You pick up your phone to do one thing, and five minutes later you cannot even remember what that thing was. That is not just “bad discipline” or a modern character flaw. It is the result of deliberate product design, engagement metrics, and relentless experimentation that turns curiosity into habit.

We walk through how big tech measures engagement in the real world, from daily active users (DAU) and monthly active users (MAU) to the DAU/MAU ratio and frequency metrics like 3D7 and 4D7. We also unpack why “engagement” looks different depending on the product: endless scrolling and sharing on social apps versus conversion actions on ride sharing, ecommerce, and travel. Once you see the scoreboard, you start to understand the game.

From there, we get into the machinery: A/B testing and experimentation at scale. We talk about how test groups are chosen, how companies manage risk when a change might hurt conversion, and why the best teams learn fast instead of clinging to being right. Hugh shares stories where tiny tweaks create massive outcomes, including a change at eBay that generated over $400 million in revenue, plus a startup example where changing a few words increased annual income by hundreds of thousands.

Finally, we explore personalisation and recommendation algorithms, how modern systems read images and video to understand content without hashtags, and why UX can vary across languages and regions. If you enjoy product management, UX design, data-driven decision making, or you are simply trying to reclaim your attention, this one is for you. Subscribe, share the episode with a friend, and leave a review: which app do you most want to put down?

Like, Subscribe, and Follow the Tech Overflow Podcast by visiting this link: https://linktr.ee/Techoverflowpodcast

Send a text

Ever watched an idea go from a sentence to a working app before your coffee cools? We put that thrill to the test. First, we vibe code a meeting cost tracker live—complete with per-person salaries and a live ticker—then we hand a broad travel brief to an AI agent and let it work unsupervised. By the time we circle back, it’s assembled sourced itineraries for Florence, aligned to festivals and budgets, and laid out the tradeoffs with surprising polish.

That side-by-side experience anchors a bigger story about where AI is actually moving work. Vibe coding collapses front-end styling, layout, and logic into a single prompt-driven flow that anyone can run. It’s not just faster; it shifts who gets to build in the first place. We talk honestly about the impact inside teams: why some companies push a barbell strategy of senior orchestrators plus junior executors, why mid-level roles feel squeezed, and how IDEs and repositories fit when LLMs become co-pilots rather than toys.

Then we step into agentic AI—the leap from chat to autonomous loops where the model plans, acts, checks, and repeats. We break down sensible guardrails: running agents on a separate machine, limiting permissions to draft-only email, and favouring safer hosted tools like Claude Co-Work before exploring open frameworks. The open ecosystem is powerful and risky; community-built skills extend agents fast, but security vetting matters when malicious add-ons can slip in.

The takeaways are practical and human. Tasks are compressing in time; jobs are reshaping in scope. Routine drafting, summarising, and basic analysis will need fewer hours, while demand surges in cybersecurity, AI safety, and the human-AI interface.

If you'd like to visit our Meeting Cost Tracker, it's available at: https://krensen.github.io/meeting-tool/

The first prompt we used in the show for vibe coding was:

"I want a webpage tool where you enter the number of people, their salary level, and it outputs a live ticker of what the meeting is costing. I want it to be a slick looking webpage that I can access in my browser locally. Once I am happy, I will deploy it to github and turn on the pages feature so I can share it. Remind me how to do that."

And it was refined with:

"Change it so that we can add people individually to the ticker. For each person, allow us to choose their approx salary. Get rid of the average idea, but def keep the coffee tracker!"

The prompt we used with Claude Cowork to book Hannah's Florence holiday was:

"I want you to plan a one week holiday for Hannah. She lives in London and she's interested in going to Florence. She's flexible on dates but wants to go on the edge of the summer. Your task is to search flight and hotel websites and find the best priced combination from London to Florence that will give her a one week holiday. The hotel should be a four-star hotel for while she is in Florence and you should also make sure that hotel reviews show that it is a lively and happening hotel in a cool area.

You can show up for five options that she can choose from. For each option, I want a list of concerts, events, exhibitions, or other types of cultural activities that are interesting within the time window."

If you enjoyed this deep dive into vibe coding and agentic AI, subscribe, share with a friend, and leave us a review telling us the first task you’d trust an agent to handle.

Like, Subscribe, and Follow the Tech Overflow Podcast by visiting this link: https://linktr.ee/Techoverflowpodcast

Send a text

Ever had an ad land so perfectly it felt like your phone must be listening? We open season two by pulling back the curtain on why targeting feels psychic without constant eavesdropping. Smart speakers like Alexa and Siri rely on wake words and short cloud trips to respond, but the real signals come from everyday behaviour: where we go, what we search, how we scroll, who we share with, and even the Wi‑Fi we share at home.

We walk through the mechanics in plain English. Location is a powerhouse signal, honed by teams obsessed with that blue dot. Search keywords and time of day amplify intent. On Instagram and Facebook, taps, pauses, replays and shares teach models what you truly like, while the friend graph links your interests to those closest to you. That’s why you’ll see cold-water swimming after your best friend dives in, or vinyl reissues if your circle is deep into music. No spy mic required—behaviour beats words.

We also talk product realities. Smart speakers started simple, users learned their limits, and even as features improved, trust lagged. Hence those nudges mid-task, a trade-off between discovery and annoyance. Meanwhile, data retention and privacy are shaped by regulators—led by the EU—while companies push for more data to serve the “long tail” of obscure but important questions. We share examples—from kitchen timers to niche medical insights—of how scale turns data into relevance.

Our bottom line is practical and honest. Free apps deliver real value—maps that never get lost, messaging that shrinks distance, feeds that surface what you care about. In return, we hand over behaviour and metadata that make ads sharper and recommendations feel uncanny. If you’re uneasy, start with permissions, location settings and usage habits; the most revealing data is not what you say out loud, but what you do. If you’re comfortable with the trade, enjoy the discovery, eyes open to how it works.

Enjoyed the conversation? Follow the show, leave a review, and share this episode with someone who swears their phone is listening. Your take: fair exchange or too much data—where do you land?

Like, Subscribe, and Follow the Tech Overflow Podcast by visiting this link: https://linktr.ee/Techoverflowpodcast