

Building AI agents is the easy part.

But what follows is a nightmare:
• Setting up infrastructure  
• Configuring CI/CD pipelines  
• Adding monitoring & observability  
• Making it Secure and production-ready

Weeks of work. Dozens of tools. Endless configuration files.

But with Agent starter pack you instantly get: 
• Fully functional agent (ReAct, RAG, or multi-agent)  
• Backend + Frontend ready to go  
• Complete deployment infrastructure  
• CI/CD pipeline configured  
• Monitoring & observability built-in  

Even better:
Already have an agent? Run `enhance` to add production-ready deployment to your existing project.

We're moving from "Can we build AI agents?" to "How fast can we ship them?"

This isn't about prototypes anymore.

This is about getting AI agents into production while your competitors are still wrestling with Terraform configs.

Try it out: The whole thing is open source. 

Zero setup required in Firebase Studio or Cloud Shell.

🌟 GitHub repo: https://lnkd.in/d8jwyAxq

♻️ Repost to share it with your network. And follow me Shubham Saboo for more such tutorials.

Google's Advent of Agents 2025 is now live 🔥

Last month, 1.5 MILLION of you joined the biggest AI Agent course ever on Kaggle. 

Now we are back with another interesting way to learn AI Agents. 

25 days. Zero to Production-Ready AI Agents. 100% free.

Here's what happens EVERY DAY until Christmas:

⚡ One new feature
⏱️ Less than 5 minutes to try
💻 Copy-paste code that actually works
📖 Direct links to docs

No theory. No fluff. Just ship.

What you'll master:
• Gemini 3 (Context engineering, Computer Use, Live API)
• Google ADK (Agent Development Kit)
• Vertex AI Agent Engine
• E2E production templates with Agent starter pack

From quickstart to multi-agent orchestration.
From localhost to production deployment.

The Hub is your permanent archive.
Missed Day 3? Go back.
Need that code from Day 12? It's there.
Building your agent on Christmas Eve? We got you.

👉 https://lnkd.in/dsCF8_Fb

To get started, check out the "Introduction to Agents" white paper, released as part of the 5 Days of Agents with Kaggle.

Read it here: https://lnkd.in/dvuZEDBB

Video intro by Abraham Gomez. A huge thanks to the team building this course for the community Elia Secchi, Alan Blount and many more googlers. 

Day 1 starts now. Let's build AI Agents this December. 

♻️ Repost to share this free and interactive course with your network. And follow this space to stay updated for what's to come in the 25 days.

We just open-sourced how to build Deep Agents with Gemini 3 and ADK 🤯

And it's already live in Agent Garden.

Production-ready. Open source. Deploys in one click.

This isn't another cool demo, it's the real agent recipe that you use in production.

Most agent demos are party tricks.
Cool demos but useless in production.

They execute tasks blindly and hope for the best.

Deep agents actually think:
• Build a strategic plan before doing anything
• Critique their own work and spot the gaps
• Refine until the output is bulletproof
• Deliver with citations and receipts

It's like having an AI who questions their own assumptions before you have to.
And you stay in control the whole time.

The agent proposes.
You approve, tweak, or reject.
Nothing moves without your sign-off.

Human-in-the-Loop done right.

The stack is clean:
React frontend.
FastAPI backend.
One-click deploy to Cloud Run or Agent Engine.

Agent Garden hosts a collection of many such production-grade agents built with ADK.

Where you can: Explore Agents → Deploy → Test → Make them yours

This isn't a demo.
It's a head start.
Clone it. Ship it. Make it yours.

Link to GitHub repo in the comments.

🥑 AI Product Manager at Tenstorrrent focused on bridging the gap between state-of-the-art software and the specialized hardware built for AI. 

📕 Co-author of "GPT-3: The Ultimate Guide To Building NLP Products With OpenAI API" and "Neural Search - From Prototype to Production with Jina"

🗞️ Run a daily AI newsletter "Unwind AI" that delivers the latest AI developments and best AI tools directly to your inbox.

🤝 Senior AI Evangelist at Jina AI responsible for building the next generation of AI ecosystem for developers to build and deploy multi-modal/cross-modal applications in the cloud.

🤖 Co-founded Kairos Data Labs to minimize the gap between state-of-the-art AI innovations and applied AI applications within organizations. Our mission is to accelerate innovation with the widespread adoption of AI.

