Compare AI tools

	ChatGPT Operator B	Devin A	Cursor S	Elicit S
Tagline	OpenAI's browser agent. Clicks and types on websites for you.	Cognition Labs' autonomous coding engineer.	VS Code fork that made AI coding actually work.	AI research assistant for academic literature.
Category	agents	agents	coding	research
Pricing	Included with ChatGPT Pro $200/mo	$500/mo	Free + $20/mo Pro + $40/mo Business	Free + $12-$42/mo
Best for	Power users willing to pay $200/mo for a browser bot.	Engineering teams offloading tickets. Ops/platform work.	Developers. Non-developers who want to ship working code.	Grad students, researchers, anyone doing literature reviews.
Strengths	Actually uses websites — fills forms, clicks, checks out Built into ChatGPT Good for repetitive web tasks	Works like an engineer — takes Slack tasks, opens PRs Handles multi-hour engineering work Reports back with what it did	Tab completion feels like mind-reading Composer for multi-file edits Runs Claude, GPT, Gemini — you pick	Searches 125M+ papers Extracts + synthesizes findings across papers Systematic review workflow
Weaknesses	Slow vs doing it yourself Breaks on complex auth flows $200/mo gate	Expensive Best for well-scoped tasks Not for solo hobbyists	Can feel overwhelming for non-coders Expensive at scale	Academic-only Can hallucinate citations — verify everything
Kai's verdict	B-tier. Still early. Manus is more flexible for less money.	A-tier for the right use case. Not for solo devs. If you manage engineers, try one license.	S-tier for coding. If you write code of any kind, this pays back the $20 in a day.	S-tier for academic research. Nothing else comes close for systematic reviews.
Link	Open →	Open →	Open →	Open →