strAIght talk: AI tips for Amazonians
Your go-to podcast for real conversations about using AI tools at Amazon. Amazonians across different roles share practical techniques you can try the same day. No theory, no jargon—just conversations about what works, what doesn’t, and how to get better together.
Episodes
AI that shops and buys for you: Inside Alexa for Shopping
Alexa for Shopping combines product expertise with personal context to help customers find, compare, and buy what they need. A Senior Manager on the team explains the AI behind the experience and where it's headed next. Guest: Brandon Knapp, Sr. Manager Product Manager Technical, Alexa for Shopping
Turn your doc feedback into an AI tool others can use
What if your documents got VP-level feedback before the actual review? On this episode of strAIght talk, hear how one builder turned a decade of leadership feedback into an AI-powered review tool now used by over a thousand colleagues each week. Guest: Isabela Huggins, Sr. Manager, Ops & Enablement, Global Logistics
She hadn't coded in 25 years. One flight later, she had a live website and a challenge for all of PXT
Beth Galetti, SVP of People Experience and Technology, hadn't written code in 25 years. Then she built a live website with AI on a transatlantic flight and challenged every person in her organization to build something in two hours or less. Over 1,000 did. Guest: Beth Galetti, SVP, People Experience and Technology, Amazon
Sharpen your next big idea with Working Backwards AI
The Working Backwards AI tool was built to be your toughest thinking partner for product ideation. The tool walks you through five customer questions, generates personas who react to your idea, and brings in domain experts to test your thinking. Over half of users say their final idea was different from what they started with. Guest: Phil Nachbar, Principal Product Manager, Wor
Try the barbell method: Your team's AI transformation in two moves
Telling your team to "experiment with AI" without a structure usually leads to scattered pilots that fizzle out. One leader built a model that loads both ends: a dedicated Tiger team reimagining one high-value workflow while the broader org gets protected time to skill up and share what's working. On this episode, our guest walks through the full framework, how the two sides feed each oth
Build an agent for doc reviews: your standard, reviewed automatically.
Reviewing a document against a standard used to mean line-by-line cross-referencing — toggling between the policy and the draft, flagging deviations manually. One team built an agent that takes the first pass, handing back an annotated Word doc with comment bubbles on anything that needs attention. On this episode, the builder shares the full setup, the exact prompts, and one trick that p
Scale your impact and efficiency with three AI workflows you can try today
What if the goal isn't getting through your tasks faster, but using AI to handle them more efficiently so you can focus on higher-impact work? In this episode of strAIght talk, one Amazonian shares how he rethought his daily work and freed himself to lead differently. Guest: Daryl Hammett, Director, Delivery & AI Platforms, AWS ProServe
Understand why using one AI tool sharpens your answers
"Which AI tool should I actually use?" Leo Ohannesian, a product manager on the Amazon Quick team, comes back to strAIght talk with a candid answer: pick one, go deep, and let it learn you. On this episode, he breaks down how Quick's desktop app builds a knowledge graph from your connected tools, learns your working style through procedural memory, and keeps your context fresh through an
Snoop Dogg as an AI judge: The 4-part framework behind Courtroom Chaos
In this episode of strAIght talk, the Amazon Luna team breaks down the four-part "harness" framework they used to turn a simple chatbot into Courtroom Chaos, a live AI-native game with celebrity judges. You'll walk away with a repeatable approach for building AI experiences that feel intentional, not generic. Whether you're prototyping your first AI feature or trying to make an existing o
Try The MIXX: the tool that does your meeting prep — from OP1 to offsites
In this episode, an Amazonian shares how he got tired of watching the best offsite conversations happen by accident, so he built an Amazon Quick app that makes them happen on purpose. The MIXX takes pre-work survey responses and delivers a complete meeting prep packet: who should sit together, where the group already agrees, and where to spend your limited time. Guest: Ma
strAIght talk: 4 AI techniques that work
We went back through every episode of strAIght talk and pulled together the four most essential AI techniques every Amazonian should know. Each one builds on the last, giving you a complete, repeatable approach to getting better results from AI. Whether you're brand new to AI or looking to sharpen your approach, start here.