👨‍💻 Founding Data Scientist responsible for creating organization-wide data strategies and infrastructure to build & scale the data science and machine learning vertical within Arcesium (The DE Shaw Group). Built state-of-the-art AI solutions in the area of post-technology services for the biggest hedge funds of the world.

💵 Lead the data initiative at 256 Network, to build a data-driven ecosystem of global decision-makers investing in the startup ecosystem.

📈 Part of the founding cohort at Plaksha's Tech Leaders Fellowship (https://plaksha.org/techleaders)

🤝 Let's Connect: Follow me to stay on top of what's happening in the AI world. Your next insight or inspiration is just a connection away.

Văn Trần

Build a multi-agent AI team with Gemini 3 and code execution using Google ADK 🤯

100% Open Source code. Production-ready that you can deploy today.

A retail location agent team that run 7 specialized AI agents in sequence.

And Agent 4? It writes and executes Python code autonomously.

Here's what blew my mind:

This isn't a demo. It's a production-ready multi-agent pipeline.
Agent 1: Extracts business type and location
Agent 2: Web search for market demographics
Agent 3: Maps competitors via Google Maps API
Agent 4: Writes Python → Runs it → Debugs → Iterates → Returns scores
Agent 5: Extends Strategic recommendations
Agent 6: Generates executive HTML presentation
Agent 7: Creates visual summary

Input: "I want to open a coffee shop in Sunnyvale Downtown"

Output 4 minutes later:
✅ Full market analysis
✅ Competitor density map
✅ Location viability score (calculated, not guessed)
✅ Strategic recommendations
✅ Executive presentation + infographic

The code execution part in ADK just amazing.

When an agent can execute code, it doesn't guess.
It calculates.
It verifies.
It iterates until correct.

Real APIs. Real code. Real deployment.
- Google Maps Places integration with live web search
- Generative UI with AG-UI by CopilotKit
- Python code execution with error handling
- Deploy to Cloud Run or Vertex AI Agent Engine
- Open source, production-ready

All autonomous. All validated. All production-ready.

Kudos to Lavi Nigam, Alan Blount, Enrique Chan and Ivan 🥁 Nardini for this example.

This is Day 7 of 25 in Google Cloud's Advent of Agents.

👉 https://lnkd.in/dsCF8_Fb

Missed previous days? The archive is live. Catch up anytime.

♻️ Repost to share this free and interactive course with your network. And follow this space to stay updated for what's to come.

CopilotKit

Building Agent Development Kit (ADK) | ML Engineer @ Google

PM <- Tech Lead - Web, FP, OS, ML, DA, & moarrr letters

Google Cloud AI/ML DevRel | Vertex AI dude | Open Models, Ray & Agents | Startup Mentor | AI Champion Innovator

Taesun Y.

Introducing Gemini 3 Pro, the new standard for multimodal understanding.

It's not just incrementally better, it's a different category of model. It beats Claude Sonnet 4.5, GPT-5.1 and Gemini 2.5 on almost every benchmark.

I've been testing it for 3 weeks. My first reaction was "wait, that shouldn't be possible."

From analyzing video streams in real-time to solving graduate-level physics, Gemini 3 Pro represents a generational leap in reasoning and capability.

Here is what makes Gemini 3 Pro a huge deal:

🚀 Best model in the world for multimodal understanding: It doesn't just read text, it natively understands video, audio, and code with unparalleled clarity.

🧠 SOTA at complex reasoning: It dives deeper into ambiguous problems, untangling complex logic that stumps other models.

🛠️ Insanely good at agentic tool use & vibe-coding: A force multiplier for developers. Whether it's one-shot prototyping or navigating complex codebases, its "vibe-coding" capabilities allow you to build faster than ever.

⚡ Great at zero-shot generation: Exceptional instruction following that nails the output on the first try, without the need for endless prompt engineering.

🏆 Tops the charts: #1 on the LMArena Leaderboard (1501 Elo), Humanity’s Last Exam, and GPQA.

💬 More direct and factual: It cuts through the noise - delivering concise, factual answers with significantly reduced hallucinations and sycophancy.

Link to the blog in the comment!

AI Product Manager @ Google | Open Source Awesome LLM Apps Repo (#1 GitHub with 79k+ stars) | 3x AI Author | Views are my Own

Build Google ADK Agents in Antigravity, Cursor, or Gemini CLI in just one command ⚡️

Creating AI agents shouldn't require an hour of battling environment configs. 

