BlueCLClaude in the product.
Engineering across the stack.
Our use of Claude spans service API workflows, parallel LLM processing, and software development. We connect that experience to MCP tools and the AI infrastructure we are building next.
01. How we use Claude today
BlueCL uses Claude API in running service workflows and parallel LLM processing. Claude and reusable Claude Skills also support our software development work.
| Area | Current use |
|---|---|
| Service API workflows | Claude API calls support AI features in our services. |
| Mindflow MCP | Implemented note summarization, task and deadline extraction, MCP tools, and Notion integration. |
| Parallel processing | Claude summarization runs alongside independent model and parsing tasks, with results combined into a connected workflow. |
| Development | Claude and reusable Skills support software development and API integration work. |
02. From model calls to connected work
Mindflow MCP is an implementation of our approach: use language models to interpret information, coordinate independent tasks, and connect the output to a tool where it can be used.
- Accept study notes.Text enters the application workflow.
- Process with language models.Claude summarizes notes and extracts tasks and deadlines. Composite workflows can combine Claude with other models.
- Coordinate parallel tasks.The implementation runs Claude summarization alongside parsing, then combines the results.
- Connect to Notion.MCP tools create or update the destination with structured information and generated content.
These capabilities are implemented in the Mindflow codebase. Product development and user validation continue alongside the existing integrations.
03. Reliability is the next engineering milestone
Our ongoing priorities are Korean-language summary quality, dependable task and deadline extraction, connected-tool reliability, and visibility into API latency and cost.
Quality
Evaluate summaries and extracted tasks against representative inputs.
Orchestration
Improve coordination, error handling, and recovery across model and tool calls.
Cost & latency
Measure workflow timing and API usage to guide practical improvements.
04. Building the AI operations layer
We are developing real-time LLM load balancing and GPU server monitoring for developers operating multiple inference servers.
| Stage | Work |
|---|---|
| Current implementation | Claude API workflows, MCP-connected tools, and parallel LLM processing. |
| In development | Real-time request distribution and GPU server monitoring in an AI operations platform. |
| Planned expansion | Claude provider integration in the operations platform and natural-language explanations of operational metrics. |
Our experience implementing Claude workflows informs the platform's direction. The operations product and its planned Claude integrations remain under development.
05. A founder-led AI software company
BlueCL is based in Mokpo, South Korea, and builds on a business established on February 24, 2023. Founder Dongju Kang develops software products and independently conducted research into MCP-based parallel LLM learning support and LLM-based website generation with visual editing.
South Korea business registration number: 494-52-00728
Two 2026 KSCI conference publications document these studies, with publication authors Soojung Lee and Dongju Kang.
Build with BlueCL
Talk to us about AI workflows, connected tools, and LLM infrastructure.
bluecl@bluecl.cloud