https://menuagentic.com/https://menuagentic.com/about/https://menuagentic.com/blogs/https://menuagentic.com/blogs/afk-coding/https://menuagentic.com/blogs/agentic-ai-for-trading-research/https://menuagentic.com/blogs/ai-in-the-trading-stack/https://menuagentic.com/blogs/ccusage-vs-codex-usage-tracker-vs-codeburn-vs-litellm-proxy/https://menuagentic.com/blogs/claude-code-vs-codex-cli-vs-cursor-agent-vs-aider/https://menuagentic.com/blogs/e2b-vs-modal-vs-daytona-vs-anthropic-code-execution/https://menuagentic.com/blogs/finrl-vs-tensortrade-vs-abides-gym-vs-elegantrl/https://menuagentic.com/blogs/getting-started-with-openhuman/https://menuagentic.com/blogs/langgraph-vs-crewai-vs-claude-managed-agents-vs-openai-agents-sdk/https://menuagentic.com/blogs/langsmith-vs-braintrust-vs-helicone-vs-arize-phoenix/https://menuagentic.com/blogs/llama-4-vs-deepseek-v3-vs-qwen3-vs-mistral-large-3/https://menuagentic.com/blogs/openclaw-vs-openhuman-vs-hermes-agent/https://menuagentic.com/blogs/pgvector-vs-pinecone-vs-weaviate-vs-qdrant/https://menuagentic.com/blogs/tag/agent-comparison/https://menuagentic.com/blogs/tag/agent-frameworks/https://menuagentic.com/blogs/tag/agentic-ai/https://menuagentic.com/blogs/tag/agentic-qa/https://menuagentic.com/blogs/tag/ai-trading/https://menuagentic.com/blogs/tag/applications/https://menuagentic.com/blogs/tag/architecture/https://menuagentic.com/blogs/tag/code-execution/https://menuagentic.com/blogs/tag/coding-agents/https://menuagentic.com/blogs/tag/cost/https://menuagentic.com/blogs/tag/developer-tools/https://menuagentic.com/blogs/tag/evals/https://menuagentic.com/blogs/tag/frontier-models/https://menuagentic.com/blogs/tag/getting-started/https://menuagentic.com/blogs/tag/infrastructure/https://menuagentic.com/blogs/tag/llm-agents/https://menuagentic.com/blogs/tag/memory/https://menuagentic.com/blogs/tag/model-comparison/https://menuagentic.com/blogs/tag/multi-agent-systems/https://menuagentic.com/blogs/tag/observability/https://menuagentic.com/blogs/tag/open-source/https://menuagentic.com/blogs/tag/orchestration/https://menuagentic.com/blogs/tag/personal-assistant/https://menuagentic.com/blogs/tag/quant-finance/https://menuagentic.com/blogs/tag/rag/https://menuagentic.com/blogs/tag/reinforcement-learning/https://menuagentic.com/blogs/tag/sandboxing/https://menuagentic.com/blogs/tag/self-hosted/https://menuagentic.com/blogs/tag/tooling/https://menuagentic.com/blogs/tag/trading/https://menuagentic.com/blogs/tag/vector-databases/https://menuagentic.com/blogs/tag/workflow/https://menuagentic.com/changelog/https://menuagentic.com/concepts/https://menuagentic.com/concepts/agent-frameworks/https://menuagentic.com/concepts/agentic-risks-intro/https://menuagentic.com/concepts/agents-vs-chatbots-workflows/https://menuagentic.com/concepts/autonomy-levels/https://menuagentic.com/concepts/choosing-a-model/https://menuagentic.com/concepts/chunking-and-vector-search/https://menuagentic.com/concepts/context-windows/https://menuagentic.com/concepts/cost-quality-latency/https://menuagentic.com/concepts/embeddings/https://menuagentic.com/concepts/evals-101/https://menuagentic.com/concepts/few-shot-prompting/https://menuagentic.com/concepts/guardrails-101/https://menuagentic.com/concepts/inference-providers/https://menuagentic.com/concepts/modalities/https://menuagentic.com/concepts/model-families/https://menuagentic.com/concepts/neural-networks-intuition/https://menuagentic.com/concepts/open-vs-closed-models/https://menuagentic.com/concepts/planning-and-termination/https://menuagentic.com/concepts/prompt-injection-101/https://menuagentic.com/concepts/prompting-basics/https://menuagentic.com/concepts/reading-benchmarks/https://menuagentic.com/concepts/reasoning-models/https://menuagentic.com/concepts/structured-outputs/https://menuagentic.com/concepts/system-vs-user-prompts/https://menuagentic.com/concepts/temperature-and-sampling/https://menuagentic.com/concepts/the-agent-loop/https://menuagentic.com/concepts/tokens-and-tokenization/https://menuagentic.com/concepts/tool-calling-explained/https://menuagentic.com/concepts/tools-actions-environments/https://menuagentic.com/concepts/training-vs-inference/https://menuagentic.com/concepts