You want to code, not config.

We just solved the "Cold Start" problem for the Agent Development Kit (ADK).

Meet the new Agent Starter Pack with IDE Magnet Context. 🧲

If you use the starter pack, you now get a "default-on" ADK cheatsheet baked right into your environment. 

This means your IDE, whether it’s Antigravity, Gemini CLI, Cursor, or Claude Code instantly knows exactly how ADK works. 

Zero hallucination, zero setup time.

Try the new super short mode: 
uvx agent-starter-pack create deep_search --adk

If you aren't using the Starter Pack yet, this is your sign to stop writing boilerplate and start building agents.

Watch Antigravity pick up the context with zero config. It just works.

This is Day 6 of 25 in Google Cloud's Advent of Agents.

👉 https://lnkd.in/dsCF8_Fb

Missed previous days? The archive is live. Catch up anytime.

♻️ Repost to share this free and interactive course with your network. And follow this space to stay updated for what's to come.

Your AI agent is doing too much work.

And that's why it's slow, expensive, and breaks every time you touch it.

I see this everywhere: developers cramming flight booking, customer support, billing logic, and data analysis into ONE agent with a 5000-token god-prompt.

Then they wonder why it hallucinates, costs a fortune, and takes 3 days to debug.

Here's what actually works:
Stop building one agent that does everything. Build 10 agents that each do one thing.

This is the Coordinator/Dispatcher pattern, and it's how smart engineers build AI systems that scale.

The setup is dead simple:
- ONE coordinator that routes requests
- TEN specialists that execute tasks

Think of it like a hospital. The triage nurse doesn't perform surgery—they send you to the right specialist.

Here's what it looks like:

User: "Book a flight to Paris"

❌ Most teams: Bloated agent with flight logic + hotel logic + weather logic + currency conversion → 5000 tokens → $0.015/call → slow as hell

✅ Smart teams: Coordinator routes to FlightAgent → focused specialist → 1000 tokens → $0.003/call → instant

The math:
Two targeted 1000-token calls cost 60% less than one bloated 5000-token call.
Scale that to 100K requests and you just saved $900/month.
But cost isn't even the point.

The real wins:
• Your BillingAgent breaks? Doesn't touch SupportAgent
• Need to add a feature? Add a specialist, don't rewrite the god-prompt
• Debugging? Check one agent, not 47 if/else branches
• Each agent has ONE job and actually does it well

The tradeoff:
You make more API calls. That's intentional.

Just like microservices vs monoliths - the coordination overhead is worth the operational sanity.

If you've ever written this in your system prompt:

"If the user asks about billing, then... else if they ask about support, then... else if..."

You need this pattern.

The bottom line: Specialists beat generalists.

Your agents should work like a team, not like one exhausted developer wearing 10 hats.

Stop building god-agents. Start building teams.

_____
♻️ Repost to share this with your network. Follow me (Shubham Saboo) for insights and tutorials on AI Agents and RAG.

Rohan Routh

Watch an AI agent write code, launch browser, and click through your app to test features - completely autonomously 🤯

Google just launched Antigravity, an agentic IDE where AI agents don't just write code - they launch browser, click through your UI, run tests, and verify features actually work. All without you even touching the keyboard.

Key capabilities:
• Multi-surface autonomy: Agents work across editor, terminal, and browser simultaneously. They write code, run tests, and verify their own work.
• Asynchronous development: Spawn multiple agents to work on different tasks in parallel while you focus on what matters. 
• Task-level abstraction: No more watching every tool call. See progress at the task level with implementation plans, walkthroughs, and screenshots.
• Built-in verification: Agents don't just write code - they launch your app and test that features actually work in the browser.
• Model flexibility: Choose between Gemini 3, Claude Sonnet 4.5, or GPT models depending on your task.
• Learning system: Agents remember successful patterns and incorporate your feedback to improve over time.

The best part?
It's free during public preview.

Available for Mac, Linux, and Windows.

Download link in the comments!

I've reviewed 100+ production AI agents this year 🤯

The ones that fail share one trait:
They treat context like a junk drawer 😣

Here's what I mean:

Most developers build agents like this:
context = system_prompt + history + rag_results + user_input 

Then they wonder why they're burning cash, hitting token limits, and watching their agent "forget" critical instructions mid-conversation.

