> For the complete documentation index, see [llms.txt](https://ai-docs.fptcloud.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai-docs.fptcloud.com/fpt-ai-inference/fpt-ai-inference/code-agents-with-fpt-serverless-inference-cloud-api/task-recommendation-by-roles.md). # Task recommendation by roles | Role | Common Tasks | Primary Model | Backup | Best Use / Notes | | ---------------------------------- | ------------------------------------------------------------ | -------------------------- | ----------------- | -------------------------------------------------------------------------- | | **Backend Engineer** | API implementation, service logic, DB query, integration | **Qwen3.6-27B** | DeepSeek-V4-Flash | Default coding agent for repo-level implementation and multi-file changes. | | **Backend Engineer** | CRUD, DTO/schema, boilerplate, simple endpoint | **DeepSeek-V4-Flash** | Qwen3-32B | High-volume value model for fast and repetitive coding tasks. | | **Backend Engineer** | Hard bugs, concurrency, transaction, distributed system | **GLM-5.1** | Qwen3.6-27B | Best for complex debugging and deep technical reasoning. | | **Backend Engineer** | Critical PR review, code audit, security-sensitive logic | **GLM-5.1** | Qwen3.6-27B | Use for high-risk review and important production code. | | **Frontend Engineer** | React/Vue components, form validation, page flow | **Qwen3.6-27B** | DeepSeek-V4-Flash | Strong default for frontend implementation and workflow changes. | | **Frontend Engineer** | Small UI fix, copy update, simple layout/component | **DeepSeek-V4-Flash** | Qwen3-32B | Good for quick UI iterations and low-risk changes. | | **Frontend Engineer** | Complex UI state, frontend refactor, multi-file change | **Qwen3.6-27B** | GLM-5.1 | Use when consistency across files matters. | | **Solution Architect / Tech Lead** | Architecture design, trade-off analysis, system design | **GLM-5.1** | Qwen3.6-27B | Best for strategic technical reasoning and design decisions. | | **Solution Architect / Tech Lead** | Break requirements into technical tasks | **GLM-4.7** | Qwen3.6-27B | Good for workflow planning and structured decomposition. | | **Solution Architect / Tech Lead** | API contract, module boundary, service workflow | **Qwen3.6-27B** | GLM-4.7 | Good balance between coding understanding and system structure. | | **AI Engineer** | LLM agent, tool calling, router logic, OpenAI-compatible API | **GLM-4.7** | Qwen3-32B | Best for tool-calling workflows and agent orchestration. | | **AI Engineer** | RAG pipeline, inference pipeline, SDK integration | **Qwen3.6-27B** | GLM-5.1 | Strong default for implementation-heavy AI engineering tasks. | | **AI Engineer** | vLLM, Ray, Kubernetes inference, scaling issue | **GLM-5.1** | Qwen3.6-27B | Use for complex infra and production-level reasoning. | | **DevOps / Platform Engineer** | Log analysis, shell script, CI/CD script | **DeepSeek-V4-Flash** | Qwen3.6-27B | Good for long-context logs, scripts, and repeated troubleshooting. | | **DevOps / Platform Engineer** | Kubernetes, networking, GPU infra, production incident | **GLM-5.1** | Qwen3.6-27B | Best for high-impact infrastructure debugging. | | **QA / Tester** | Unit test generation, mock data, test data | **DeepSeek-V4-Flash** | Qwen3-32B | Cost-effective for high-volume test generation. | | **QA / Tester** | Integration test, E2E flow from codebase | **Qwen3.6-27B** | DeepSeek-V4-Flash | Better when the model needs to understand code flow. | | **QA / Tester** | Edge case analysis, coverage review | **GLM-5.1** | Qwen3.6-27B | Use for deeper reasoning and missing-case detection. | | **QA / Tester** | Manual test case, regression checklist | **Llama-3.3-70B-Instruct** | GLM-4.7 | Good for clear QA documentation and structured test cases. | | **BA / Product** | User story, acceptance criteria, PRD/SRS | **Llama-3.3-70B-Instruct** | GLM-4.7 | Best for requirement writing and business-facing documents. | | **BA / Product** | Requirement ambiguity, conflict, missing logic | **GLM-5.1** | Qwen3.6-27B | Use when requirements need deeper reasoning or clarification. | | **PM / Delivery** | Summary, release note, client-facing document | **Llama-3.3-70B-Instruct** | Qwen3-32B | Good for communication, documentation, and delivery updates. | --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://ai-docs.fptcloud.com/fpt-ai-inference/fpt-ai-inference/code-agents-with-fpt-serverless-inference-cloud-api/task-recommendation-by-roles.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.