Agentic & Tool-Use

HALO

HALO organizes a team of agents into three tiers that mirror how an organization tackles a hard project: a planner breaks the task into pieces, role designers decide who is needed and instantiate the right specialist agents, and inference agents do the work. It searches over possible action paths with a tree-search method and refines the prompts along the way, so complex tasks are handled by a purpose-built team rather than a single generalist.

*These are learning tools, not prompts. They teach you to write your own, think of them as training wheels that guide you while you learn, then fall away once you can ride on your own.

The Core Insight

Build the Team, Then Do the Work

Many multi-agent systems fix their roles in advance: a coder, a reviewer, a planner, decided by the designer before the task is known. That is brittle. A task may need a role nobody anticipated, or too many of a role that turns out not to matter. HALO's insight is that the team itself should be designed for the task at hand, not assumed ahead of time.

It arranges agents into three tiers. A high-level planning agent decomposes the task into subtasks. Mid-level role-design agents look at those subtasks and instantiate the specific specialist agents each one needs, creating the right roles on demand. Low-level inference agents then carry out the work. Responsibility flows down a clear hierarchy, from strategy to team design to execution.

To choose well among the many ways a task could unfold, HALO searches the space of possible actions with Monte Carlo Tree Search, exploring and scoring paths rather than committing to the first one. An adaptive prompt-refinement step turns the user's request into well-shaped task prompts for the agents. The result is a logic-oriented orchestration that assembles a fit-for-purpose team and searches for a good way through the task.

Three Tiers, Roles on Demand

HALO's hierarchy is plan, design roles, execute. The planner decomposes the task, role-design agents instantiate the specialists each subtask needs, and inference agents do the work. Tree search over actions and adaptive prompt refinement guide the choices, so the team fits the task instead of being fixed in advance.

The HALO Process

Plan, design the roles, search the actions, and execute

1

Plan at the Top Tier

A high-level planning agent reads the task and decomposes it into subtasks. This top tier sets the strategy, deciding what needs to happen without yet deciding who does it or how.

Example

Task: produce a market brief. Subtasks: gather data, analyze trends, draft the brief, review for accuracy.

2

Design Roles at the Middle Tier

Mid-level role-design agents examine each subtask and instantiate the specialist agents it needs, creating roles tailored to the work rather than drawing from a fixed roster. The team is assembled to fit the task.

Example

"Analyze trends" spawns a data-analyst agent; "review for accuracy" spawns a fact-checker agent.

3

Search the Action Space

HALO explores possible sequences of actions with Monte Carlo Tree Search, scoring paths and favoring promising ones instead of committing to the first idea. An adaptive step refines the prompts given to the agents as it goes.

Example

The search compares gathering data before analysis versus analyzing partial data first, and keeps the ordering that scores better.

4

Execute at the Bottom Tier

Low-level inference agents carry out the chosen actions, each playing the specialist role it was instantiated for. The hierarchy delivers the finished result, having planned, staffed, and searched before doing the work.

Example

The data-analyst agent produces the trend analysis, the fact-checker verifies it, and the brief is assembled.

See the Difference

Fixed roles versus a team designed for the task

Fixed-Role Team

Roles Set in Advance

The designer picks the agents and their roles before seeing the task. If the task needs a different mix, the team cannot adapt.

Effect

A mismatch between the fixed team and the actual task leaves gaps or wastes agents on work that does not matter.

Team may not fit the task
VS

HALO

Roles Designed for the Task

A planner decomposes the task, role designers instantiate the specialists it needs, and a tree search picks a good action path.

Effect

The team is fit for the task, and the search plus prompt refinement guide it toward a strong way through the work.

Purpose-built team, searched execution

Practice Responsible AI

Always verify AI-generated content before use. AI systems can produce confident but incorrect responses. When using AI professionally, transparent disclosure is both best practice and increasingly a legal requirement.

Most US states are actively legislating AI transparency and accountability. Critical thinking remains your strongest tool against misinformation.

HALO in Action

See how the tiers assemble a team and search the work

Task

"Produce a compliance-ready summary of a new regulation," which unexpectedly needs a legal-interpretation role.

HALO Response

Plan: read the regulation, interpret the legal requirements, summarize, check compliance.

Design roles: the middle tier instantiates a legal-interpreter agent that a fixed roster would not have included.

Execute: the tailored team produces an accurate, compliance-aware summary.

Choice

Should the team validate inputs before or after the main analysis? Both orders are plausible.

Tree Search

HALO explores both paths, scoring how well each leads to a correct result.

Result: it finds that validating inputs first avoids wasted analysis on bad data, and keeps that ordering, rather than guessing.

Input

A vague user request that would confuse a specialist agent if passed along as-is.

Adaptive Prompt Refinement

HALO rewrites the request into a clear, well-scoped task prompt for the relevant agent.

Result: the specialist receives instructions it can act on precisely, improving the quality of its output.

When to Use HALO

Best for complex tasks that need a tailored team of agents

Perfect For

Complex, Multi-Part Tasks

Jobs that need several specialties benefit from a middle tier that instantiates exactly the roles the task calls for.

Unpredictable Role Needs

When you cannot know in advance which specialists a task will require, designing roles on demand beats a fixed roster.

Many Possible Approaches

When a task can be tackled several ways, searching the action space finds a strong path instead of committing to the first one.

Accuracy Over Speed

When getting it right justifies more compute, the planning, role design, and search pay off with a more reliable outcome.

Skip It When

Simple Single-Agent Tasks

If one agent handles the job, standing up a three-tier hierarchy is heavy machinery for a light task.

Tight Latency or Cost Limits

Planning, role design, and tree search all cost model calls, so strict speed or budget limits may rule the approach out.

Well-Known Fixed Roles

If the ideal team is already obvious and stable, a simpler fixed-role setup avoids the overhead of designing roles each time.

Use Cases

Where HALO delivers the most value

Complex Analysis

Assemble the right specialist agents for a multi-faceted analysis, instantiating roles the task reveals rather than guessing them up front.

Document Production

Coordinate research, drafting, and review agents to produce reports, with the middle tier adding roles like fact-checking when needed.

Decision Support

Explore multiple approaches to a complex decision with tree search, keeping the path that scores best across the team's work.

Software Projects

Spin up the design, implementation, and testing roles a coding task needs, adding specialists like a security reviewer when the work calls for it.

Adaptive Orchestration

Run multi-agent systems where the ideal team is not known in advance, letting the hierarchy design it from the task.

Reliability-Critical Work

Spend extra compute on planning, role design, and search where a correct outcome is worth more than a fast one.

Where HALO Fits

Hierarchical orchestration in the multi-agent family

Agentic Prompting Agents That Act Reason, act, observe
LATS Search a Single Agent Tree search over actions
HALO Three-Tier Orchestration Plan, design roles, execute
MAS-squared Self-Configuring Systems Agents that build agents
Chain These

Where LATS applies tree search to a single agent, HALO applies planning and search across a hierarchy that designs its own team. Reach for it on complex tasks whose ideal set of specialist roles is not known in advance.

Design the Team for the Task

Explore how planning and role design shape a multi-agent system in the Prompt Builder, or see related agentic techniques.