The problem isn't your model. It's your architecture.

Google's ADK v1.16 just introduced Context Layers.

Think of it like memory management for your agent's brain:

🧬 Static Layer
Your agent's DNA. System prompts, persona, tool definitions.
Cached once. Reused forever. You pay for it one time—not every turn.

⚡ Turn Layer
Fresh RAG results. UI state. Validation errors.
Injected per-interaction, then discarded.
Steers the model without polluting history.

🧹 Context Compaction
Automatic garbage collection for conversations.
Summarizes old exchanges. Keeps memory. Kills bloat.

The shift? Stop treating context as a string.
Start treating it as a compiled view.

ADK pipelines filter, compact, and format a clean working context—while your raw session state stays structured and durable underneath.

This is how you kill:
→ Latency spirals
→ "Lost in the middle" hallucinations
→ Runaway API costs

The best agents aren't the ones with the biggest context windows.

They're the ones that know what to forget.

This is Day 8 of 25 in Google Cloud's Advent of Agents.

👉 https://lnkd.in/dsCF8_Fb

Missed previous days? The archive is live. Catch up anytime.

Don't forget to check out the "Context Engineering" white paper, released as part of the 5 Days of Agents with Kaggle.

What's your biggest pain point managing agent context? Drop it below 👇

♻️ Repost to share this free and interactive course with your network. And follow this space to stay updated for what's to come.

🗓️ SAVE THE DATE: The November ADK Community Call is next week. 

We are back with our monthly deep dive into the Google ADK. This isn't just a roadmap update; it’s where we break down the technical roadmap, answer your implementation questions, and show you exactly what’s coming next.

This month is packed with major updates to the developer experience (less boilerplate, more building!) and a look at the tools required to take your agents into production.

Here is what you can expect:

🔹 Focus on the Agent, not the Runner: We are stripping away the complexity. We’ll show you how we’ve reduced the boilerplate code needed to test your agents down to a single .run_debug() command.

🔹 Prototype to Production: Best practices for Agent-to-Agent (A2A) protocols and deployment patterns.

🔹 Observability & Evaluation: Building the agent is only half the battle. We are doing a technical deep dive into how to trace execution, run user simulations, and validate your agent's behavior using our latest tooling.

🔹 Context & Plugins: We will also share critical updates on managing state and extending your agent's capabilities with our new plugin architecture.

🔹 Live Demos: See the new .run_debug() method and Time Travel features in action.

🔹 New Agent Resources: A look at the 10 new tutorials from the Kaggle 5-Day Agents Intensive

If you're actively building with or contributing to ADK, get the event calendar to join the technical discussion! 

🗓️ Date: Nov 19th, 2025 (Next Wednesday!)
⏰ Time: 9:30 AM - 10:30 AM PST
🔗 Virtual, links in the comments 

Join us to meet the core team behind ADK and more... Julia Wiesinger, Polong Lin, Alan Blount, Bo Yang, Hangfei Lin, Katie O'Leary, Kristopher Overholt, Ivan 🥁 Nardini 

#OpenSource #AIAgents #ADK #Python

Which desk is your AI agent working at right now?

Look at the image below. It explains why your agents fall apart deep in a conversation.

❌ The Left Side (The Trap): A typical agent at Turn 50. It's drowning in 160k tokens of noise, conflicting instructions, and irrelevant history. It's signal drowning.

✅ The Right Side (The Fix): The same agent with Context Engineering. Ruthless relevance. A single source of truth. Summarized history.

Think of your LLM as a brilliant engineer you’ve hired. By turn 50, you haven't just given them a task. You’ve buried their desk under:

→ 50 tabs of stale data. 
→ Three contradictory rule sets. 
→ Mountains of old API logs.

The engineer isn't incompetent. The workspace is impossible.

I see 160k token windows where 70% is pure noise. You're spending a fortune to make a genius wade through garbage.

The difference between failure and success usually isn't a newer model. It’s a cleaner and smarter context.

Stop asking for a miracle in a digital landfill. Focus on signal over noise.

Full blog link in the comment.

Your AI agent just hallucinated and ruined a 47-message conversation.

Your user's only option? Refresh and start over.

This is broken. And everyone just accepts it.

Here's the thing:

Every other app on your phone has undo. Ctrl+Z is muscle memory. Google Docs auto-saves every keystroke.

