Conceptual summary of agents:

  • Agent = any external (to the LLM) program that calls the LLM API. Basically plays the role of a human during chat (but can do much more).
  • Agent + AI = an LLM is used as a useful assistant.

External (not LLM internal) agents provide

  • reliable workflows built around models, tools, and automation.
  • tolerance of AI faults and unpredictable outputs


Agentic AI in ZiptieAI evolution (about this diagram)
drones

from “qs” 26.0615

The center of the Agentic AI universe is the AI agent.

drones

The agent and LLM together can doing amazing things. But they also have severe limitations. “Tuning” then to work together is the core focus.

drones


3.1 Agentic (no AI). Core concepts and basic demos

The core control loop is traditional non-AI deterministic programming


3.2 Agentic + AI

The core control loop is traditional non-AI deterministic programming that performs (with the help of an LLM)

  • Input and output (of “messy” human language representations)
  • Task planning (breaking up complex human language tasks into smaller deterministic tasks)
  • Rule injection (by AI into the main loop)

Conceptual summary: Traditional deterministic agents existed long before AI, but were rigid and difficult to scale because human language and semantic relationships required hardcoded logic.

Modern TF/UFA systems made such agents vastly more practical by providing semantic capabilities such as:

  • Semantic interpretation of human language
  • Structured constrained outputs (JSON, schemas, workflows)
  • Contextual reasoning over long token sequences
  • Task decomposition / workflow synthesis
  • Ontology alignment / semantic normalization
  • Generalization beyond explicit hardcoded rules

The core control loop itself remains ordinary deterministic software (“extAgent”), while the LLM provides semantic functionality.


3.2.1 Intro

Just like iAgent and TF work together internally, the extAgent and LLM must work together externally.

  • 1 Deterministic agents existed before AI
  • 2 TF/UFA semantic capabilities made modern agentic systems practical
  • 3 extAgent orchestrates deterministic execution
  • 4 LLM provides semantic functionality
  • 5 Model Interface Layer (MIL)


3.2.2 Diagrams

Core diagrams (my own) that explain the architecture.

  • 1 Ecosystem
  • 2 extAgent <> LLM interface
  • 3 Workflow diagram / simple
  • 4 Workflow diagram / detailed


3.2.3 AI infrastructure

Agents require external orchestration layers that augment the TF/UFA semantic engine capabilities (such as Tools, Filesystem access, RAG,MCP, APIs, and Workflow orchestration).


3.2.4 Basic demos

Very basic demos that show how deterministic agents use TF/UFA semantic capabilities.

  • 1 Basic tool
  • 3 Filesystem
  • 5 RAG
  • 6c MCP + LLM tool choice.


3.2.5 PAL demos

PAL (Palantir) demos focus on:

  • ontology systems
  • semantic workflows
  • deterministic execution
  • LLM-assisted planning
  • structured outputs
  • external orchestration


26.0614 (0524)