back_office_ops · saas · workflow
Inside Meta's Home Grown AI Analytics Agent: From Hack to Company-Wide Tool
Data scientists at Meta are repeatedly asked similar questions within a familiar set of tables, spending hours on routine analysis, while their accumulated query knowledge lived scattered across query editors and notebooks and remained invisible to any system that might learn from it.
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 · User submits analysis question
A user asks a natural language question, such as why a metric dropped.
Tools used
Analytics AgentSQLPythonRScubaLLMsmatplotlib
Outcome
Six months after the prototype moved to production, 77% of Meta's Data Scientists and Data Engineers use Analytics Agent on a weekly basis, alongside roughly 5x as many users from non-data roles, and 4,500+ community-created recipes had been used 150,000 times.
Results
Time saved77%
Volume88%
Grounding & classification
Source type: technical build writeup
39 fields verified against source quotes.
agentic workflowcode generationenterprise searchpersonalizationragsummarizationknowledge basebuilder submittedfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwareautomation rateemployee productivitytime savedtechnical build writeupback office opsagentic task executionrag answering