But AI agents? One bad response and your entire session state is toast.

Until now.

Google ADK v1.16 introduces Time Travel for agents.

Yes, actual Ctrl+Z for your AI.

Here's how it works:

⏪ Rewind, Don't Delete
The rewind_async feature doesn't just erase chat history. It computes state deltas—the exact difference between "now" and "then"—and restores your agent's variables, memory, and artifacts to that precise moment.

🔀 Fork From Any Checkpoint
Bad response at message 23? Fork the conversation from message 22. Let users retry prompts without nuking everything that came before.

📜 Keep Your Audit Trail
Every rewind appends an event to the log. Nothing gets destroyed. Full history. Complete accountability. Compliance teams can breathe.

What this enables:
→ "Edit message" features without database surgery
→ "Regenerate response" that actually works
→ Crash recovery that doesn't punish your users
→ A/B testing conversation branches from the same checkpoint

You don't just "go back."

You restore the entire world to exactly how it was.

Stop building brittle agents that punish mistakes.

Start building forgiving ones.

This is Day 9 of 25 in Google Cloud's Advent of Agents.

👉 https://lnkd.in/dsCF8_Fb

Missed previous days? The archive is live. Catch up anytime.

Alan Blount, Enrique K Chan, Julia Wiesinger, Hangfei Lin, Shangjie Chen

♻️ Repost to share this free and interactive course with your network. And follow this space to stay updated for what's to come.

Day 5 of Google's Advent of Agents is now live 🔥

Your agent is deployed. But what's it actually doing?

Agent Starter Pack now includes production observability. Zero config required. 

I'm not talking about basic logging.

I'm talking about full production-grade observability that enterprises need. Built-in from day one.

What you get out of the box:

Two levels of observability, automatically configured:

1️⃣ Agent Telemetry 
• Cloud Trace captures every execution
• LLM calls with latency breakdown
• Tool execution timing
• Full conversation flow visibility

2️⃣ Prompt-Response Logging (Auto-enabled)
• Full E2E journey provisioned via Terraform
• Log Analytics + Log Buckets with custom retention
• BigQuery Delta Lake with custom views for easy querying
• No sensitive data in logs - all content written to GCS

Deploy with one command:
uvx agent-starter-pack create my-agent -a adk_base -d agent_engine
make deploy

And here's where it gets interesting:

Most teams spend weeks setting up observability infrastructure. You get it in minutes.

No configuration. No setup. No custom instrumentation. Just deploy and start monitoring.

Everything you need is now live on adventofagents.com:

Step-by-step tutorial. Code samples. Complete documentation on production observability for AI agents.

This is Day 5 of 25 in Google Cloud's Advent of Agents.

👉 https://lnkd.in/dsCF8_Fb

Missed previous days? The archive is live. Catch up anytime.

♻️ Repost to share this free and interactive course with your network. And follow this space to stay updated for what's to come.

Day 4 of Google's Advent of Agents is now live 🔥

It works on my machine to now it works everywhere.

Agent Engine now supports source-based deployment. 

I'm not talking about fragile deployment pipelines.

I'm talking about deploying your source code directly. What runs locally runs in production. Exactly the same.

What you get with source-based deployment:

❌ Pickle errors
❌ Serialization nightmares
❌ Module path headaches

Your code. Your environment. Deployed as-is.

Get started with Agent Starter Pack:

New project:
uvx agent-starter-pack create my-agent -a adk_base -d agent_engine

Already have an ADK agent:
uvx agent-starter-pack enhance --d agent_engine
Then run make deploy

And you are Done.

And here's where it gets interesting:

Most deployment systems force you to package, serialize, and pray it works in production. Agent Engine deploys your source directly.

No translation layer. No environment mismatches. No deployment debugging.

Everything you need is now live on the website: 

• Step-by-step tutorial. 
• Code samples. 
• Complete documentation on source-based deployment with Agent Engine.

This is Day 4 of 25 in Google Cloud's Advent of Agents.

👉 https://lnkd.in/dsCF8_Fb

Missed previous days? The archive is live. Catch up anytime.

Join us for our first office hours tomorrow: https://lnkd.in/dkiqsjcV

♻️ Repost to share this free and interactive course with your network. And follow this space to stay updated for what's to come.