The one question, asked daily, changed how this VP works, eats, and leads
In this episode, a VP who leads HR for Amazon's global operations shares his personal AI journey: from basic prompts to a daily framework that changed how he runs meetings, helped him lose 20 pounds, and even helped someone in his community build a business plan. His one rule: stay the human in charge. Guest: J. Ofori Agboka, VP People Experience & Technology (PXT) &nb
The AI debate partner technique: One team rebuilt onboarding in 6 weeks
In this episode, Morgan shares how her talent development team used AI not just to code a new product, but to fundamentally rethink what onboarding should look like. What started as a debate with AI led to a six-week rebuild that shifted the focus from task completion to customer delivery. Guest: Morgan Grimes, Sr Manager, Product Management, Amazon eXperience & Upskilling&
AI Solution Jams: 15 minutes to teach, 30 to build. Try it with your team
One team in Global Tax Data used AI to reimagine how they work together — from automating month-end data validation that used to take days, to building an agent that translates code into plain English for compliance reviews. On this episode, members from Amazon’s Global Tax Data team share how "AI Solution Jams" (teach, demo, create) helped them scale AI experimentation across six countri
AWS certifications made easy: Let AI create a custom study plan for you
Carving out hours for exam prep feels impossible when you're juggling deliverables, launches, and meetings. On this episode, Sery Cybulski shares how she used AI to pass multiple AWS certifications with just 30 minutes a day. Her approach: tell AI exactly what you don't know, let it build a tailored study plan, and when you get questions wrong, feed them back so it adapts to your gaps. N
A rough idea + AI became Kate Spade's concierge — here's how
One team at AWS used AI at every step to build Kate Spade’s AI "gift concierge" — a shopping assistant that asks customers what they need and narrows options through conversation. On this episode, David Dorf shares how they went from concept to live product in 12 weeks. His biggest tip: you don't need a perfect idea. Keep a backlog, present a rough one to AI, and let it research and refin
Don't scrap it, ask it why: How one marketer made five AI agents reliable.
"I built an agent... now what?" Orlando O'Neill built five custom AI agents for his marketing work. On this episode, he shares how he makes them reliable: asking agents to diagnose their own mistakes, fixing issues permanently with steering files, and running weekly reviews to improve them over time. His biggest tip: when your agent gets something wrong, don't scrap it. Ask it why, and fi
Cortex Kickstart asked her one question, then built four AI agents
Jackie Pizaña wanted AI to do more than summarize documents. Using an internal guided workflow called Cortex Kickstart, she built four AI agents that track commitments, flag escalations, prep coaching materials, and orient her week. Her biggest tip: lean into one tool, learn it well, and let your confidence build from there.Guest: Jackie Pizana, Senior Manager, Operations Field Talent Acq
8 weeks, no roadmap, and a 50% chance of success. Here's how Kiro helped this PM deliver.
Eight weeks, no roadmap, and a 50/50 shot. Vedran Brozovic shares how he used AI to find the right data, generate technical requirements, and build an hourly forecasting system in weeks—not months. His biggest tip: ask AI questions like you'd ask a colleague, not a search engine. Guest: Vedran Brozovic, Product Manager, Automated Profitability Management
Describe your problem, Amazon Quick builds the fix—try these skills today
Spending your mornings triaging emails and rewriting the same docs? Eric Johnson shares how he uses Quick to turn everyday pain points into automated workflows. Just describe your problem, and Quick’s desktop app builds the solution for you.Guest: Eric Johnson, Principal Developer Advocate, AWS
Not a developer? You can still build real solutions — here's how
You've got the idea. A tracker, a dashboard, a tool that would save your team hours. You just can't code it. Or can you? Two Amazonians share how to go from ideas to working prototypes using agentic coding tools. The secret? You don't need to know code; you need to know how to communicate.Guests: Alex Neier, Software Builder Experience (ASBX) & Curtis Morton, AWS Training and Certific
Your AI questions, answered—with a little help from Alexa
Host Alex Kalish gets a little help from a very special co-host, Alexa, who steps in to ask the questions while Alex tackles your toughest listener submissions head-on. The throughline? Context is king, and Alex's five-step framework will change the way you think about AI.Guest: Alexa, Amazon’s cloud-based voice service available on hundreds of millions of devices from Amazon and third-pa
