Cohere Compass 2 vs Perplexity Research Pages for Teams

“The primitive here is a retrieval pipeline that can ingest mixed-format documents — PDFs with embedded charts, scanned tables, image-heavy slides — and return semantically relevant chunks without requiring a preprocessing ETL step per modality. That's a real problem: anyone who's tried to build RAG over a 10,000-document enterprise library knows the pain is 80% in the ingestion layer. The DX bet is that Cohere handles the multimodal parsing so you don't glue together a PDF parser, a table extractor, and a vision model yourself. The on-prem deployment option is actually the headline feature for the buyer, not the multimodal part — that's what gets it past legal review. My skip concern is documentation: the blog post is long on capability claims and short on API surface, schema design, and what 'image understanding' means at query time versus index time. Show me the query API, then we'll talk.”

“The direct competitors are Azure AI Search with multimodal indexing, AWS Kendra, and increasingly any RAG stack bolted onto GPT-4o's native PDF vision. Compass 2's real differentiator is not the multimodal capability — every major cloud provider is shipping that — it's the on-premises deployment for enterprises with data residency requirements, combined with a retrieval model trained specifically for enterprise document retrieval rather than general web content. The scenario where this breaks is at the 'chart understanding' claim: interpreting a bar chart semantically in a way that survives a specific quantitative query ('find all documents where Q3 revenue exceeded Q2') is a much harder problem than the blog post implies, and I've seen this class of tool hallucinate chart data confidently. What kills this in 12 months isn't a competitor — it's that the chart and table comprehension doesn't hold up under production query loads and the feature gets quietly deprioritized. I'm shipping it narrowly: for text-heavy PDFs with some visual elements in air-gapped environments, this is probably the best available option right now.”

“The direct competitor here is 'Notion AI plus a shared doc,' and Perplexity beats it on one specific axis: the research artifact and the annotation layer are the same object. You're not copy-pasting AI output into a doc and losing provenance. Where this breaks is at scale — the moment a team has 50 Research Pages and no folder structure or cross-page linking, it becomes a graveyard of orphaned reports. Perplexity has 12 months before Microsoft Copilot Pages ships something functionally identical inside Teams, so the clock is running.”

“The buyer is a VP of IT or Chief Data Officer at a regulated enterprise — financial services, pharma, government — and the budget comes from the data infrastructure or compliance line, not a software tools budget. That's a real check-writer with a real problem: they have document libraries they legally cannot send to OpenAI's API, and they need search that works across formats. The on-prem deployment option is the actual moat here, not the multimodal capability — Cohere has been building that distribution channel for two years and it creates genuine switching costs once it's integrated into an enterprise's document management stack. The risk is that the pricing model is 'contact sales' all the way down, which means a long sales cycle and high CAC that has to be recovered on large contracts. What survives the model-gets-cheaper scenario is the enterprise integration layer and compliance certifications, not the retrieval model itself — Cohere needs to be pricing for that, not for compute.”

“The buyer is a knowledge-work team lead whose budget comes from the productivity or research tools line, not IT — that's a faster sales motion than enterprise software usually allows. The upsell logic is clean: individual Perplexity users already exist inside the company, and Research Pages is the forcing function to upgrade the whole team to Team or Enterprise plans. The moat question is real though — this is a collaboration layer on top of a search product, and Google, Microsoft, and Notion all have stronger collaboration primitives and bigger distribution. Perplexity wins if it becomes the research-first destination before the incumbents catch up, which means 18 months, not 36.”

“The thesis Compass 2 is betting on: enterprise knowledge is fundamentally multimodal — it lives in slide decks, scanned contracts, financial tables, and annotated diagrams — and the first retrieval system that treats those formats as first-class citizens rather than edge cases will own the enterprise search layer. That's a plausible and falsifiable bet, but the dependency is that 'understanding' a chart means something semantically useful at query time, not just 'we embedded the image.' The second-order effect that matters here isn't faster document search — it's that if this works, structured data that currently lives locked in PDFs becomes queryable without a data engineering team to extract it, which shifts power from BI teams who own structured pipelines toward anyone with a document library. Cohere is riding the trend of on-premises LLM deployment for regulated industries — that trend is real and accelerating, and they're on-time to it, not early. The future state where this is infrastructure is 'every regulated enterprise has a Compass instance the same way they have an Active Directory instance.' I'd believe that in five years if the chart comprehension claim is real.”

“The thesis here is falsifiable: AI-generated research will become a primary knowledge artifact for teams — not a stepping stone to a Word doc, but the terminal output that gets cited, annotated, and versioned like code. If that's true, whoever owns the collaborative layer on top of AI research owns the institutional memory market. The dependency is that Perplexity's search quality stays ahead of commodity LLM search long enough to create annotation lock-in — users don't annotate outputs they don't trust. The second-order effect is more interesting than the feature itself: if teams start citing Perplexity Research Pages internally, Perplexity becomes infrastructure for organizational knowledge, which is a completely different pricing and retention story than 'AI search subscription.'”

“The job-to-be-done is singular and clear: take AI research out of individual chat histories and make it a team asset. That's a real problem — every team I've seen use Perplexity has a 'great, now how do I share this with my team' moment that currently ends in a screenshot. The onboarding question is whether the first shared page delivers value without a meeting to explain it, and that depends entirely on how clean the annotation UI is — which Perplexity hasn't shown in any public demo. The gap between 'shipped' and 'complete' is a real search and discovery layer for your team's pages; without it, this is a feature, not a workflow.”