AI Agent Patterns: How to Plan, Use Tools, Execute Code, and Evaluate Results
Learn the core AI agent patterns for planning, tool use, code execution, and evaluation, with Novita LLM API and Agent Sandbox in the stack.
Filter posts by category
Looking for Cline? Cline vs Cursor for VS Code Coding Agents
If you searched for Cline, compare it with Cursor to see which VS Code agent fits terminal-heavy approvals, refactors, and daily IDE work.
How to Use Claude in PyCharm: JetBrains Claude Agent, Claude Code, and Novita AI
Use Claude in PyCharm with JetBrains Claude Agent or Claude Code, then route the backend through Novita AI and Agent Sandbox.
What Is an Agentic Workflow? How to Build One That Plans, Acts, and Evaluates
An agentic workflow uses an LLM to plan, call tools, run code, and evaluate results. Learn the architecture, trade-offs, and a practical build path.
Macaron V1 Tall Quick Start on Novita AI: First Request, Endpoint, and Free 262K Context
Make your first Macaron V1 Tall API request with the verified model ID, endpoint, limits, and time-limited free 262K context.
Macaron V1 Tall on Novita AI: Free 262K-Context MoL Model for Long-Context Workflows
Macaron V1 Tall pairs 262K context with reasoning, function calling, and time-limited free pricing on Novita AI.
Wan 2.7 VideoEdit API on Novita AI: Edit Existing Clips with Prompts and Reference Images
Use Wan 2.7 VideoEdit to restyle existing footage, preserve motion, and poll async results. Includes Python and cURL examples.
Ling-3.0-flash API Quick Start for Function Calling and Reasoning in Agent Workflows
Call Ling-3.0-flash for function calling and reasoning in agent workflows on Novita AI's OpenAI-compatible API with runnable Python and cURL examples.
Macaron V1 Venti Quick Start on Novita AI: 1M Context, Endpoint, and Examples
Connect to Macaron V1 Venti on Novita AI with the verified model ID, 1M context window, pricing, limits, and runnable examples.
Ling-3.0-flash on Novita AI: Free API for Agentic Inference
Use Ling-3.0-flash free on Novita AI: a 124B MoE model with 5.1B active parameters, 262K context, reasoning, and function calling.
Macaron V1 Venti on Novita AI: 748B Mixture-of-LoRA Flagship for Coding, Agents, and GenUI
Macaron V1 Venti is a 748B Mixture-of-LoRA flagship for coding, agents, and GenUI. See its specs, Novita AI availability, pricing, and best-fit use cases.
OpenCode vs Claude Code: Which Coding Agent Fits Your Workflow?
OpenCode vs Claude Code compared by setup, providers, MCP, execution, cost control, and team fit, with Novita AI integration paths.
Anthropic API Model Names: Claude Model IDs Explained
Learn how Anthropic API model names work, which Claude model IDs belong in requests, and how to avoid alias, version, and provider-routing mistakes.
OpenCode vs Cursor: Which AI Coding Workflow Fits You?
OpenCode vs Cursor compared for developers: workflow, model flexibility, context, MCP tools, execution, cost control, and Novita AI setup.