You're probably using AI like a search engine—here's how to make it your work partner
Stop treating AI like a tool. Start treating it like a partner. Regional Director in Amazon Logistics shares how he transformed his relationship with AI from task assistant to strategic partner and the simple habit that made all the difference. His breakthrough: stop asking AI to complete tasks and start having conversations with it like you would with a colleague.Guest: Joe Hoeksema, Reg
This PM used AI as a career coach—his tips for you to earn new opportunities
Want to think more strategically and accelerate your career growth? Program Manager with Amazon's GoAI team, shares how he uses AI as a personal career coach to prepare for high-stakes meetings, build advocates, and shift from tactical execution to strategic thinking. His approach: create a context document with your role, goals, and priorities, then use AI to help you see what you're mis
One prompt manages emails and slack—here's what it is
Senior Manager AI/ML Specialist from AWS closes all his apps and does everything through AI for one day. The result? Events planned in minutes instead of hours, and a completely new way of working. Ahmed Raafat shares his "napkin test" and the daily prompt that keeps him focused on what matters. Listen to discover how the GenAI Day technique can work for you.Guest: Ahmed Raafat, Senior Ma
16-year Amazonian shares the AI technique he's adopting to build faster
Principal Software Engineer shares how he went from AI skeptic to AI evangelist — and the exact technique that changed his mind. Learn about the prompt-driven development technique that made AI an indispensable partner for building faster.Guest: James Hood, Principal Software EngineerNote: Some tools, resources, and internal references discussed in this podcast may only be accessible
Try this research prompt framework to get sharper, more useful analysis from AI
It took 20 iterations. Now, the prompt framework a program manager from Amazon's Global Corporate Communications team built consistently delivers high-quality research analysis — faster and more precisely than before. Listen to find out how she got there — and how you can apply the same approach to your own research process.Guest: Caitlin Gallagher, Program ManagerNote: Some tools, resour
Want faster AI results? You need to try meta-prompting
Three hundred questions. Generated by AI, not a human. An AI program lead from Amazon's Global Supply Chain Operations discovered that the secret to better AI results isn't writing better prompts — it's asking AI to write them for you. Listen to find out how.Guest: Lavanya Srivastava, AI Program LeadNote: Some tools, resources, and internal references discussed in this podcast may only be
Aza can handle tasks for you: Aza's AI agent explained
Many people use AI like a search engine. But AI agents can do things — find information, manage requests, and take action on your behalf. In this episode we break down what makes agents different and how to put them to work, to see what's possible.Guest: Rashi Dixit, Principal Project ManagerNote: Some tools, resources, and internal references discussed in this podcast may only be accessi
How to make AI give you exactly what you need, not everything it knows
Three pages of text when you needed three bullet points. Sound familiar? An Ops Tech Solutions leader cracked the code on getting AI to give you exactly what you asked for — no more, no less. Listen to find out how guardrails and constraints can fix that.Guest: Connor McIntyre, Ops Tech Solutions LeaderNote: Some tools, resources, and internal references discussed in this podcast may only
Learn the 3-question technique that makes AI your thought partner
Forty hours saved. Insights he never would have found on his own. An Amazon Robotics facilitator discovered that asking AI the right questions — and letting it ask some back — changed everything. Listen to find out how the 3-question technique can work for you.Guest: Josh McCay, Amazon Robotics Onboarding Academy FacilitatorNote: Some tools, resources, and internal references discussed in
The context document technique: How you can get better AI results in minutes
A few minutes of setup, dramatically better AI results. An AI Integration Lead built a simple context document that transformed how AI understands his role — and you can do the same. Listen to learn how to create yours.Guest: David Metzger, AI Integration LeadNote: Some tools, resources, and internal references discussed in this podcast may only be accessible to Amazon employees. Disclaim
Recommended
زن بودن
Medicine with Meaning
Yours Truly Johnny Dollar Collection
Take Back Your Health®
CBS Radio Mystery Theater | Old Time Radio
Solved Murders - True Crime Stories
紐約鳥｜New York Aperture
The Swerve Podcast: Obscure Topics | Conspiracy Theories
The Bread and Banter Podcast
The Church of What's Happening Now: The New Testament
Busted Open
Deadline: White House
