Perplexity
Step 1 of the onboarding ladder — zero install, exposure to every major model through one tab. Perplexity wraps multiple LLM providers so the choice of engine is a dropdown, not a migration.
It's no longer about search, but delivering the best answers the fastest, in the right context. Finding answers is an essential skill for life and business. The beauty of search introduced by Google is that you don't have to think to interact with the user interface.
Reduce time and energy to achieve valuable outcomes
Prediction
Augmented intelligence is the future of search, where context aware and personalised AI will recognise triggers then act as a personal coach to prompt it's owner to improve OODA loop decisions that lead to living a fulfilled life.
The prompters will become the prompted
Best Practices
Shorten time through: Intention => Search => Decision => Action
Use the free Complexity Extension to add advanced features.
Comet
The Comet browser extends the same tab from ask to act — it operates on pages directly instead of only answering about them. Same browser, one more plane of capability, still zero install beyond signing in. When Comet starts feeling like a ceiling, graduate to Claude Code at Step 2.
Context
- Onboarding Ladder — three-step journey from ask to orchestrate
- Claude Code Onboarding — Step 2, LLM with hands on your files
- LLM Models
- Decisions
- Prompts
Links
Questions
Which engineering decision related to this topic has the highest switching cost once made — and how do you make it well with incomplete information?
- At what scale or complexity level does the right answer to this topic change significantly?
- How does the introduction of AI-native workflows change the conventional wisdom about this technology?
- Which anti-pattern in this area is most commonly introduced by developers who know enough to be dangerous but not enough to know what they don't know?