← Graph

AI Agent

concept 8 connections

Autonomous or semi-autonomous general-purpose LLM-powered program. Uses tools — APIs and integrations — via function calling. Works best with powerful LLMs (currently OpenAI's GPT-4 leads, though leadership changes weekly). Useful for automating workflows and business processes. Reliability increases as the number of responsibilities/tasks decreases: focused agents are POC-ready, general-purpose reliable agents would constitute AGI.

category
architecture
talk Forms Are Dead: Building Agentic Workflows in Ruby
about
AI Agent concept
The talk is framed around building agentic workflows.
talk Building LLM powered applications in Ruby
about
AI Agent concept
Covers AI agents, function calling, and the focus/reliability trade-off.
takeaway Narrow Agent Responsibilities For Reliability
about
AI Agent concept
Takeaway is specifically about how to make AI agents reliable.
question Generate code once vs instruct LLM per request
about
AI Agent concept
Question concerns alternative architectures for agent-style LLM apps.
talk I'm Not a Vibe Coder
about
AI Agent concept
Discusses interacting with LLM-powered coding tools (cursor, Claude) as black boxes
talk Rethink Modularity in Rails
about
AI Agent concept
Argues AI-era economics force rethinking existing modularity techniques
talk Next Token!
about
AI Agent concept
Argues agents aren't real — just stop-token/embeddings/output-formatting abuse.
concept AI Agent
related_to
MCP Server concept
MCP servers expand the tool surface available to agents.

Provenance

Created in
Building LLM-Powered Applications in Ruby — Andrei Bondar... 2026-04-17 23:20
Read by
40 extractions