back_office_ops · finance · workflow
Coinbase uses Sourcegraph Cody to save developers 5-6 hours per week while meeting strict security standards
Coinbase wanted to adopt AI code assistants to improve developer productivity but faced strict security requirements around code exposure, model training data use, and potential attack vectors in an industry where handling digital assets demands an especially high security bar, at a time when little public data existed on large-scale AI code assistant adoption.
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 · Security threat model built
Coinbase's security team developed a threat model to identify risks and severities across AI code assistants in key areas.
Tools used
Cody
Outcome
Coinbase developers save roughly 5-6 hours per week using Cody, write code 2x faster, and 75% noted they were more productive in a recent survey.
Results
Time savedroughly 5-6 hours per week
Volume2x faster
Grounding & classification
Source type: vendor customer story
19 fields verified against source quotes.
code generationcode diff prhuman review describedmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedfinancial servicesemployee productivitytime savedvendor customer storyback office opsai draft human approval