🧠 All Things AI
Beginner

Project: Research Companion

A general-purpose chatbot is a poor researcher. It has a knowledge cutoff, cannot access live sources, blends information from across its training data without attributing anything, and has no memory of what you researched last week. This project builds a personal research companion — a stack of three specialist AI tools working together that covers discovery, deep reading, and organisation. You will end up with a reliable, repeatable research workflow for any topic. No coding required.

Why Generic Chat Fails at Research

Research needGeneric chat (ChatGPT / Claude)Specialist tool
Live, up-to-date informationTraining cutoff — may be months out of datePerplexity — real-time web search with citations
Source attributionBlends sources — hard to verify any claimPerplexity — numbered inline citations, every claim sourced
Reading your own documentsMay mix uploaded content with training dataNotebookLM — grounded only in what you upload
Academic literatureCannot reliably find real papers or citationsElicit — 125 million academic papers, structured extraction
Continuity across sessionsNo memory of past research threadsNotebookLM notebooks — persistent, topic-specific workspaces
Comprehensive report on a topicPossible but slow and requires careful promptingDeep Research (Perplexity / ChatGPT / Gemini)

Your Three-Tool Research Stack

Each tool does one job extremely well. Together they cover the full research cycle.

🔍

Tool 1 — Perplexity AI (Discovery)

Your starting point for any research question. Perplexity searches the live web and academic sources simultaneously, then writes a structured answer with numbered inline citations you can click through to verify. Every claim links to a real source.

Free tier: Unlimited standard searches, 5 Deep Research queries per day
Pro ($20/month): 500 Deep Research queries per day, GPT-4o/Claude as engine, file uploads
Key feature: Academic mode — searches peer-reviewed sources only (toggle in search bar)
Deep Research: Launched Feb 2025 — analyses 50+ sources per query, builds structured multi-page reports, exports to PDF or Perplexity Pages
Accuracy: 93.9% on SimpleQA benchmark (Feb 2025); 22% faster than ChatGPT Deep Research for comparable queries
📓

Tool 2 — Google NotebookLM (Organisation & Deep Reading)

Your research workspace. Upload PDFs, articles, notes, web pages, and YouTube links. NotebookLM answers only from what you uploaded — it cannot confabulate from training data. Use one notebook per research topic and it becomes a persistent, searchable knowledge base for that subject.

Free tier: Unlimited notebooks, 50 sources per notebook, 1M token context window
NotebookLM Plus ($20/month): 500 sources per notebook, priority access, shared notebooks
Audio Overview: Generates a two-host podcast discussing your sources — now in 80+ languages (Aug 2025 rollout)
New formats (Sep 2025): Choose between Deep Dive, Brief, Critique, or Debate audio styles
Video Overview: Short video summaries of your notebook — 6 visual styles, available in 80 languages
Mind Maps: Auto-generated concept map of all uploaded sources — helps you spot connections
Lecture Mode (testing 2025/2026): Single-host 30-minute lecture from your materials — intended as a class-session replacement
Studio panel: Store multiple outputs (audio, video, mind map, report) per notebook
📚

Tool 3 — Elicit (Academic Literature)

For any question that needs peer-reviewed evidence. Elicit searches 125 million academic papers and returns structured data — not just titles, but key findings, methodologies, sample sizes, and limitations — in a sortable table. Designed for systematic literature reviews without needing a university library subscription.

Free tier: 12 full paper analyses per month
Plus ($12/month): Unlimited analyses, data extraction columns, CSV export
Key feature: Data extraction table — pulls out populations, interventions, outcomes, effect sizes across many papers at once
Use for: "What does the research say about X?" questions where you need real evidence, not AI summarisation

When to Use Each Tool

Research situationBest toolWhy
Quick background on an unfamiliar topicPerplexity standard searchFast, cited, current — gets you oriented in 60 seconds
Comprehensive report you can actually usePerplexity Deep Research50+ sources, structured multi-page output, exportable
Understanding a set of specific documentsNotebookLMSource-grounded — answers come only from your files
Turning dense material into audio for commutingNotebookLM Audio OverviewPodcast-style discussion of your uploaded sources
"What does the research actually show about X?"ElicitReal papers with real data — not AI summarisation
Finding papers related to one you already haveResearchRabbit / Connected PapersCitation network maps — visually explores what a paper cites and is cited by
Deep report with more narrative depth than PerplexityChatGPT Deep Research or Gemini Deep ResearchBetter synthesis and argumentation — slower but more analytical

Build Your Research Companion — Step by Step

Step 1: Set Up Your Tools (15 minutes, one time)

1. Create a Perplexity account — go to perplexity.ai, sign up free. Bookmark the search bar. You will use this every time you start a new research question.
2. Open NotebookLM — notebooklm.google.com (free Google account required). Create one notebook per topic you are researching. Name them clearly: "Sleep science", "Climate policy 2025", "Our company competitor analysis".
3. Create an Elicit account — elicit.com, free tier. You do not need it for every project — use it when a question needs peer-reviewed evidence.
4. Bookmark ResearchRabbit — researchrabbitapp.com, free. Use it when following citation trails from a paper you found through Elicit.

