agents
Agent design, loops, and autonomy
Topics
- Agent and LLM framework landscapeFrameworks provide building blocks for LLM applications: model clients, tool loops, retrieval, memory, orchestration, tracing. They speed up getting started, but add a layer between you and the…
- Agent patternsAn agent is an LLM that works in a loop: it decides what to do, uses tools, observes the results, and continues until the task is done. Agents suit open-ended tasks whose steps cannot be…
- Agent skillsA skill is a folder of instructions, scripts, and reference files that teaches an agent how to do a specific job: fill in a PDF form, follow a company style guide, run a deployment. The agent sees…
- Coding agentsCoding agents read a codebase, plan, edit files, run commands and tests, and iterate until a task is done. They range from IDE assistants to terminal tools to cloud agents that open pull requests…
- Evaluating LLM applicationsAn eval is a repeatable test of how well a model, prompt, or agent does a task. Without evals, changes to prompts, models, or tools are guesswork. Public benchmarks compare models in general; your…
- Memory for agentsModels have no memory between requests: each call sees only what is in its context. Agents that work for long periods or across sessions need ways to keep what matters and drop what does not.…
- Prompting and context engineeringPrompting is writing the instructions and context a model works from. As models have improved, the craft has moved from tricks and magic phrases toward context engineering: choosing what…
- Security for LLM apps and agentsLLM applications add new attack surfaces: the model follows instructions found in any text it reads, and agents can act on those instructions with real tools and credentials. The core rule is to…
- Tool use (function calling)Tool use lets a model call functions you define: search a database, call an API, run code, edit files. The model does not run anything itself. It returns a structured request (tool name plus JSON…
Sources
- AI SDK 7release · Vercel · 25 June 2026
- Accelerating the search for antimicrobial peptides with Google Antigravityarticle · Google DeepMind · 15 October 2026
- Muse Wonderarticle · Meta · 12 October 2026
- How we contain Claude across productsarticle · Max McGuinness, Mikaela Grace, Jiri De Jonghe, Jake Eaton, Abel Ribbink (Anthropic) · 25 May 2026
- LangGraph 1.2.0 release notesrelease · LangChain · 12 May 2026
- OpenAI "rogue" agent activities found on Wikimedia projectsarticle · Selena Deckelmann, Wikimedia Foundation · 5 October 2026
- OpenAI API changelog: GPT-6.1 Sol, Agents API computer use, ultrafast tierrelease · OpenAI · 29 September 2026
- Gemini API changelog, September 2026release · Google · 22 September 2026
- Introducing Muse Spark 1.1article · Meta Superintelligence Labs · 9 July 2026
- ReAct: Synergizing Reasoning and Acting in Language Modelspaper · Yao et al. (Princeton, Google Research) · 6 October 2022
- Pydantic AI v2.54.0release · Pydantic · 2 October 2026
- OpenAI Agents SDK (Python) v0.23.0release · OpenAI · 2 October 2026
- Google Agent Development Kit (Python) v2.11.0release · Google · 2 October 2026
- Agent Skills overview (Claude docs)docs · Anthropic
- Building effective agentsarticle · Anthropic · 19 December 2024