miatz™
Log inSit Chuun
Free concept playground · no account

Agent Builder

Watch the planner-executor loop light up, node by node.

All 90 playgrounds Join the free cohort

Agent Builder

AvailableFree

An agent isn’t a magic box — it’s a planner-executor loop. Step through the scripted run and watch each node light up: the planner picks an action, the executor calls a tool, the loop observes and decides whether to go again or halt. The step budget is the ceiling that stops a runaway loop from burning spend.

Step budget1 / 6 nodes fired
Running the planner-executor loop — Plan phase
  1. PlanplannerPlanner decomposes the task and picks the first action — it emits a step, not an answer.
  2. Call toolexecutorwaiting for the loop to reach here
  3. Observeobservewaiting for the loop to reach here
  4. Decidedecidewaiting for the loop to reach here
  5. Call tool (loop)executorwaiting for the loop to reach here
  6. Finishstopwaiting for the loop to reach here
How the loop actually runscontrol flow, not magic

An agent is this loop made of parts you can name: plan → call a tool → observe → decide, repeating until a stop condition says halt. Right now it is in the Plan phase.

Planner phase — the model decides WHAT to do next. It outputs a step, not the final answer.

  • plannerPlan
  • executorCall tool
  • observeObserve
  • decideDecide
  • executorCall tool (loop)
  • stopFinish
Was this playground useful?

Agent Builder

Watch an AI agent stop being a magic box. This playground runs a scripted planner-executor loop and lights it up node by node: the planner decomposes the task and picks an action, the executor calls a tool, the loop observes the result, and a decide step checks the stop condition and the step budget before looping again or finishing. What most explanations hand-wave as "the agent thinks" is really this small control-flow graph — and the step-budget ticker is the hard ceiling that catches a runaway loop before it burns real spend. Runs entirely in your browser (0 uploads, works offline).

How to use it

  1. Press Advance one step to move the cursor one node at a time, or Run the loop to jump to the finish.
  2. Watch each node light up: the current node is highlighted, and everything behind it stays lit as the loop progresses.
  3. Read the step budget ticker — it shows how many of the loop's nodes have fired against the ceiling.
  4. Open the X-ray panel to see the phase the agent is in (planner, executor, observe, decide, stop) and why a weak stop condition is the classic way agents loop forever.

What this clears up (the fundamentals)

  • An agent is a loop, not an oracle — plan → call a tool → observe → decide → repeat. Naming the nodes turns "the AI figures it out" into a control-flow graph you can reason about and debug.
  • Planner and executor are different jobs — the planner decides what to do next and emits a step, not an answer; the executor turns that step into a real tool call. Every pass through the executor spends budget.
  • The stop condition is the whole game — the decide node is where the loop checks whether it is done. A weak stop condition is exactly how an agent spins forever and runs up a bill instead of returning.
  • The step budget is a safety ceiling — a hard cap on iterations means a runaway loop fails visibly and cheaply here, instead of silently on a live invoice.

Where it's used

A top-of-funnel AI-engineering explainer — the fastest way to feel why "agentic" means a plan-act-observe loop with a stop condition, not a smarter prompt. It is a miatz build-lab concept playable: play the seeded loop here, then learn to build the state machine, the tool-call budget, and the stop-condition stress test yourself in the AIE-301 agent module.

FAQ

What is a planner-executor loop?

It is the core agent architecture: a planner decides the next action, an executor runs it (usually a tool call), the loop observes the result, and a decide step checks whether to stop or go again. Repeat until a stop condition or budget ends it.

What is a stop condition, and why does it matter?

A stop condition is the rule that halts the loop — goal reached, budget exhausted, or a step cap hit. It matters because it is the most common failure point: a weak one lets the agent loop forever, re-planning and re-calling tools until it burns its whole budget with nothing to show.

What is the step budget ticker?

A visible ceiling on how many loop iterations the agent may run. In real systems it is a token or step budget that forces a runaway loop to fail fast and cheap. Here it fills as each node fires so you can see the loop pressing against its limit.

Does this call a real AI model?

No. This is a seeded, scripted run — the nodes and their outputs are baked into the engine so the loop is deterministic and completely offline. It teaches the control flow, not a live inference.

Is anything uploaded?

No. The whole loop runs in your browser from a fixed script — nothing is transmitted, stored, or logged. Turn off your Wi-Fi and it still works.

Limits

This is a seeded demo: a fixed, scripted planner-executor loop with hand-authored nodes, built to teach the control flow — it is not running a real model, real tools, or a real budget. Live BYOK inference (bring your own key, real tool calls, a real cost meter, and the five adversarial loop-inducing tasks) is a separate future mode. What the demo shows about the shape — plan, act, observe, decide, stop — is exactly how real agent loops work.

Related

Part of the Demystify Playgrounds. Explore the rest from the Playgrounds home.

Bookmark this page (Ctrl+D, or ⌘D on Mac) — it works offline the next time you need it.

More playgrounds

Ninety playgrounds. Zero setup.

Every concept here is playable free, no account — and inside the program you learn to rebuild the machinery yourself.

Browse all playgrounds Join free