Is this worth building, and how would we know it worked?
Business
Build versus buy, what an agent changes about activation and support load, and the measurements that tell you before the quarter ends.
15 posts
Start here
How to add an AI agent to a mobile app: the complete guide
What an in-app agent is made of, what each of its five pieces costs to own, and the honest path from a first spoken turn to something you can hand to users.
- What typing on a phone actually costs your appPeople type about 36 words a minute on a phone. Here is what the research measures, what it does not, and why the fix is removing the form.Business8 min
- What a checkout screen costs, and what the research measuresThe checkout abandonment numbers everyone quotes, what they were actually measured on, and which reasons a redesign can move.Business8 min
- Using an agent to get a user to first valueOnboarding leaks where people have to type. An agent can collapse setup into one request, and there are four kinds of friction it genuinely cannot touch.Business8 min
- The metrics that tell you an in-app agent worksSeven numbers worth tracking, what each one hides, and why containment is the one that looks best while telling you least about the feature.Business9 min
- Conversational commerce numbers that survive checkingWe opened every source behind the statistics people quote about voice and AI shopping. Here is what held up, what did not, and what nobody has measured.Business10 min
- Build vs buy: what an in-app agent really costs to ownWiring a speech API to a model takes an afternoon. The nine workstreams that turn it into something you can hand to a user do not have an end date.Business10 min
- The business case for an in-app agent, and its missing numberHow to build an ROI model for an in-app agent when the one input that decides the answer has no public benchmark, and which of the levers you can honestly measure.Business8 min
- Deflection is the wrong number: measure whether the task finishedA deflection rate scores a user who gave up the same as one who was helped. What Gartner's own self-service figures show, and what to count instead.Business9 min
- Agents in a travel app: rebooking is the feature worth buildingBooking is already a form. The task an agent is uniquely good at is rebooking under disruption, and it needs four read tools before it can answer anything.Business8 min
- Agents in a logistics app: the driver's hands are the constraintHands-free is a legal requirement in a cab, not a convenience. What a logistics agent should do, how proof of delivery works spoken, and the offline case.Business8 min
- An agent in a healthcare app: booking, refills, and the stop lineThe three patient-facing tasks an in-app agent does well, the escalation line that belongs in code, and the compliance question to settle before any of it.Business9 min
- Agent runtimes for mobile apps: an honest comparison (2026)OpenAI Realtime, LiveKit, ElevenLabs, Vapi and Retell compared on what a mobile team actually chooses between: layer coverage, client SDKs and the write path.Business8 min
- Where in-app agents are being adopted fastestAdoption is running ahead of the English-speaking world in several large markets. What that means for a team shipping an agent outside its home country.Business10 min
- What the first week of real assistant traffic teaches youReal users ask for things no test plan contains. Three questions only live traffic answers, and the metric that looks good while telling you nothing.Business10 min