/transformers-overview/https://menuagentic.com/concepts/what-is-ai/https://menuagentic.com/concepts/what-is-an-agent/https://menuagentic.com/concepts/what-is-an-llm/https://menuagentic.com/concepts/what-is-rag/https://menuagentic.com/concepts/when-to-use-an-agent/https://menuagentic.com/deep-dives/https://menuagentic.com/deep-dives/architectures-and-patterns/https://menuagentic.com/deep-dives/architectures-and-patterns/agent-search-strategies/https://menuagentic.com/deep-dives/architectures-and-patterns/pattern-landscape/https://menuagentic.com/deep-dives/architectures-and-patterns/plan-and-execute/https://menuagentic.com/deep-dives/architectures-and-patterns/react-pattern/https://menuagentic.com/deep-dives/architectures-and-patterns/reflection-pattern/https://menuagentic.com/deep-dives/architectures-and-patterns/router-pattern/https://menuagentic.com/deep-dives/architectures-and-patterns/single-vs-multi-agent/https://menuagentic.com/deep-dives/architectures-and-patterns/tool-error-recovery/https://menuagentic.com/deep-dives/memory-and-context/https://menuagentic.com/deep-dives/memory-and-context/context-budgeting/https://menuagentic.com/deep-dives/memory-and-context/context-compaction/https://menuagentic.com/deep-dives/memory-and-context/evaluating-memory/https://menuagentic.com/deep-dives/memory-and-context/memory-stores/https://menuagentic.com/deep-dives/memory-and-context/memory-types/https://menuagentic.com/deep-dives/memory-and-context/retrieval-augmented-memory/https://menuagentic.com/deep-dives/memory-and-context/short-vs-long-term-memory/https://menuagentic.com/deep-dives/multi-agent-systems/https://menuagentic.com/deep-dives/multi-agent-systems/agent-debate-and-ensembles/https://menuagentic.com/deep-dives/multi-agent-systems/multi-agent-failure-modes/https://menuagentic.com/deep-dives/multi-agent-systems/multi-agent-topologies/https://menuagentic.com/deep-dives/multi-agent-systems/multi-agent-when-and-why/https://menuagentic.com/deep-dives/multi-agent-systems/shared-memory-and-blackboard/https://menuagentic.com/deep-dives/multi-agent-systems/supervisor-worker-pattern/https://menuagentic.com/deep-dives/protocols-and-interop/https://menuagentic.com/deep-dives/protocols-and-interop/a2a-communication/https://menuagentic.com/deep-dives/protocols-and-interop/building-interoperable-agents/https://menuagentic.com/deep-dives/protocols-and-interop/capability-discovery/https://menuagentic.com/deep-dives/protocols-and-interop/interop-problem/https://menuagentic.com/deep-dives/protocols-and-interop/mcp-architecture/https://menuagentic.com/deep-dives/protocols-and-interop/structured-tool-io/https://menuagentic.com/deep-dives/protocols-and-interop/tool-calling-standards/https://menuagentic.com/deep-dives/reasoning-and-test-time-compute/https://menuagentic.com/deep-dives/reasoning-and-test-time-compute/chain-of-thought/https://menuagentic.com/deep-dives/reasoning-and-test-time-compute/inference-time-scaling/https://menuagentic.com/deep-dives/reasoning-and-test-time-compute/self-consistency-and-sampling/https://menuagentic.com/deep-dives/reasoning-and-test-time-compute/tree-and-graph-of-thought/https://menuagentic.com/deep-dives/reasoning-and-test-time-compute/verifier-guided-search/https://menuagentic.com/deep-dives/reasoning-and-test-time-compute/when-reasoning-helps/https://menuagentic.com/deep-dives/retrieval-and-rag/https://menuagentic.com/deep-dives/retrieval-and-rag/advanced-rag-architectures/https://menuagentic.com/deep-dives/retrieval-and-rag/agentic-retrieval/https://menuagentic.com/deep-dives/retrieval-and-rag/choosing-a-vector-database/https://menuagentic.com/deep-dives/retrieval-and-rag/document-parsing-for-rag/https://menuagentic.com/deep-dives/retrieval-and-rag/evaluating-rag/https://menuagentic.com/deep-dives/retrieval-and-rag/graph-rag/https://menuagentic.com/deep-dives/retrieval-and-rag/hybrid-search-and-reranking/https://menuagentic.com/deep-dives/retrieval-and-rag/query-understanding-for-rag/https://menuagentic.com/deep-dives/tool-capability-design/https://menuagentic.com/deep-dives/tool-capability-design/tool-design-antipatterns/https://menuagentic.com/deep-dives/tool-capability-design/tool-design-principles/https://menuagentic.com/deep-dives/tool-capability-design/tool-discovery-and-docs/https://menuagentic.com/deep-dives/tool-capability-design/tool-error-messages/https://menuagentic.com/deep-dives/tool-capability-design/tool-granularity/https://menuagentic.com/deep-dives/tool-capability-design/tool-schemas-and-contracts/https://menuagentic.com/deep-dives/training-agentic-models/https://menuagentic.com/deep-dives/training-agentic-models/process-vs-outcome-rewards/https://menuagentic.com/deep-dives/training-agentic-models/prompt-finetune-or-rl/https://menuagentic.com/deep-dives/training-agentic-models/reward-design-and-hacking/https://menuagentic.com/deep-dives/training-agentic-models/rl-for-tool-use/https://menuagentic.com/deep-dives/training-agentic-models/rlhf-and-rlaif/https://menuagentic.com/deep-dives/training-agentic-models/sft-rejection-sampling-distillation/https://menuagentic.com/field-guide/https://menuagentic.com/field-guide/async-python/https://menuagentic.com/field-guide/benchmarks-and-ci/https://menuagentic.com/field-guide/code-agents/https://menuagentic.com/field-guide/computer-use/https://menuagentic.com/field-guide/cost-and-latency/https://menuagentic.com/field-guide/deployment/https://menuagentic.com/field-guide/eval-driven-dev/https://menuagentic.com/field-guide/first-eval-suite/https://menuagentic.com/field-guide/llm-as-judge/https://menuagentic.com/field-guide/llm-mental-model/https://menuagentic.com/field-guide/multi-agent/https://menuagentic.com/field-guide/observability/https://menuagentic.com/field-guide/prompts/https://menuagentic.com/field-guide/real-loop/https://menuagentic.com/field-guide/research/https://menuagentic.com/field-guide/retrieval/https://menuagentic.com/field-guide/safety/https://menuagentic.com/field-guide/the-loop/https://menuagentic.com/field-guide/three-layers/https://menuagentic.com/field-guide/tool-use/https://menuagentic.com/field-guide/what-to-read/https://menuagentic.com/operations/https://menuagentic.com/operations/agentops/https://menuagentic.com/operations/agentops/concurrency-and-scaling/https://menuagentic.com/operations/agentops/cost-control-in-the-loop/https://menuagentic.com/operations/agentops/durable-state-and-resumability/https://menuagentic.com/operations/agentops/feature-flags-for-agents/https://menuagentic.com/operations/agentops/idempotency-and-retries/https://menuagentic.com/operations/agentops/incident-response-for-agents/https://menuagentic.com/operations/agentops/kill-switches/https://menuagentic.com/operations/agentops/rollout-and-versioning/https://menuagentic.com/operations/economics-roi/https://menuagentic.com/operations/economics-roi/build-vs-buy/https://menuagentic.com/operations/economics-roi/cost-attribution/https://menuagentic.com/operations/economics-roi/economics-failure-modes/https://menuagentic.com/operations/economics-roi/measuring-roi/https://menuagentic.com/operations/economics-roi/per-customer-economics/https://menuagentic.com/operations/economics-roi/pricing-models/https://menuagentic.com/operations/economics-roi/unit-economics/https://menuagentic.com/operations/evaluation-and-observability/https://menuagentic.com/operations/evaluation-and-observability/eval-driven-agent-development/https://menuagentic.com/operations/evaluation-and-observability/llm-as-judge-for-agents/https://menuagentic.com/operations/evaluation-and-observability/online-vs-offline-evals/https://menuagentic.com/operations/evaluation-and-observability/outcome-vs-trajectory-eval/https://menuagentic.com/operations/evaluation-and-observability/reading-agent-benchmarks/https://menuagentic.com/operations/evaluation-and-observability/tracing-and-observability/https://menuagentic.com/operations/evaluation-and-observability/why-agent-eval-is-hard/https://menuagentic.com/operations/governance-compliance/https://menuagentic.com/operations/governance-compliance/accountability-and-roles/https://menuagentic.com/operations/governance-compliance/audit-trails/https://menuagentic.com/operations/governance-compliance/data-governance/https://menuagentic.com/operations/governance-compliance/eu-ai-act-for-agents/https://menuagentic.com/operations/governance-compliance/governance-in-practice/https://menuagentic.com/operations