نقشه راه AI Agents

Learn to design, build and ship AI agents in 2025

عمومی

سطح

امیر دایی

مدرس

5

1 رای

956

بازدید

0

دیدگاه

DeepEvalInput / Output SchemaVisit the following relevant tracksModel Context Protocol (MCP)Anthropic Tool UseToken Based PricingCreating MCP ServersWhat are Tools?OpenAI Assistant APIAPI RequestsReAct (Reason + Act)Other ArchitecturePatternsWeb Scraping / CrawlingFine-tuning vs Prompt EngineeringUsage ExamplesSafety + Red Team TestingProvide additional contextPlanner ExecutorExamples of ToolsBuilding AgentsUnderstand the BasicsopenllmetryAutoGenMCP HostsLLM Native "Function Calling"What are AI Agents?Backend Beginner RoadmapOpenAI Functions CallingSecurity & EthicsPricing of Common Models2Max LengthFile System AccessMaintaining MemoryMCP ClientDeployment ModesRAG AgentRemote / CloudOpen Weight ModelsGeneration ControlsContext WindowsLLM FundamentalsEpisodic vs Semantic MemoryError HandlingAgent LoopDAG AgentsSmol DepotBias & Toxicity GuardrailsTokenizationCore ComponentsVector DB / SQL / CustomStreamed vs Unstreamed ResponsesLocal DesktopTop-pLlamaIndexkaar2.irGemini Function CallingLearn the Pre-requisitesModel MechanisAI AgentsSummarization / CompressionStopping CriteriaGit and GitHub RoadmapLangchainWeb Search4Find the detailed version of this roadmapalong with other similar roadmapsTemperaturePerception / User InputShort Term MemoryForgetting / Aging StrategiesGit and Terminal UsageHeliconeCode Execution / REPLParsing model outputReasoning vs Standard ModelsDirect LLM API callsTools / ActionsTree-of-ThoughtIterate and Test your PromptsAI EngineerNPC / Game AIImplementing the agent loopFrameworksDebugging and MonitoringIntegration Testing for FlowsCode generationPersonal assistantObservability ToolsError & Rate-limithandlingTool DefinitionEmail / Slack / SMSBe specific in what you wantUser Profile StorageCommon ArchitecturesUnit Testing for Individual ToolsREST API KnowledgeChain of Thought (CoT)Writing Good PromptsUnderstand the Basics of RAGData Privacy + PII RedactionHuman in the Loop EvaluationAI & Data ScientistActing / Tool InvocationLangSmithPrompt Injection / JailbreaksAgentArchitecturesUse relevant technical termsDatabase QueriesWhat is Agent Memory?Example UsecasesAI Agents 101Closed Weight ModelsPrompt EngineeringWithin PromptLong Term MemoryCrewAIEmbeddings and Vector SearchAgent MemoryLangFuseManual (from scratch)Tool sandboxing / PermissioningMetrics to TrackPresence PenaltyName and DescriptionBasic Backend DevelopmentBuilding Using Frameworks31Prompt Engineering RoadmapRAG and Vector DatabasesData analysisRELATED ROADMAPS› AI Engineer Roadmap› AI and Data Scientist Roadmap› MLOps Roadmap› AI Red Teaming Roadmap› Prompt Engineering RoadmapSpecify Length, format etcModel Families and LicencesLangSmithHaystackEvaluation and TestingWhat is Prompt EngineeringReason and PlanAPI Design RoadmapUse Examples in your PromptMCP ServersRagasTransformer Models and LLMsObservation & ReflectionFrequency PenaltyStructured logging & tracing