How we built our own Claude Code
Blog post from Tinybird
Tinybird Code is a newly developed CLI agent designed to enhance the workflow of AI-native developers working with Tinybird projects and ClickHouse® at scale. Inspired by Claude Code, it addresses the challenges of managing large-scale, real-time data, enabling users to focus on feature development rather than the intricacies of ClickHouse® operations. Built using the Pydantic AI framework, Tinybird Code supports custom model providers and multi-agent architecture, allowing for specialized sub-agents to manage tasks such as SQL queries, data quality tests, and mock data analysis. It features two usage modes—interactive and one-shot—to accommodate different development needs and integrates error recovery and modular rendering for improved user experience. Additionally, the agent is designed with secure model provider authentication, workflow-oriented tools, and safe environment handling, ensuring efficient and secure operations within Tinybird’s ecosystem.
| Trend | Post Mentions | Total Month Mentions | Posts | Companies | MoM |
|---|---|---|---|---|---|
| LLM | 4 | 4,688 | 764 | 235 | -8% |
| Real-time | 3 | 5,669 | 1,214 | 278 | 0% |
| Multi-agent systems | 2 | 318 | 105 | 60 | -26% |
| AI Agents | 1 | 3,159 | 623 | 196 | +13% |
| Developer Experience | 1 | 496 | 231 | 120 | -3% |
| Secrets Management | 1 | 1,241 | 209 | 106 | -19% |
| Subagents | 1 | 30 | 8 | 8 | +173% |
Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.