#agentworkflows — Public Fediverse posts

Agents do not need RAG or vector databases for most real world work. They need structure and semantics.

Agent Knowledge Graphs turn mixed repositories of code, docs, configs, and PDFs into a connected model that agents can reason over. This often replaces entire retrieval pipelines.

https://antaoalmada.dev/posts/Code-Agent-Knowledge-Graphs/

#AIEngineering #KnowledgeGraphs #CodingAgents #AgentWorkflows #SoftwareArchitecture #Graphify

Agents do not need RAG or vector databases for most real world work. They need structure and semantics.

Agent Knowledge Graphs turn mixed repositories of code, docs, configs, and PDFs into a connected model that agents can reason over. This often replaces entire retrieval pipelines.

https://antaoalmada.dev/posts/Code-Agent-Knowledge-Graphs/

#AIEngineering #KnowledgeGraphs #CodingAgents #AgentWorkflows #SoftwareArchitecture #Graphify

One thing that is strangely missing from this blogpost is the comparative resource efficiency of each workflow, based on a standard fixed metric. But I imagine that for Anthropic that's not a problem ;-)

"Success in the LLM space isn't about building the most sophisticated system. It's about building the right system for your needs. Start with simple prompts, optimize them with comprehensive evaluation, and add multi-step agentic systems only when simpler solutions fall short.

When implementing agents, we try to follow three core principles:

- Maintain simplicity in your agent's design.

- Prioritize transparency by explicitly showing the agent’s planning steps.

- Carefully craft your agent-computer interface (ACI) through thorough tool documentation and testing.

- Frameworks can help you get started quickly, but don't hesitate to reduce abstraction layers and build with basic components as you move to production. By following these principles, you can create agents that are not only powerful but also reliable, maintainable, and trusted by their users."

https://www.anthropic.com/engineering/building-effective-agents

#AI #AIAgents #AgentWorkflows #GenerativeAI #LLMs #Chatbots #ACI

One thing that is strangely missing from this blogpost is the comparative resource efficiency of each workflow, based on a standard fixed metric. But I imagine that for Anthropic that's not a problem ;-)

"Success in the LLM space isn't about building the most sophisticated system. It's about building the right system for your needs. Start with simple prompts, optimize them with comprehensive evaluation, and add multi-step agentic systems only when simpler solutions fall short.

When implementing agents, we try to follow three core principles:

- Maintain simplicity in your agent's design.

- Prioritize transparency by explicitly showing the agent’s planning steps.

- Carefully craft your agent-computer interface (ACI) through thorough tool documentation and testing.

- Frameworks can help you get started quickly, but don't hesitate to reduce abstraction layers and build with basic components as you move to production. By following these principles, you can create agents that are not only powerful but also reliable, maintainable, and trusted by their users."

https://www.anthropic.com/engineering/building-effective-agents

#AI #AIAgents #AgentWorkflows #GenerativeAI #LLMs #Chatbots #ACI