My 2 months at Google. Feeling like 2 years of AI innovation 🤯 

When I joined Google just ~60 days ago, I thought I'd ease into things.

Instead? I've witnessed and contributed to what feels like a DECADE of AI breakthroughs compressed into November alone.

Let me put this in perspective:

🚀 What We Actually Shipped This Month:
• Gemini 3 Pro: Our most capable model yet, now available 
• Nano Banana Pro: Turning ideas into stunning visuals instantly 
• Google Antigravity: Fully autonomous IDE that plans, build and test code
• Agent Development Kit expansion: Now works in Python, Java AND Go fluently
• Vertex AI Agent Builder: Build, Scale and Govern AI Agents 
• WeatherNext-2: Predicting weather disasters before they happen
• SIMA 2:  An AI agent that plays, reasons, and learns alongside you in 3D worlds
• NoteBookLM: Can now generate amazing infographics and slide decks
• Kaggle 5 Days of Agents: one of the biggest ever AI Agent course with ~1.5M learners 

Each bullet represents work that used to take years. And we shipped it all. This month. And I might be missing a lot of things!! 

But here's what really gets me:

We're not just building AI products and models. We're democratizing it.

Gemini 3 enabling people to vibe-code, reason and use it for daily work. 

The ADK ecosystem alone has been downloaded 7 Million times till early Nov.

Our Agent Garden is helping developers with one-click ready-to-use agent templates and recipes. 

And that Kaggle intensive? Taught millions about building AI Agents

Every morning, I walk into the office thinking "What will be the next big thing?"

And every evening, I come across some individuals or a team doing something impossible.

This isn't just about technology milestones. It's about fundamentally reimagining how humans and AI collaborate, create, and solve problems together.

I feel super grateful to be a part of this orgnization filled with the smartest and most humble people. 

To everyone building with our models, products and tools: You're the real heroes. Keep pushing boundaries.

The future isn't coming. We're shipping it. Daily. 🎯

What AI product are you most excited about?
Drop a comment - I'd love to hear what you're building! 💬

🍌 Nano Banana Pro is HERE and I've been secretly obsessed with it for weeks

I've been testing Google's Nano Banana Pro (Gemini 3 Pro Image) for a while, and honestly?

I can't go back to how I used to work. 

Last week, I needed to create a product roadmap visualization for an all-hands. I fed it 14 different inputs: UI screenshots, feature mockups, user journey maps, our design system components and asked for a cohesive infographic.

It didn't just combine them. It understood the narrative. The hierarchy. The flow.

4K output. Perfect text rendering (finally, AI that can spell!). It can even pull REAL-TIME data through Google Search to create factually accurate visuals.

Some mind-blowing capabilities:
→ Mix up to 14 reference images (goodbye, endless revision rounds)
→ Native 4K resolution (print-ready from prompt)
→ Text that's actually readable AND beautiful
→ Real-time data grounding via Google Search
→ Translates text in images while preserving design

Adobe and Figma are already integrating it. Google Antigravity agents can use it directly. This isn't just another image model, it's a creative partner that actually gets it.

Available NOW in Google AI Studio and Vertex AI.

Who's ready to go absolutely bananas? 🍌

taplio

Shubham Saboo's Linkedin Analytics

Shubham Saboo

Performance ScoreShubham Saboo's LinkedIn Performance

What is Shubham talking about?

Shubham Saboo's Best Posts (last 30 days)

Ready to grow your LinkedIn presence?

taplio

.css-6ytdur{background-image:linear-gradient(284deg, rgba(39, 43, 72, 1) 0%, rgba(33, 47, 183, 1) 100%);color:transparent;-webkit-background-clip:text;background-clip:text;}Shubham Saboo's Linkedin Analytics

Shubham Saboo

Performance Score.css-goub6s{font-size:var(--chakra-fontSizes-md);font-weight:500;color:var(--chakra-colors-gray-600);display:block;margin-top:var(--chakra-space-1);}Shubham Saboo's LinkedIn Performance

What is Shubham talking about?

Shubham Saboo's Best Posts .css-1emoo84{font-size:var(--chakra-fontSizes-md);font-weight:400;color:var(--chakra-colors-gray-600);}(last 30 days)

Ready to grow your LinkedIn presence?

Shubham Saboo's Linkedin Analytics

Performance ScoreShubham Saboo's LinkedIn Performance

Shubham Saboo's Best Posts (last 30 days)