Step 2: The Standard Research Loop

For any new research question, follow this sequence:

StepActionTool
1Ask your question in plain language. Review the cited sources, not just the answer.Perplexity standard search
2Follow up with 2–3 clarifying questions in the same Perplexity thread to go deeper.Perplexity (follow-up mode)
3Save key articles, PDFs, or web pages. Upload them to a topic-specific notebook.NotebookLM notebook
4Chat with the notebook to extract specific information, compare sources, and spot contradictions.NotebookLM chat
5If empirical evidence is needed, run the question through Elicit to find real studies.Elicit
6Add the most relevant papers from Elicit to your NotebookLM notebook.NotebookLM
7Generate a Mind Map or Audio Overview to consolidate your understanding.NotebookLM Studio

Step 3: Perplexity Deep Research (for big questions)

For research questions that need a comprehensive report — a market overview, a technology landscape, a policy comparison — use Deep Research. It spends 2–4 minutes analysing 50+ sources before writing a structured, multi-page response.

When to use it: When a standard search gives you a starting point but you need depth — competitor intelligence, a technology briefing, a policy landscape.
How to trigger it: In the Perplexity search bar, look for "Deep Research" mode below the text input. On the free tier you have 5 queries per day; Pro users get 500.
Export and organise: Export the report as a PDF (or to Perplexity Pages for a public link), then upload the PDF to a NotebookLM notebook to ask follow-up questions against the report content.
When ChatGPT Deep Research is better: For academic reports, nuanced analysis, or longer-form synthesis. Perplexity is faster and cites more sources; ChatGPT Deep Research produces more analytical, essay-quality writing. Use Perplexity for briefings you need quickly; use ChatGPT Deep Research for reports you will publish or share.

Step 4: Build a Persistent Research Library

The real power of this setup is that research accumulates. Each NotebookLM notebook becomes a searchable, queryable library for that topic — and it never forgets.

Naming convention: Create one notebook per project or topic area. Use clear names: "AI Regulation 2025", "Personal Finance Research", "Job Hunt — Industry Background". Do not put unrelated topics in the same notebook.
What to upload: PDFs of key articles, saved web pages (paste URL directly into NotebookLM), your own written notes (paste as text source), YouTube video URLs (NotebookLM extracts the transcript), Google Docs/Slides.
What to ask the notebook: "Summarise the key arguments across all these sources", "What do my sources say about X specifically?", "Are there any contradictions between these sources?", "What are the main gaps or unknowns in my current set of sources?"
Returning to old research: Coming back to a topic weeks later? Open the notebook, read the Mind Map to refresh context, then continue the conversation where you left off. The AI has the full source history available.

Copy-Paste Prompt Templates

Ready-to-use prompts for common research situations.

Initial topic orientation (Perplexity)

Give me a structured overview of [topic]. Cover: (1) what it is in plain language, (2) the main sub-topics or components, (3) the key debates or open questions, (4) the most important recent developments in 2024–2025. Cite your sources for each section.

Deep Research briefing (Perplexity Deep Research)

Write a comprehensive briefing on [topic] as of 2025. Structure it as: (1) Executive summary (3 sentences), (2) Background and context, (3) Current state of the field, (4) Key players and perspectives, (5) Major trends and forecasts, (6) Open questions and controversies, (7) Recommended next sources for deeper reading. Use at least 30 sources.

NotebookLM — source synthesis

Across all the sources in this notebook, what are the 5 most important claims or findings? For each one, tell me which source(s) support it, and whether any other source contradicts or qualifies it.

NotebookLM — gap finder

Based on the sources in this notebook, what important questions about [topic] are NOT answered by what I have uploaded? What additional source types or perspectives would fill those gaps?

Elicit — evidence search

[Paste this into Elicit's search bar] Does [intervention/behaviour/treatment] improve [outcome] in [population]? After Elicit returns papers, add these columns to the extraction table: sample size, study design (RCT/observational/meta-analysis), effect size, and limitations.

Research-to-output summary (NotebookLM or Claude)

I have researched [topic] and gathered [N] sources. Based on this material, write a 500-word summary I can share with [audience — e.g. colleagues / my manager / a general reader]. The summary should: cover the key findings, note any important uncertainties, and end with 3 actionable implications. Do not add information beyond what is in my sources.

