A search-first assistant — answers grounded in live web results with sources attached.
Pick this whenThe question is about the current state of the world and you want citations rather than recall.
What makes it different
Search-grounded by default, so freshness isn't something you have to ask for
Used in the course as a spec-checker: paste laptop specs, ask which local model variant fits
What it does
Answers current-events and product questions with live sources
Acts as a screenshot-a-problem debugging companion alongside ChatGPT
What it does not do
Common wrong expectationsDoesn't replace a reasoning assistant for long structured work
Where it sits in a stack
Quick grounded lookups during a build, especially hardware and version questions where training data is stale.
ShelfChat assistants · Scraping & data sources
Our status · not-usingWeb search inside the Claude stack covers this.
For your projectsNone pressing.
| Session | Coverage | Moment | What happened |
|---|
| Session 5: Mastering Lead Generation | demonstrated | 1:47:59 | Live cited lookup of current Sales Navigator filter names — the antidote to ChatGPT's stale training data |
| Find a Profitable Niche and Build Your Positioning Statement: the Passion/Profit Matrix, Four Validation Questions, Perplexity-then-ChatGPT Research, and the Master Formula | demonstrated | | Niche research |
| Four Ways to Never Run Out of Ideas: Expertise Mining, the 5-Year Reflection Interview, Audience-Question Mining in Perplexity, and Competitor Analysis | demonstrated | | Audience questions |
| Prompt Engineering for Writers, Part 2: Four Templates - Voice Matching, Hook + CTA, Thought-Leadership Outline, Complex-Topic Simplifier | demonstrated | | Research for the hook template |
| Day 1: The Magic Prompt Formula, a Toolkit Tour, Thinker-and-Doer Data Analysis, the Blind-Men-and-the-Elephant Research Method, and a Living Pitch Deck | demonstrated | | Research; Labs dashboards |
| Day 2: Custom GPTs and Gems, Markdown Prompting, Cloning Your Writing Style, MCP in Daily Use, a Vibe-Coded Calorie Counter, and the Consultant-to-SaaS Road | demonstrated | | Competitor research |
| Vibe Coding for Non-Coders: Pain Point to MoSCoW to Stack, 'Use AI to Build AI' with Grok, and an Audio Note-Taker Built Live on Lovable + Supabase + OpenAI | demonstrated | | Competitors and tool list |
| Perplexity Overview: Live Web Search plus AI Synthesis with Line-Level Citations, Live Data, and Deep Research | demonstrated | | |
| Perplexity Spaces and Templates: a Project Room with Standing Instructions and Your Own Files, and Adapting a Template | demonstrated | | |
| Perplexity Deep Research, Citations and the Model Selector: Three Search Tiers, Back-Checking Every Line, and Choosing a Model | demonstrated | | |
| Perplexity Discover, Personalisation, Multimodal Uploads and Voice: Context About You, Image Analysis, Dictation and Two-Way Voice | demonstrated | | |
| Evaluating AI Research Tools, Part 2: Buyer Personas, Marketing Trends, a Content-Gap Analysis, the Verdict, and Adapting a Proven Prompt | demonstrated | | |
| AI Sprint: The Open Source Playbook — Day 1 (Licenses, Open Weights, and Why Open Isn't Free) | demonstrated | | The live open-source triage tool: n8n check, model-tier lookups, technical-term homework |
| AI Sprint: The Open Source Playbook — Day 2 (Weights 101, OpenCode, and the Subsidy Math) | demonstrated | | The model-council feature being rebuilt; also the assigned lookup tool for technical terms |
| Day 1: What Makes an LLM an Agent - Planning, Tools, Memory, Actions; Five Design Patterns; and Cursor, Antigravity and Claude Code Live | explained | | LLM orchestrator that always searches first |
| Organic Sales Playbook, Part 2: Email List, Lead Magnets, Communities and DMs, SEO Fundamentals, and AEO Citations | explained | | Citation tendencies |
| AI Sprint: Claude Code with Antigravity — Day 1 (Taste as the Moat, the Muscle-and-Mirror Setup, and the Model Council Build) | explained | | The model-council feature being rebuilt — 'charging $200 for this' |
