it_support · saas · workflow
How Qovery built an Agentic DevOps Copilot through 4 technical phases to automate infrastructure tasks
Qovery wanted to eliminate the grunt work of DevOps by building an assistant that could understand developer intent and autonomously take action on infrastructure, but early hardcoded approaches could not handle real-world unplanned requests.
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 · Developer submits request
A developer submits a natural language infrastructure request to the DevOps Copilot.
Tools used
Claude Sonnet 3.7QDrant
Outcome
The Agentic DevOps Copilot is live in Alpha, helping developers automate deployments, optimize infrastructure, and answer advanced configuration questions, with drastically improved user experience after the addition of conversation memory.
What failed first
The first-phase basic agent required every new intent to be hardcoded with no flexibility for unplanned requests; the second-phase agentic system improved flexibility but tool chaining was fragile, meaning a single tool failure broke the entire plan.
Results
Time savedup to 10 seconds
Grounding & classification
Source type: technical build writeup
19 fields verified against source quotes.
agentic workflowai agentknowledge basebuilder submittedfailure mode describednamed customerproduction runtime claimedtools describedworkflow describedsoftwareemployee productivitytechnical build writeupit supportagentic task executionautonomous resolution