agent workflow

Bilingual

Show HN: Claudaholic – Keep Up with Claude
2 months ago
- The text outlines a daily practice regimen to improve skills in working with AI agents, structured around six facets.
- Each facet involves six daily tasks: Judgment (six calls to catch agent mistakes), Orchestration (six workflow questions), Architecture (six design questions), Leverage (six budget calls), Taste (six taste calls), and Knowledge (six knowledge nuggets).
- The goal is to keep up with Claude by proving skills daily through these exercises.
Building Agentic Workflows in Python with LangGraph
2 months ago
- LangGraph represents an agent as a graph with state, nodes, and edges; state is a shared TypedDict, nodes are functions that update state, edges define execution order.
- MessagesState provides built-in message history with add_messages reducer to accumulate conversation automatically.
- Model calls are placed inside a node; tools are registered using @tool decorator and bound to the model via bind_tools.
- ToolNode handles tool execution; tools_condition routes graph between model and tool nodes in a ReAct loop.
- A checkpointer (e.g., InMemorySaver) persists conversation state across separate graph invocations using a thread_id.
- The standard ReAct pattern involves two model calls per tool use: one to decide the call, one to interpret the result.
I Cut an AI Agent's Token Use by 94%
2 months ago
- AI agent token use reduced by 94% by compiling stable workflow parts into deterministic code.
- Natural-language skills used initially for flexibility, then specialized harnesses created after analyzing historical traces.
- LLMs only applied for semantic judgment steps like candidate selection and drafting, not for repetitive tasks.
- Optimization pattern: express workflow in natural language, gather traces, compile stable parts, keep LLM calls for key judgments.
- Incentives of big model vendors may not prioritize token reduction, creating opportunities for independent builders.

agent workflow

Show HN: Claudaholic – Keep Up with Claude

Building Agentic Workflows in Python with LangGraph

I Cut an AI Agent's Token Use by 94%