/governance-compliance/nist-ai-rmf-for-agents/https://menuagentic.com/operations/governance-compliance/policy-enforcement/https://menuagentic.com/operations/governance-compliance/regulatory-landscape/https://menuagentic.com/operations/safety-and-security/https://menuagentic.com/operations/safety-and-security/agent-identity/https://menuagentic.com/operations/safety-and-security/agentic-threat-model/https://menuagentic.com/operations/safety-and-security/alignment-basics/https://menuagentic.com/operations/safety-and-security/data-exfiltration-risks/https://menuagentic.com/operations/safety-and-security/deployment-safety-checklist/https://menuagentic.com/operations/safety-and-security/guardrails/https://menuagentic.com/operations/safety-and-security/human-in-the-loop/https://menuagentic.com/operations/safety-and-security/prompt-injection/https://menuagentic.com/operations/safety-and-security/rag-security/https://menuagentic.com/operations/safety-and-security/safety-red-teaming/https://menuagentic.com/operations/safety-and-security/scoped-credentials-for-agents/https://menuagentic.com/playbooks/https://menuagentic.com/playbooks/agent-ux-and-human-interaction/https://menuagentic.com/playbooks/agent-ux-and-human-interaction/approval-and-confirmation-ux/https://menuagentic.com/playbooks/agent-ux-and-human-interaction/designing-for-failure/https://menuagentic.com/playbooks/agent-ux-and-human-interaction/designing-for-trust/https://menuagentic.com/playbooks/agent-ux-and-human-interaction/interruption-and-handoff/https://menuagentic.com/playbooks/agent-ux-and-human-interaction/progressive-autonomy/https://menuagentic.com/playbooks/agent-ux-and-human-interaction/progressive-disclosure-ux/https://menuagentic.com/playbooks/agent-ux-and-human-interaction/transparency-and-explainability/https://menuagentic.com/playbooks/coding-and-computer-use-agents/https://menuagentic.com/playbooks/coding-and-computer-use-agents/browser-agents/https://menuagentic.com/playbooks/coding-and-computer-use-agents/coding-agent-architecture/https://menuagentic.com/playbooks/coding-and-computer-use-agents/computer-use-and-gui-agents/https://menuagentic.com/playbooks/coding-and-computer-use-agents/evaluating-coding-agents/https://menuagentic.com/playbooks/coding-and-computer-use-agents/ide-agents/https://menuagentic.com/playbooks/coding-and-computer-use-agents/patch-generation-and-tests/https://menuagentic.com/playbooks/coding-and-computer-use-agents/repo-navigation-and-context/https://menuagentic.com/playbooks/coding-and-computer-use-agents/sandboxing-and-execution/https://menuagentic.com/playbooks/domain-playbooks/https://menuagentic.com/playbooks/domain-playbooks/customer-support-agents/https://menuagentic.com/playbooks/domain-playbooks/data-analysis-agents/https://menuagentic.com/playbooks/domain-playbooks/devops-sre-agents/https://menuagentic.com/playbooks/domain-playbooks/finance-agents/https://menuagentic.com/playbooks/domain-playbooks/healthcare-agents/https://menuagentic.com/playbooks/domain-playbooks/legal-agents/https://menuagentic.com/playbooks/domain-playbooks/playbook-meta/https://menuagentic.com/playbooks/domain-playbooks/research-agents/https://menuagentic.com/playbooks/domain-playbooks/sales-and-gtm-agents/https://menuagentic.com/playbooks/voice-realtime-agents/https://menuagentic.com/playbooks/voice-realtime-agents/latency-budget/https://menuagentic.com/playbooks/voice-realtime-agents/outbound-voice-agents/https://menuagentic.com/playbooks/voice-realtime-agents/realtime-architecture/https://menuagentic.com/playbooks/voice-realtime-agents/speech-stack/https://menuagentic.com/playbooks/voice-realtime-agents/turn-taking-and-barge-in/https://menuagentic.com/playbooks/voice-realtime-agents/voice-failure-modes/https://menuagentic.com/playbooks/voice-realtime-agents/voice-tooling-and-state/https://menuagentic.com/zh/https://menuagentic.com/zh/about/https://menuagentic.com/zh/blogs/https://menuagentic.com/zh/blogs/afk-coding/https://menuagentic.com/zh/blogs/agentic-ai-for-trading-research/https://menuagentic.com/zh/blogs/ai-in-the-trading-stack/https://menuagentic.com/zh/blogs/ccusage-vs-codex-usage-tracker-vs-codeburn-vs-litellm-proxy/https://menuagentic.com/zh/blogs/claude-code-vs-codex-cli-vs-cursor-agent-vs-aider/https://menuagentic.com/zh/blogs/e2b-vs-modal-vs-daytona-vs-anthropic-code-execution/https://menuagentic.com/zh/blogs/finrl-vs-tensortrade-vs-abides-gym-vs-elegantrl/https://menuagentic.com/zh/blogs/getting-started-with-openhuman/https://menuagentic.com/zh/blogs/langgraph-vs-crewai-vs-claude-managed-agents-vs-openai-agents-sdk/https://menuagentic.com/zh/blogs/langsmith-vs-braintrust-vs-helicone-vs-arize-phoenix/https://menuagentic.com/zh/blogs/llama-4-vs-deepseek-v3-vs-qwen3-vs-mistral-large-3/https://menuagentic.com/zh/blogs/openclaw-vs-openhuman-vs-hermes-agent/https://menuagentic.com/zh/blogs/pgvector-vs-pinecone-vs-weaviate-vs-qdrant/https://menuagentic.com/zh/blogs/tag/agent-comparison/https://menuagentic.com/zh/blogs/tag/agent-frameworks/https://menuagentic.com/zh/blogs/tag/agentic-ai/https://menuagentic.com/zh/blogs/tag/agentic-qa/https://menuagentic.com/zh/blogs/tag/ai-trading/https://menuagentic.com/zh/blogs/tag/applications/https://menuagentic.com/zh/blogs/tag/architecture/https://menuagentic.com/zh/blogs/tag/code-execution/https://menuagentic.com/zh/blogs/tag/coding-agents/https://menuagentic.com/zh/blogs/tag/cost/https://menuagentic.com/zh/blogs/tag/developer-tools/https://menuagentic.com/zh/blogs/tag/evals/https://menuagentic.com/zh/blogs/tag/frontier-models/https://menuagentic.com/zh/blogs/tag/getting-started/https://menuagentic.com/zh/blogs/tag/infrastructure/https://menuagentic.com/zh/blogs/tag/llm-agents/https://menuagentic.com/zh/blogs/tag/memory/https://menuagentic.com/zh/blogs/tag/model-comparison/https://menuagentic.com/zh/blogs/tag/multi-agent-systems/https://menuagentic.com/zh/blogs/tag/observability/https://menuagentic.com/zh/blogs/tag/open-source/https://menuagentic.com/zh/blogs/tag/orchestration/https://menuagentic.com/zh/blogs/tag/personal-assistant/https://menuagentic.com/zh/blogs/tag/quant-finance/https://menuagentic.com/zh/blogs/tag/rag/https://menuagentic.com/zh/blogs/tag/reinforcement-learning/https://menuagentic.com/zh/blogs/tag/sandboxing/https://menuagentic.com/zh/blogs/tag/self-hosted/https://menuagentic.com/zh/blogs/tag/tooling/https://menuagentic.com/zh/blogs/tag/trading/https://menuagentic.com/zh/blogs/tag/vector-databases/https://menuagentic.com/zh/blogs/tag/workflow/https://menuagentic.com/zh/changelog/https://menuagentic.com/zh/concepts/https://menuagentic.com/zh/concepts/agent-frameworks/https://menuagentic.com/zh/concepts/agentic-risks-intro/https://menuagentic.com/zh/concepts/agents-vs-chatbots-workflows/https://menuagentic.com/zh/concepts/autonomy-levels/https://menuagentic.com/zh/concepts/choosing-a-model/https://menuagentic.com/zh/concepts/chunking-and-vector-search/https://menuagentic.com/zh/concepts/context-windows/https://menuagentic.com/zh/concepts/cost-quality-latency/https://menuagentic.com/zh/concepts/embeddings/https://menuagentic.com/zh/concepts/evals-101/https://menuagentic.com/zh/concepts/few-shot-prompting/https://menuagentic.com/zh/concepts/guardrails-101/https://menuagentic.com/zh/concepts/inference-providers/https://menuagentic.com/zh/concepts/modalities/https://menuagentic.com/zh/concepts/model-families/https://menuagentic.com/zh/concepts/neural-networks-intuition/https://menuagentic.com/zh/concepts/open-vs-closed-models/https://menuagentic.com/zh/concepts/planning-and-termination/https://menuagentic.com/zh/concepts/prompt-injection-101/https://menuagentic.com/zh/concepts/prompting-basics/https://menuagentic.com/zh/concepts/reading-benchmarks/https://menuagentic.com/zh/concepts/reasoning-models/https://menuagentic.com/zh/concepts/structured-outputs/https://menuagentic.com/zh/concepts/system-vs-user-prompts/https://menuagentic.com/zh/concepts/temperature-and-sampling/https://menuagentic.com/zh/concepts/the-agent-loop/https://menuagentic.com/zh/concepts/tokens-and-tokenization/https://menuagentic.com/zh/concepts/tool-calling-explained/https://menuagentic.com/zh/concepts/tools-actions-environments/https://menuagentic.com/zh/concepts/training-vs-inference/https://menuagentic.com/zh/concepts/transformers-overview/https://menuagentic.com/zh/concepts/what-is-ai/https://menuagentic.com/zh/concepts/what-is-an-agent/https://menuagentic.com/zh/concepts/what-is-an-llm/https://menuagentic.com/zh/concepts/what-is-rag/https://menuagentic.com/zh/concepts/when-to-use-an-agent/https://menuagentic.com/zh/deep-dives/https://menuagentic.com/zh/deep-dives/architectures-and-patterns/https://menuagentic.com/zh/deep-dives/architectures-and-patterns/agent-search-strategies/https://menuagentic.com/zh/deep-dives/architectures-and-patterns/pattern-landscape/https://menuagentic.com/zh/deep-dives/architectures-and-patterns/plan-and-execute/https://menuagentic.com/zh/deep-dives/architectures-and-patterns/react-pattern/https://menuagentic.com/zh/deep-dives/architectures-and-patterns/reflection-pattern/https://menuagentic.com/zh/deep-dives/architectures-and-patterns/router-pattern/https://menuagentic.com/zh/deep-dives/architectures-and-patterns/single-vs-multi-agent/https://menuagentic.com/zh/deep-dives/architectures-and-patterns/tool-error-recovery/https://menuagentic.com/zh/deep-dives/memory-and-context/https://menuagentic.com/zh/deep-dives/memory-and-context/context-budgeting/https://menuagentic.com/zh/deep-dives/memory-and-context/context-compaction/https://menuagentic.com/zh/deep-dives/memory-and-context/evaluating-memory/https://menuagentic.com/zh/deep-dives/memory-and-context/memory-stores/https://menuagentic.com/zh/deep-dives/memory-and-context/memory-types/https://menuagentic.com/zh/deep-dives/memory-and-context/retrieval-augmented-memory/https://menuagentic.com/zh/deep-dives/memory-and-context/short-vs-long-term-memory/https://menuagentic.com/zh/deep-dives/multi-agent-systems/https://menuagentic.com/zh/deep-dives/multi-agent-systems/agent-debate-and-ensembles/https://menuagentic.com/zh/deep-dives/multi-agent-systems/multi-agent-failure-modes/https://menuagentic.com/zh/deep-dives/multi-agent-systems/multi-agent-topologies/https://menuagentic.com/zh/deep-dives/multi-agent-systems/multi-agent-when-and-why/https://menuagentic.com/zh/deep-dives/multi-agent-systems/shared-memory-and-blackboard/https://menuagentic.com/zh/deep-dives/multi-agent-systems/supervisor-worker-pattern/https://menuagentic.com/zh/deep-dives/protocols-and-interop/https://menuagentic.com/zh/deep-dives/protocols-and-interop/a2a-communication/https://menuagentic.com/zh/deep-dives/protocols-and-interop/building-interoperable-agents/https://menuagentic.com/zh/deep-dives/protocols-and-interop/capability-discovery/https://menuagentic.com/zh/deep-dives/protocols-and-interop/interop-problem/https://menuagentic.com/zh/deep-dives/protocols-and-interop/mcp-architecture/https://menuagentic.com/zh/deep-dives/protocols-and-interop/structured-tool-io/https://menuagentic.com/zh/deep-dives/protocols-and-interop/tool-calling-standards/https://menuagentic.com/zh/deep-dives/reasoning-and-test-time-compute/https://menuagentic.com/zh/deep-dives/reasoning-and-test-time-compute/chain-of-thought/https://menuagentic.com/zh/deep-dives/reasoning-and-test-time-compute/inference-time-scaling/https://menuagentic.com/zh/deep-dives/reasoning-and-test-time-compute/self-consistency-and-sampling/https://menuagentic.com/zh/deep-dives/reasoning-and-test-time-compute/tree-and-graph-of-thought/https://menuagentic.com/zh/deep-dives/reasoning-and-test-time-compute/verifier-guided-search/https://menuagentic.com/zh/deep-dives/reasoning-and-test-time-compute/when-reasoning-helps/https://menuagentic.com/zh/deep-dives/retrieval-and-rag/https://menuagentic.com/zh/deep-dives/retrieval-and-rag/advanced-rag-architectures/https://menuagentic.com/zh/deep-dives/retrieval-and-rag/agentic-retrieval/https://menuagentic.com/zh/deep-dives/retrieval-and-rag/choosing-a-vector-database/https://menuagentic.com/zh/deep-dives/retrieval-and-rag/document-parsing-for-rag/https://menuagentic.com/zh/deep-dives/retrieval-and-rag/evaluating-rag/https://menuagentic.com/zh/deep-dives/retrieval-and-rag/graph-rag/https://menuagentic.com/zh/deep-dives/retrieval-and-rag/hybrid-search-and-reranking/https://menuagentic.com/zh/deep-dives/retrieval-and-rag/query-understanding-for-rag/https://menuagentic.com/zh/deep-dives/tool-capability-design/https://menuagentic.com/zh/deep-dives/tool-capability-design/tool-design-antipatterns/https://menuagentic.com/zh/deep-dives/tool-capability-design/tool