back_office_ops · education · workflow
Duolingo builds an agentic feature flag remover using Codex CLI and Temporal
Duolingo engineers needed agentic tooling to automate simple but repetitive tasks like feature flag removal, and lacked a clean, reliable pattern for building agents that operate directly on their codebase.
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 initiates via self-service UI
Through the Platform Self-Service UI, a workflow is kicked off in Temporal's gateway dispatcher namespace.
Tools used
TemporalCodex CLIECSlangchainfast-agentBaymaxGithub MCP
Outcome
Development was described as quick, easy, and immediately successful — a prototype was running in approximately one day and a productionized version was ready within one week.
What failed first
Two parallel implementations — one using langchain with an internal toolset called Baymax, and one using fast-agent with the Github MCP — were in development for 1–2 weeks before being abandoned when Codex CLI was released and worked immediately with a single prompt.
Results
Time saved~1 day
Grounding & classification
Source type: technical build writeup
26 fields verified against source quotes.
agentic workflowai agentcode generationcode diff prfailure mode describedhuman review describednamed customerproduction runtime claimedtools describedworkflow describededucationemployee productivitytime savedtechnical build writeupback office opsagentic task execution