Agent Flow Steps

Agents in reasoning mode process every request through a pipeline of flow steps. The entire pipeline is exposed on the agent’s Configuration tab, there are no hidden system instructions. Each LLM-powered step is a card you can open, inspect, and customize: what you see in the pipeline is exactly what runs.

The pipeline

Step	Required	What it does
Orchestrate	Yes	Plans the next move, reviews the request, current state, and prior results, then picks one capability to run.
Action	Yes	Where your capabilities execute (API calls, LLM calls, workflows, webhooks, sub-agents). Not an LLM step, manage these on the Capabilities tab.
Process	Optional, on by default	Distills each action result into a rolling summary and findings, and writes state updates. Two sub-calls: Summary & Findings and Form Updates. Disable it to keep a raw message transcript instead.
Progress Probe	Optional, off by default	After each result, checks whether the agent should continue, respond, or rewind. Adds a guardrail LLM call per iteration.
Respond	Yes	Produces the final, user-facing answer once the loop decides the task is done. Freeform text by default; you can bake in a structured JSON schema on the step (Response Format in the step config), and callers can still override per request via `response_format` (see Agent Call) structured final response.

Configuring a step

Click any step in the pipeline to open its configuration:

System prompt: every step ships with Maitai’s default prompt template. Edit it to tailor the step to your agent; a badge on the step shows Default vs Customized, and you can reset back to the default at any time.
Model & parameters: each step runs as its own intent, so each can use its own model and hyperparameters. A common pattern: a fast, cheap model for Orchestrate and Process, and a premium model for Respond.

Guidance that previously lived in “special instructions” now belongs directly in the step prompts:

Prioritization logic, checklists before calling tools go in Orchestrate
How to interpret and synthesize capability results goes in Process
Tone, formatting, and response policy go in Respond
Structured JSON answer shape (schema) goes in Respond, under Response Format

Flow steps run through your Application like any other intent, which means each step shows up in request monitoring and can be independently fine-tuned over time.

Toggling optional steps

Process and Progress Probe have switches directly on the pipeline. Turning Process off trades context quality for latency; turning Progress Probe on trades latency for tighter loop control.

Per-request overrides (SDK)

You can toggle flow steps for a single request without touching the published agent, for example, skipping the Progress Probe on a latency-sensitive call:

agent = client.agent.get("YOUR_AGENT_NAME", version="prod")
agent.config.system_steps.progress = False

request = agent.to_request(messages=[...], session_id="YOUR_SESSION_ID")
response = client.agent.completions.create(request=request)

The step keys are orchestration, processing, progress, and respond. Overrides are validated against the published version and only whitelisted toggles apply (see Agent Call) per-request overlays.

Define the fields your agent maintains: Agent State
Full walkthrough: Build an Agent

​The pipeline

​Configuring a step

​Toggling optional steps

​Per-request overrides (SDK)

​Next

The pipeline

Configuring a step

Toggling optional steps

Per-request overrides (SDK)

Next