-design-principles/https://menuagentic.com/zh/deep-dives/tool-capability-design/tool-discovery-and-docs/https://menuagentic.com/zh/deep-dives/tool-capability-design/tool-error-messages/https://menuagentic.com/zh/deep-dives/tool-capability-design/tool-granularity/https://menuagentic.com/zh/deep-dives/tool-capability-design/tool-schemas-and-contracts/https://menuagentic.com/zh/deep-dives/training-agentic-models/https://menuagentic.com/zh/deep-dives/training-agentic-models/process-vs-outcome-rewards/https://menuagentic.com/zh/deep-dives/training-agentic-models/prompt-finetune-or-rl/https://menuagentic.com/zh/deep-dives/training-agentic-models/reward-design-and-hacking/https://menuagentic.com/zh/deep-dives/training-agentic-models/rl-for-tool-use/https://menuagentic.com/zh/deep-dives/training-agentic-models/rlhf-and-rlaif/https://menuagentic.com/zh/deep-dives/training-agentic-models/sft-rejection-sampling-distillation/https://menuagentic.com/zh/field-guide/https://menuagentic.com/zh/field-guide/async-python/https://menuagentic.com/zh/field-guide/benchmarks-and-ci/https://menuagentic.com/zh/field-guide/code-agents/https://menuagentic.com/zh/field-guide/computer-use/https://menuagentic.com/zh/field-guide/cost-and-latency/https://menuagentic.com/zh/field-guide/deployment/https://menuagentic.com/zh/field-guide/eval-driven-dev/https://menuagentic.com/zh/field-guide/first-eval-suite/https://menuagentic.com/zh/field-guide/llm-as-judge/https://menuagentic.com/zh/field-guide/llm-mental-model/https://menuagentic.com/zh/field-guide/multi-agent/https://menuagentic.com/zh/field-guide/observability/https://menuagentic.com/zh/field-guide/prompts/https://menuagentic.com/zh/field-guide/real-loop/https://menuagentic.com/zh/field-guide/research/https://menuagentic.com/zh/field-guide/retrieval/https://menuagentic.com/zh/field-guide/safety/https://menuagentic.com/zh/field-guide/the-loop/https://menuagentic.com/zh/field-guide/three-layers/https://menuagentic.com/zh/field-guide/tool-use/https://menuagentic.com/zh/field-guide/what-to-read/https://menuagentic.com/zh/operations/https://menuagentic.com/zh/operations/agentops/https://menuagentic.com/zh/operations/agentops/concurrency-and-scaling/https://menuagentic.com/zh/operations/agentops/cost-control-in-the-loop/https://menuagentic.com/zh/operations/agentops/durable-state-and-resumability/https://menuagentic.com/zh/operations/agentops/feature-flags-for-agents/https://menuagentic.com/zh/operations/agentops/idempotency-and-retries/https://menuagentic.com/zh/operations/agentops/incident-response-for-agents/https://menuagentic.com/zh/operations/agentops/kill-switches/https://menuagentic.com/zh/operations/agentops/rollout-and-versioning/https://menuagentic.com/zh/operations/economics-roi/https://menuagentic.com/zh/operations/economics-roi/build-vs-buy/https://menuagentic.com/zh/operations/economics-roi/cost-attribution/https://menuagentic.com/zh/operations/economics-roi/economics-failure-modes/https://menuagentic.com/zh/operations/economics-roi/measuring-roi/https://menuagentic.com/zh/operations/economics-roi/per-customer-economics/https://menuagentic.com/zh/operations/economics-roi/pricing-models/https://menuagentic.com/zh/operations/economics-roi/unit-economics/https://menuagentic.com/zh/operations/evaluation-and-observability/https://menuagentic.com/zh/operations/evaluation-and-observability/eval-driven-agent-development/https://menuagentic.com/zh/operations/evaluation-and-observability/llm-as-judge-for-agents/https://menuagentic.com/zh/operations/evaluation-and-observability/online-vs-offline-evals/https://menuagentic.com/zh/operations/evaluation-and-observability/outcome-vs-trajectory-eval/https://menuagentic.com/zh/operations/evaluation-and-observability/reading-agent-benchmarks/https://menuagentic.com/zh/operations/evaluation-and-observability/tracing-and-observability/https://menuagentic.com/zh/operations/evaluation-and-observability/why-agent-eval-is-hard/https://menuagentic.com/zh/operations/governance-compliance/https://menuagentic.com/zh/operations/governance-compliance/accountability-and-roles/https://menuagentic.com/zh/operations/governance-compliance/audit-trails/https://menuagentic.com/zh/operations/governance-compliance/data-governance/https://menuagentic.com/zh/operations/governance-compliance/eu-ai-act-for-agents/https://menuagentic.com/zh/operations/governance-compliance/governance-in-practice/https://menuagentic.com/zh/operations/governance-compliance/nist-ai-rmf-for-agents/https://menuagentic.com/zh/operations/governance-compliance/policy-enforcement/https://menuagentic.com/zh/operations/governance-compliance/regulatory-landscape/https://menuagentic.com/zh/operations/safety-and-security/https://menuagentic.com/zh/operations/safety-and-security/agent-identity/https://menuagentic.com/zh/operations/safety-and-security/agentic-threat-model/https://menuagentic.com/zh/operations/safety-and-security/alignment-basics/https://menuagentic.com/zh/operations/safety-and-security/data-exfiltration-risks/https://menuagentic.com/zh/operations/safety-and-security/deployment-safety-checklist/https://menuagentic.com/zh/operations/safety-and-security/guardrails/https://menuagentic.com/zh/operations/safety-and-security/human-in-the-loop/https://menuagentic.com/zh/operations/safety-and-security/prompt-injection/https://menuagentic.com/zh/operations/safety-and-security/rag-security/https://menuagentic.com/zh/operations/safety-and-security/safety-red-teaming/https://menuagentic.com/zh/operations/safety-and-security/scoped-credentials-for-agents/https://menuagentic.com/zh/playbooks/https://menuagentic.com/zh/playbooks/agent-ux-and-human-interaction/https://menuagentic.com/zh/playbooks/agent-ux-and-human-interaction/approval-and-confirmation-ux/https://menuagentic.com/zh/playbooks/agent-ux-and-human-interaction/designing-for-failure/https://menuagentic.com/zh/playbooks/agent-ux-and-human-interaction/designing-for-trust/https://menuagentic.com/zh/playbooks/agent-ux-and-human-interaction/interruption-and-handoff/https://menuagentic.com/zh/playbooks/agent-ux-and-human-interaction/progressive-autonomy/https://menuagentic.com/zh/playbooks/agent-ux-and-human-interaction/progressive-disclosure-ux/https://menuagentic.com/zh/playbooks/agent-ux-and-human-interaction/transparency-and-explainability/https://menuagentic.com/zh/playbooks/coding-and-computer-use-agents/https://menuagentic.com/zh/playbooks/coding-and-computer-use-agents/browser-agents/https://menuagentic.com/zh/playbooks/coding-and-computer-use-agents/coding-agent-architecture/https://menuagentic.com/zh/playbooks/coding-and-computer-use-agents/computer-use-and-gui-agents/https://menuagentic.com/zh/playbooks/coding-and-computer-use-agents/evaluating-coding-agents/https://menuagentic.com/zh/playbooks/coding-and-computer-use-agents/ide-agents/https://menuagentic.com/zh/playbooks/coding-and-computer-use-agents/patch-generation-and-tests/https://menuagentic.com/zh/playbooks/coding-and-computer-use-agents/repo-navigation-and-context/https://menuagentic.com/zh/playbooks/coding-and-computer-use-agents/sandboxing-and-execution/https://menuagentic.com/zh/playbooks/domain-playbooks/https://menuagentic.com/zh/playbooks/domain-playbooks/customer-support-agents/https://menuagentic.com/zh/playbooks/domain-playbooks/data-analysis-agents/https://menuagentic.com/zh/playbooks/domain-playbooks/devops-sre-agents/https://menuagentic.com/zh/playbooks/domain-playbooks/finance-agents/https://menuagentic.com/zh/playbooks/domain-playbooks/healthcare-agents/https://menuagentic.com/zh/playbooks/domain-playbooks/legal-agents/https://menuagentic.com/zh/playbooks/domain-playbooks/playbook-meta/https://menuagentic.com/zh/playbooks/domain-playbooks/research-agents/https://menuagentic.com/zh/playbooks/domain-playbooks/sales-and-gtm-agents/https://menuagentic.com/zh/playbooks/voice-realtime-agents/https://menuagentic.com/zh/playbooks/voice-realtime-agents/latency-budget/https://menuagentic.com/zh/playbooks/voice-realtime-agents/outbound-voice-agents/https://menuagentic.com/zh/playbooks/voice-realtime-agents/realtime-architecture/https://menuagentic.com/zh/playbooks/voice-realtime-agents/speech-stack/https://menuagentic.com/zh/playbooks/voice-realtime-agents/turn-taking-and-barge-in/https://menuagentic.com/zh/playbooks/voice-realtime-agents/voice-failure-modes/https://menuagentic.com/zh/playbooks/voice-realtime-agents/voice-tooling-and-state/