back_office_ops · ecommerce · workflow
Hermes V3: Building Swiggy's Conversational AI Analyst
The original Hermes text-to-SQL tool struggled with niche metrics, required users to repeat context in every prompt, generated inconsistent SQL output, and provided no way to debug or trust the results.
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 · Employee asks question in Slack
Employees query data in plain English via Hermes, a lightweight interface embedded in Slack.
Tools used
ClaudeSnowflakeSlackvector DB
Outcome
Hermes V3 improved SQL query accuracy from 54% to 93% on a benchmark of approximately 100 manually tagged queries, reduced fully incorrect queries from 20% to 7%, achieved near-zero table-not-found errors, and became the backbone for all internal AI co-pilots at Swiggy.
What failed first
The previous pipeline achieved only 54% accuracy with 20% of queries fully incorrect, and relied on generic embeddings that frequently failed to resolve inconsistent or obscure column names.
Results
Volume93%
Grounding & classification
Source type: technical build writeup
27 fields verified against source quotes.
agentic workflowconversational aidata extractionragknowledge basemetric backednamed customerproduction runtime claimedtools describedworkflow describedecommerceaccuracy improvementemployee productivityerror reductiontechnical build writeupback office opsagentic task executionrag answering