Deepgram ships 4-10x more durable code with Claude
DeepgramClaude Code · Claude EnterpriseDeepgram, which builds speech-to-text, text-to-speech and Voice Agent API models, rebuilt its engineering organization around Claude Code and Claude Enterprise after an internal bake-off and cohort study. Regular and power Claude users produced durable code (code that stayed in the codebase rather than being replaced) at roughly 4-10x the rate of non-users. The company also built Deephive, a multi-agent support system where a central agent spawns parallel read-only workers to diagnose customer incidents, cutting incident triage from multi-day back-and-forth to minutes, and its most productive engineering team now runs about 95% Claude-written code.
Overview
Deepgram, which builds speech-to-text, text-to-speech and Voice Agent API models, rebuilt its engineering organization around Claude Code and Claude Enterprise after an internal bake-off and cohort study. Regular and power Claude users produced durable code (code that stayed in the codebase rather than being replaced) at roughly 4-10x the rate of non-users. The company also built Deephive, a multi-agent support system where a central agent spawns parallel read-only workers to diagnose customer incidents, cutting incident triage from multi-day back-and-forth to minutes, and its most productive engineering team now runs about 95% Claude-written code.
This entry has 14 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Deepgram's engineering surface - inference, APIs, SDKs, billing, integrations, infrastructure, and apps - was outgrowing traditional, human-speed workflows, and the cost of AI-native code generation among competitors was approaching zero. Incident triage showed the cost most plainly: when a customer reported an issue, an engineer pulled logs and metrics by hand from data spread across five places and pieced together a response, often over a multi-day back-and-forth, and the engineer fielding the report wasn't always the one who owned the affected service.
The solution
Deepgram ran a real-world bake-off of Claude Code against other coding agents on its Rust, Python, and infrastructure-as-code codebases, then an internal cohort study tracking which Claude-assisted code stayed in the codebase (durable) versus got replaced. It then did a hard company-wide cutover to Claude Enterprise in mid-2026, with training off by default, centrally managed retention, tool permissions, and MCP allowlists, and auto-issued new-hire accounts. The default engineering loop runs through Claude Code in plan mode, connected via MCP to Slack, Asana, GitHub and Grafana; reusable solutions become SKILL.md files in a shared repository. One engineer built Deephive, a multi-agent support system where a central Opus-class agent spawns parallel read-only Sonnet-class workers that pull context from Slack, DevRev, Notion, GitHub and Asana to diagnose customer incidents, with every deliverable requiring human sign-off.
Reported business value
Regular and power Claude users produced durable code at roughly 4-10x the rate of non-users. Deepgram's most productive engineering team now runs about 95% Claude-written code, and one new hire shipped 40+ substantial pull requests in six weeks. Customer incident triage that once ran multi-day back-and-forth now returns verified root causes in minutes. The research team replaced roughly 80% of its legacy stack with an agent-native environment, and the whole company migrated to Claude Enterprise with SSO and centrally managed compliance.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other software development entries in the register.
How Atlassian builds AI agents teams can trust with Claude and Google Cloud
Atlassian, whose products including Jira and Confluence serve over 350,000 customers, built an internal AI model gateway on Google Cloud that routes complex, long-running agentic work to Claude while simpler high-volume tasks go to Gemini Flash. Claude powers Rovo Chat (Atlassian's in-app assistant used by millions), Rovo CLI (its primary developer AI experience), and Rovo Max, an early-access mode that plans and executes complex multi-step work across Atlassian's Teamwork Graph. More than 5 million AI agents now run in customer business workflows each month.
Atlassian· AustraliaClaude Platform · Claude Code · Google Cloud
Notion builds agent orchestration where teams and Claude collaborate on real work
Notion built agent orchestration on Claude Managed Agents, letting teams delegate work like coding, presentations and client deliverables directly from task boards, with teams able to kick off 30+ concurrent agent tasks at once. Claude also powers Notion's existing AI Writer, Autofill and Enterprise Search features, with prompt caching cutting Notion's infrastructure costs by 90% and latency by up to 85%. Enterprise customer Osaka Gas reports a 35% reduction in time spent searching for information, Remote saves an estimated 10 minutes per search across 300 daily queries, and dbt Labs saved over $35k annually by eliminating the need for separate AI tools.
NotionClaude Managed Agents · Claude PlatformWas this helpful?
Your feedback helps us improve our use case database