What Works Well

Tool specialisation beats one-tool-does-all

Using the right tool at each stage — Perplexity for discovery, NotebookLM for depth, Elicit for evidence — produces far better results than trying to use a single chatbot for everything.

Source-grounding is the key safety feature

NotebookLM's refusal to answer outside your sources is a feature, not a limitation. If it says "I don't see that in your sources", that is useful information — you need to find and upload the relevant material rather than getting a confident hallucinated answer.

Audio Overviews dramatically improve retention

Generating a NotebookLM Audio Overview of your sources and listening to it as a podcast — on a commute, during exercise — significantly improves recall compared to reading alone. Available in 80+ languages from August 2025.

Research compounds across sessions

A notebook you built two months ago is immediately queryable when the topic comes up again. You are not starting from scratch — you have an annotated, searchable library of everything you already found.

Failure Modes

Trusting Perplexity citations without clicking through

Perplexity cites sources inline, but it can still misrepresent them. The citation format is not a guarantee — it means "this claim came from this URL", not "this URL fully supports this claim". Open the top 2–3 sources for any important claim.

Uploading low-quality sources to NotebookLM

NotebookLM is only as good as what you upload. If you fill a notebook with opinion pieces, company blog posts, and SEO content, the AI will synthesise those confidently. Garbage in, garbage out — even in a source-grounded system.

Using Elicit for non-empirical questions

Elicit is powerful for evidence-based questions with measurable outcomes. It is not useful for opinion, strategy, or emerging topics with little peer-reviewed literature. Use Perplexity for those instead.

Treating Deep Research output as finished work

Deep Research produces impressive-looking reports that can contain errors of synthesis or missed nuance. Treat the output as a high-quality first draft — review the cited sources, spot-check the key claims, and add your own judgement before using it professionally.

One giant notebook for everything

Mixing unrelated topics in a single notebook makes it harder to query. "What are the main findings?" becomes ambiguous when the notebook contains sources on three different subjects. Keep notebooks scoped to a single topic or project.

Extend Your Research Companion

Add citation network mapping — When you find a key paper in Elicit, paste it into ResearchRabbit to see all related papers (what it cites, what cites it). This uncovers seminal work and recent follow-up studies that Elicit alone might not surface.
Add a writing step — After building a NotebookLM notebook, open Claude or ChatGPT alongside it. Copy the notebook's synthesised findings as context, then use Claude to draft a written output — a report, a briefing note, a blog post.
Add spaced review — Every month, open a notebook you have not touched recently, generate a new Mind Map, and ask: "What has changed in this topic since I last researched it?" Then do a fresh Perplexity search to update your sources.
Add shared research — NotebookLM Plus supports shared notebooks. Two people working on the same project can build a shared source library and ask questions against the same set of materials — useful for teams or study groups.

2025–2026 Developments

Deep Research became a standard feature across all major platforms (Feb 2025)

Perplexity, OpenAI, and Google all launched "Deep Research" modes in early 2025. Each runs dozens to hundreds of searches automatically, synthesises across sources, and produces a structured report. What required a research analyst for hours can now be done in under five minutes by anyone. Perplexity's version launched February 14, 2025 and is free for 5 queries per day.

NotebookLM's Audio/Video Overviews went global (Aug–Sep 2025)

In August 2025, NotebookLM removed the English-only restriction, expanding Audio Overviews to 80+ languages. The September 2025 update added format choices — Deep Dive, Brief, Critique, Debate — making it genuinely useful for different research styles. Video Overviews followed in the same rollout. A Lecture Mode (single-host, 30-minute structured talk) was in testing as of late 2025.

Research tool convergence — every AI is adding search

ChatGPT, Claude, and Gemini all added or improved live web search in 2025. The distinction between "chat AI" and "search AI" is eroding. What makes dedicated tools like Perplexity and Elicit still worth using is specialisation: Perplexity's citation density and academic mode, Elicit's structured paper extraction. As general tools improve, the bar for specialist tools rises — but their structural advantages remain.

Checklist: Do You Understand This?

  • Can you explain why using three specialist tools beats one general-purpose chatbot for research?
  • Do you know when to use Perplexity versus NotebookLM versus Elicit?
  • Can you describe the standard 7-step research loop from initial question to organised notebook?
  • Do you know what Perplexity Deep Research does and how many free queries you get per day?
  • Can you explain why NotebookLM's source-grounding is a feature, not a limitation?
  • Do you know how to use Elicit for an evidence-based research question?
  • Can you name three failure modes and how to avoid them?
  • Do you know what the NotebookLM Audio Overview formats are as of September 2025?