Lesson 362 of 2116
Research Agent Setups: Perplexity, Elicit, Consensus, And Friends
A tour of the research-agent tool landscape and how to pick the right one per task. The meta-skill: knowing which tool for which question.
Lesson map
What this lesson covers
Learning path
The main moves in order
- 1The current landscape (2026)
- 2Perplexity
- 3Elicit
- 4Consensus
Concept cluster
Terms to connect while reading
Section 1
The current landscape (2026)
Compare the options
| Tool | Sweet spot | Not great at |
|---|---|---|
| Perplexity | Quick current-events research with citations | Deep scientific literature |
| Elicit | Literature review with structured extraction | Current events, non-English sources |
| Consensus | Claim-level 'what does research say' queries | Emerging questions with thin literature |
| Scite | Citation sentiment (supporting vs contradicting) | First-pass discovery |
| Semantic Scholar | Free API, good metadata, citation graph | UX, integrated summarization |
| GPT Deep Research | 30-minute multi-hop web investigation | Paywalled academic content |
| Gemini Deep Research | Long-form research with Google's index | Niche academic databases |
| Claude Projects | Document-grounded research on YOUR corpus | Discovery outside your docs |
The decision tree
- 1Do you already have the source documents? → Claude Projects or NotebookLM
- 2Is this academic literature? → Elicit or Consensus, then Semantic Scholar to verify
- 3Is this current events or industry? → Perplexity or GPT Deep Research
- 4Is this a claim-level question (X causes Y?)? → Consensus or Scite
- 5Is this a full systematic review? → ASReview + Rayyan + Elicit as a pipeline
Stacking tools
The best workflows chain tools. Example: Elicit to map the literature → Consensus to validate specific claims → Semantic Scholar API to pull a citation graph → Claude Project to synthesize across everything → Obsidian for atomic note capture.
Key terms in this lesson
The big idea: no single research agent is good at everything. The researchers who get the most out of these tools are the ones who know exactly when to switch between them.
End-of-lesson quiz
Check what stuck
15 questions · Score saves to your progress.
Tutor
Curious about “Research Agent Setups: Perplexity, Elicit, Consensus, And Friends”?
Ask anything about this lesson. I’ll answer using just what you’re reading — short, friendly, grounded.
Progress saved locally in this browser. Sign in to sync across devices.
Related lessons
Keep going
Creators · 40 min
AI-Driven Systematic Reviews: The New Workflow
Tools like Elicit and ASReview are reshaping systematic review. Here's how to use them without sacrificing rigor.
Creators · 40 min
Literature Review With LLMs: Scope First, Search Second
Use an LLM to define the scope of your lit review before touching a search engine — the single highest-leverage move in modern research workflow.
Creators · 11 min
Deep Research Workflows: Multi-Hop Questions Done Right
Deep research tools like GPT Deep Research and Gemini Deep Research can run 30-minute multi-hop investigations. Here's how to brief them so the output is usable.