Agent Patterns: ReAct, Reflection & Planning — From One LLM Call to a Production Loop
ReAct, Reflection, and Planning for LLM agents — when to use each, guardrails against runaway loops, and links to tool use and orchestration.
Filter/Tag
#llm_10
10 entries
-
-
Function Calling & Tool Use — JSON Schema, the Agent Loop, Parallel Calls & Security
How LLM function calling bridges models to the world: JSON Schema tools, the request→execute→result loop, parallel calls, validation, MCP, and security.
-
Choosing an LLM for Agents: A Durable Framework Beyond Leaderboards
A senior engineer framework for model selection — capability tiers, context, modality, cost, privacy, tool use — plus routing, cascades, and why benchmarks lie.
-
Evaluating LLMs & Agents: Golden Sets, Metrics, LLM-as-Judge, and Regression in CI
Why eval is the hardest part of shipping agents — golden datasets, offline vs online metrics, LLM-as-judge rubrics, human agreement, and regression in CI.
-
Fine-tuning vs Prompting vs RAG: A Decision Framework for Adapting LLMs
When to prompt, retrieve, or fine-tune: knowledge vs behavior, data needs, cost, privacy, SFT/LoRA/DPO — and why most teams start with prompt + RAG.
-
Context Engineering & Agent Memory — Packing the Window Without Losing the Thread
How senior engineers pack system prompts, tools, history, RAG, and output reserve into a fixed context window — and manage memory when the budget breaks.
-
Stopping Criteria & Output Control — When Generation Ends and What to Do About It
EOS tokens, max_tokens, stop sequences, and finish_reason handling for production LLM agents — streaming, truncation, and runaway cost guards.
-
Prompt Engineering for Agents — Messages, Personas, Few-Shot & Structured Output
Agent prompt design: messages/roles, personas, few-shot trade-offs, CoT vs reasoning models, JSON schemas, templates, injection guards, iteration.
-
Sampling for Agents: Temperature, Top-p, Top-k — When Randomness Helps or Hurts
How LLMs turn logits into tokens — temperature, top_p, top_k, penalties, seeds — and why agent builders tune sampling differently for tool calls vs brainstorming.
-
Tokens & Context Windows — The Hard Budget Every AI Agent Must Respect
Tokens are the atomic unit of LLM memory and cost. Learn subword tokenization, context window math, and agent budgeting before you ship.