United StatesFinance and insurance2025 – ongoingRamp
Claude Code for engineering workflows
Ramp implemented more than 1 million lines of AI-suggested code in 30 days, Anthropic reported
Problem
Ramp engineers spent time cycling between code changes and tests. Incident investigation required gathering information from separate monitoring systems.
Approach
Engineers adopted Claude Code and connected it to testing frameworks. They also used it for documentation and ticket-driven development. Ramp was building incident tools connected to Datadog and Sentry.
Results
Takeaway
The rollout reached recurring engineering work. The suggested incident-triage improvement remained an early observation.
Categories
- Industry
- Finance and insurance
- Business function
- IT and R&D
- Innovation type
- Process innovation
- AI technology
- Generative AIAI agents
- Adoption
- Off-the-shelf tool or platform
- Evidence
- Vendor case study
Sources
Source summaries
Anthropic reported more than 1 million lines of AI-suggested code implemented in 30 days and nearly 50% weekly engineering usage. Incident tooling was still being built; early observations suggested potential initial-triage reductions of up to 80%.
Full details are in the original sources.