Agentic AI System — Architecture (Skills & Tools)

High-levelHigh-level system diagram showing orchestrator, skills, tools, runtimes, data stores, and guardrails

Overview & Architecture

TheThe design below is a general-purpose blueprint for an agentic AI system, drawn as a single reference diagram rather than a narrative report. It brings together several strands from the current agentic-AI literature: an orchestrator that interleaves reasoning with tool calls in the style of the ReAct pattern[1]; a skill/tool catalog that lets a model decide which external function to invoke and with what arguments, following the tool-use approach demonstrated by Toolformer[2]; and a vector database feeding retrieval into the model runtime, the retrieval-augmented generation pattern that combines a language model's parametric knowledge with an external, non-parametric index[3]. The event bus, sandboxed tool adapters, and audit log are this design's own choices for turning those patterns into a production-shaped system with policy enforcement and provenance tracking.

Architecture Diagram

Related Topics

• LLM Orchestration, Context Engineering & Agentic AI — a no-code explanation of the orchestrator/tool-use pattern this diagram draws as a system, including the same ReAct-style reasoning-plus-acting loop.
• Retrieval-Augmented Generation — walks through the indexing/embed/retrieve/generate pipeline behind this diagram's Vector DB component in detail.
• Software Architecture Styles — the event-bus/message-queue and sandboxed-adapter choices in this diagram are the same distributed-systems architecture trade-offs (coupling, independent scaling, partial failure) discussed there for services in general.
• K-Blade Geometric Algebra as a Replacement for Scalar Tensors in Large Language Models — a different layer of the same subject: this page diagrams a system built around an LLM, that one proposes changing the LLM's own internal representation.

References

1. Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2023). ReAct: Synergizing Reasoning and Acting in Language Models. International Conference on Learning Representations (ICLR 2023). arXiv:2210.03629
2. Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023). Toolformer: Language Models Can Teach Themselves to Use Tools. arXiv:2302.04761
3. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances in Neural Information Processing Systems (NeurIPS 2020). arXiv:2005.11401