back_office_ops · saas · workflow
Dropbox Dash: knowledge graphs, MCP, and DSPy prompt optimization for enterprise AI search
Work content is scattered across dozens of SaaS apps and unavailable to LLMs, making it nearly impossible for employees to find what they need or get AI assistance with their work.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Connect third-party apps
Custom crawlers connect to all third-party apps and pull content into one place.
Tools used
Dropbox DashBM25MCPDSPyo3CLIP-based modelsNDCGRAG
Outcome
Dropbox Dash combines custom connectors, knowledge graphs, hybrid BM25/vector retrieval, and DSPy-optimized LLM judges to enable cross-app AI search and agentic queries, with LLM judge disagreement reduced from an initial 8% through iterative prompt refinement, model upgrades, and DSPy optimization.
Results
Time savedup to 45 seconds
Volume8%
Grounding & classification
Source type: technical build writeup
32 fields verified against source quotes.
agentic workflowdocument aienterprise searchknowledge searchmulti agent workflowragknowledge basemeeting recordingmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedsoftwareaccuracy improvementemployee productivitytechnical build writeupback office opsagentic task executionrag answering