| AI Sprint: Windsurf & Devin — Day 2 (Building Superplexity: Plan with Opus, Execute with Cascade, Review with Devin) | explained | | Sonar (Perplexity's search model) replaces Google entirely — the better-Perplexity built on Perplexity |
| Basecamp 2: Vibe Coding | mentioned | 2:17:21 | Screenshot-a-problem debugging companion alongside ChatGPT |
| Basecamp 3: Introduction to n8n — I | mentioned | 2:11:46 | Paste laptop specs, ask which local model variant fits |
| Office Hours I: Vetting an Idea, Niching Against the Frontier Labs, and Paul's Aircraft-Parts App (PWA, and 'What If I Get Hit by a Bus') | mentioned | | Deep research; guardrail reading |
| Office Hours II: When to Pay for Vercel, Scraping Public Data for Paul's Gold-Pressure App, Audits as a Sales Hook, and Why Distribution Beats Building | mentioned | | Find target companies and people |
| Session 2: How to Plan, Scope and Sell your AI Projects | mentioned | 0:32:42 | 'Where are real estate agents hanging out?' — niche channel research |
| Session 10: Building on Cursor & connect with AI workflows | mentioned | 2:12:11 | The unstick move for any service setup: 'I am trying to do X, I am stuck here' |
| Session 20: Complete LinkedIn Agency Automation — Carousels + Newsletter from One Content System | mentioned | | Sonar API named and declined: 'I didn't find it that great' |
| Session 21: Advanced Data Extraction from PDFs — Parsing, OCR, and the Token-Free Product | mentioned | | Sonar API named on the scraping side of the divide |
| Session 22: Automate Admin Tasks — Advanced RAG (Enterprise 'Internal Perplexity' Built Live) | mentioned | | The interface pattern being cloned ('internal Perplexity') |
| Session 23: Automating AEO/GEO — Audits, the File Layer, and Evidence-Led AI Search | mentioned | | Named among the answer engines ('wrappers like Perplexity') whose bots the file layer admits |
| Founder Stack Ep03 with Shai Krishna: Why Wrappers Make AI Slop - CLAUDE.md as the Brain and DESIGN.md as the Art Direction, Founder-Led UGC with AI Avatars, Trial Reels, and Email Journeys | mentioned | 0:27:00 | |
| Day 5: MCP as Concierge — Easy/Medium/Hard Modes, Stacking Servers, Smithery Vetting, and RAG vs MCP | mentioned | | Stacking target and install helper; Perplexity MCP deferred |
| Pillar 2 - Your Specialty: Own One Thing, the Specificity Formula, and the 'Get Ultra Specific' Interrogation Workflow | mentioned | | |
| The LinkedIn Lead-Gen Mindset and Your Ideal Customer Profile: the Funnel, Five ICP Dimensions, Buying Signals, and Deposit Before You Withdraw | mentioned | | Question mining |
| Introduction to AI-Powered Content Creation: the Five-Step Stack, the 70/30 Split, Tool Roles, and a Starter Challenge | mentioned | | |
| Learning Topics: Sessions 1–5 — Foundations to AI Director | mentioned | | Comet agentic browser (toolkit #10) — crawl-your-own-profile pattern feeding the interview rehearsal |
| AI Career Coach: a Custom GPT That Knows Your Resume, and a Gemini Gem Industry Researcher | mentioned | | |
| AI Sprint: Meet GrokBot — Stop Prompting, Start Delegating (One Cloud Computer, a Chief of Staff, Four Specialist Bots, and the Reversible/Irreversible Rule) | mentioned | | Perplexity Computer, same family |
| AI Sprint: The Hermes Agent — Day 1 (Always-On Agents, the Employee-on-Day-One System, and the Self-Improving Ghostwriter) | mentioned | | 'If your question starts with does Hermes—, ask Perplexity' — the training-wheels boundary |
| AI Sprint: Build Your Own AI Skills - Day 1 (Solve It Three Times Before You Build the Skill, Prompt / Skill / Project Rule, the Video-Restoration Walkthrough, and the Two-Skill Voice-Then-Deslop Pipeline) | mentioned | | Found GitHub video-restoration repos |
| AI Sprint: Windsurf & Devin — Day 1 (Vibe to Agentic: GitHub as Pizza, the Four Spec Concerns, and the IDE Lineage) | mentioned | | The benchmark Superplexity aims to advance |
Perplexity