MEVZU N° TAG / VOL. 004
1 blog · 0 news · 30 wiki
Prompt Engineering tek mesaj kuruyor; Agentic Engineering ise hedefi olan, araç kullanan, kendi kendini düzelten bir sistem tasarlıyor. Üç aşamalı evrim, klasik yazılımla karşılaştırma, somut bir Türkçe örnek ve insan-denetimi prensipleri.
Autonomous AI agents that can read files, run commands, and produce code in a developer environment.
Software development workflows in which AI agents read and write files, run commands, and execute tests.
An agent pattern that interleaves reasoning steps with tool actions in a single thought-action loop.
An open-source Python framework that organizes role-based agents as a collaborating crew.
A practice popularized by Karpathy of letting AI write code from natural-language vibes without reviewing each line.
A two-step agent pattern where an LLM critiques and revises its own output.
An autonomous software system that takes its own steps toward a goal, often using tools along the way.
The discipline of designing, shipping and maintaining LLM-driven agent systems in production.
An LLM extending its capability by calling external tools, APIs or functions.
A technique in which a model evaluates its own output against explicit criteria to surface errors and weaknesses.
An AI agent navigating and acting on web pages by driving a browser like a human.
An open-source framework from Microsoft Research for building conversation-based multi-agent applications.
Memory that persists beyond a single session, available to an agent across future runs.
An agent's ability to detect errors or failed steps and automatically recover from them.
A control layer that keeps an LLM or agent within sanctioned behavior boundaries.
An AI agent's ability to operate an entire computer via mouse, keyboard, and screenshots.
An agent capable of operating over long horizons without human intervention, making and acting on its own decisions.
A RAG architecture in which an agent decides retrieval steps instead of a fixed pipeline.
A stateful, graph-based agent workflow framework from the LangChain team.
A modern AI agent where an LLM is the decision-maker, taking multiple steps and using tools.
An API feature that lets a model invoke a predefined function via structured JSON output.
An open protocol from Anthropic that gives AI agents a standard interface for connecting to external systems.
An agent's ability to design and order the steps it will take to reach a goal.
The component that plans and coordinates the execution of multiple agents, models, or tools.
A secondary agent invoked by a parent agent to handle a specific subtask with its own prompt and tools.
A system in which multiple AI agents collaborate, negotiate, or divide labor to accomplish a goal.
A feedback loop that continuously measures and refines an agent's output.
A memory type that recalls specific events or interactions together with their time and context.
The in-session memory an agent keeps within its context window — recent turns and intermediate state.
A structured pipeline of LLM-driven steps with explicit branching, rather than a single agent's free-form loop.