Sep 20, 2026 · 26 min
AI use moves from clever prompts to coordinated systems
7 Ways How We Use AI Is Changing
As AI becomes part of everyday work, the advantage increasingly depends on how people structure context, goals, costs, and collaboration around it.
- 1AI use is expanding beyond prompt engineering into persistent conversations, voice interaction, and goal-oriented workflows.
- 2Context, harness, and loop engineering shift attention from isolated prompts toward systems that guide AI through ongoing work.
- 3Cost management and shared multi-agent systems become central as individuals and teams use AI more continuously.
Don't miss
The episode’s central turn is its move from prompt engineering to context, harness, and loop engineering as the framework for understanding everyday AI use.
The brief
Nathaniel Whittemore frames AI use as an evolution from prompt engineering toward context, harness, and loop engineering—an effort to understand how systems reshape existing work.
The episode follows seven developments, including persistent conversations, voice interaction, and goal-oriented workflows that make AI less like a search box and more like an ongoing collaborator.
As these systems become more capable, the work shifts toward engineering context and loops: deciding what information AI receives, how it acts, and how progress is checked.
The discussion also treats cost as part of the design problem, since continuous AI use changes the tradeoffs around when systems should run and how much complexity they can support.
Shared multi-agent systems extend the shift from individual prompting to team infrastructure, suggesting that the most important unit of AI use may become a coordinated workflow.
What was said on this episode
19 statements · 16 positive · 1 negative · 2 neutral
AI is changing existing work and enabling new kinds of work.
“the reality is that we are all together on this journey figuring out just the best way to use a completely new technology that is changing both how we do our current work and opening up new possibilities of what work we can even do”
Listen at 0:13
Several AI interaction shifts are fundamental and likely to persist.
“I do think that some of these shifts, which I'm going to cover in this show, are fairly fundamental and likely to stick”
Listen at 1:41
AI products are moving toward simpler, more integrated user experiences.
“there is a push towards simplification and integration and user experiences that have less rather than more cognitive decision-making for the end user”
Listen at 2:02
David Herman predicts Meta Muse will win the casual AI market.
“David Herman wrote, I think Muse is going to win the casual AI race”
Listen at 3:37
Claude is moving toward a unified experience replacing fragmented product choices.
“Claude is careening towards an experience where instead of it being fragmented and full of decisions for the user before they even get started, instead a single unified experience”
Listen at 4:25
AI interfaces are entering another paradigm shift.
“it's increasingly clear we're in another paradigm shift moment in my opinion”
Listen at 5:52
Effective context compaction increases the value of persistent AI threads over time.
“with good context compaction, a thread's value increases over time”
Listen at 8:22
Chatbots increasingly coordinate fleets of specialized agents.
“chatbots are increasingly agent fleet managers”
Listen at 10:18
Many conventional apps will become databases or become obsolete.
“apps disappear quickly— many will become databases at best or entirely obsolete at worst”
Listen at 12:01
Agents will become the default interface for personal and professional activities.
“The agent will be the default interface to your personal and professional life”
Listen at 12:06
Voice interfaces become valuable when agents can perform real work.
“Voice plus real work is the combo”
Listen at 16:06
Voice is becoming a major present and future AI interface.
“Voice is the interface of the present and future”
Listen at 16:50
Users are increasingly setting goals for AI instead of writing individual prompts.
“instead of prompting our AIs, we increasingly set goals for them”
Listen at 17:06
Peter Steinberger recommends designing recurring loops rather than prompting coding agents directly.
“you shouldn't be prompting coding agents anymore, you should be designing loops that prompt your agents”
Listen at 17:42
Managing model selection by task will increasingly become an important discipline.
“understanding where different types of models and model capabilities are needed and how to normalize that in your management of your AI is going to increasingly be an important discipline”
Listen at 20:11
2026 will be remembered as the year AI agents became real.
“2026 will be looked back at as the year that agents became real after years and years of excitement”
Listen at 21:02
Teams will need shared agents operating across team contexts.
“we're probably going to need agents that live at the intersection of our teams, not just agents that live in our own little individual worlds”
Listen at 21:46
Multiplayer AI will be a major design problem in 2027.
“multiplayer AI will be one of the biggest design problems of 2027”
Listen at 23:05
Teams can gain an advantage by adopting shared agents early.
“there is certainly some alpha to be had by getting out ahead of that”
Listen at 25:41
Statements are attributed to the speaker as said on the episode and reflect their view at the time, not PodLume's. They are not advice.
Listen to the full episode and explore every guest, topic, and moment on PodLume.