Cohere Blog ·
A source describing Compass, Cohere’s retrieval system, covering its cloud deployment rationale, cost benefits from precise retrieval, design requirements for agentic workflows, and accuracy gains—benchmarked on a financial RAG task. Read 4 viewpoints with supporting evidence and source links.
Lines show the reading structure. Select an idea to read its explanation and evidence.
Synthesis
Teams consistently asked for a managed Compass offering—wanting its best-in-class retrieval without the operational overhead of self-hosting.
Original excerpt
Customer demand for a managed option has been clear and consistent: teams want Compass' best-in-class retrieval capabilities, but many do not want the operational overhead that comes with self-hosting.
Cohere Team · Paragraph 5
Read in source context →Continue exploring
product deployment strategy →More precise retrieval delivers smaller, higher-quality inputs to generative models, cutting inference costs and task completion time. Retrieval is among the most effective cost levers available to businesses today.
Original excerpt
Token economics: Every irrelevant result passed to a model consumes tokens and occupies limited context space. More precise retrieval creates smaller, higher-quality inputs, reducing inference costs and cutting the time needed to complete a task. Retrieval is one of the most effective cost levers available to businesses today.
Cohere Team · Paragraph 10
Read in source context →Continue exploring
cost optimization →Agents may issue dozens of queries per task. Retrieval systems must therefore perform reliably across sequences of machine-generated queries—not just single-shot searches—while maintaining relevance, enforcing permissions at every step, and avoiding latency accumulation.
Original excerpt
Agentic access patterns: Agents may issue dozens of queries while completing one task, reformulating requests and traversing multiple sources. In these multi-hop loops, latency accumulates, relevance can drift, and permissions must be enforced at every step. Retrieval must therefore perform reliably across sequences of machine-generated queries, not only single-shot searches.
Cohere Team · Paragraph 11
Read in source context →Continue exploring
retrieval system design →On the High Finance benchmark—a Cohere-built investment-banking RAG workload—Compass improved accuracy by 14–16 points over Azure Search (64.8 → 81.1). That gap can distinguish between unsatisfactory and great end-user answers.
Original excerpt
The figure below is one instance of the accuracy gain over traditional or standalone search infrastructure on a representative financial-industry RAG workload: embed a query, retrieve presentation materials from an index, and score the top results. On High Finance, a Cohere-built investment-banking benchmark, Compass achieved a 14-16 point improvement on Azure Search (from 64.8 to 81.1). A gap of this size can be the difference between an unsatisfactory answer and a great one for the end user.
Cohere Team · Paragraph 25
Read in source context →Continue exploring
performance benchmarking →Attributed passages with the context to verify them. Open the original text to check the source.
Original excerpt
Customer demand for a managed option has been clear and consistent: teams want Compass' best-in-class retrieval capabilities, but many do not want the operational overhead that comes with self-hosting.
Original excerpt
Token economics: Every irrelevant result passed to a model consumes tokens and occupies limited context space. More precise retrieval creates smaller, higher-quality inputs, reducing inference costs and cutting the time needed to complete a task. Retrieval is one of the most effective cost levers available to businesses today.
Original excerpt
The figure below is one instance of the accuracy gain over traditional or standalone search infrastructure on a representative financial-industry RAG workload: embed a query, retrieve presentation materials from an index, and score the top results. On High Finance, a Cohere-built investment-banking benchmark, Compass achieved a 14-16 point improvement on Azure Search (from 64.8 to 81.1). A gap of this size can be the difference between an unsatisfactory answer and a great one for the end user.
Original excerpt
Agentic access patterns: Agents may issue dozens of queries while completing one task, reformulating requests and traversing multiple sources. In these multi-hop loops, latency accumulates, relevance can drift, and permissions must be enforced at every step. Retrieval must therefore perform reliably across sequences of machine-generated queries, not only single-shot searches.
Cohere Team uses Azure Search as a baseline comparison for Compass on the High Finance benchmark, reporting its score (64.8) without evaluative judgment beyond relative performance.
Read supporting evidence · Cohere TeamCohere Team reports that Compass achieved a 14–16 point accuracy improvement over Azure Search on the High Finance benchmark, calling the gap decisive for end-user answer quality.
Read supporting evidence · Cohere TeamThese viewpoints are linked to their original sources. Paraphrases are labeled and are not verbatim quotes.
Open transcript or source material (opens in a new tab)Report an issueMore sources on topics discussed here. Shared topics do not imply agreement.