Festi Harness: The AI Agent Harness That Runs Agent Mode

Let AI agents operate your platform, with your permissions, your approvals and a full record of every step.

Festi Harness is the AI agent harness of the Festi Agentic AI Platform. It runs Agent Mode, the assistant inside the platform that does real work for a signed in user: it reads data, starts jobs, hands tasks to other agents and reports back. The harness turns one message into a governed run, drives the language model and a curated set of tools, asks a person before anything risky happens and streams what it does to the browser.

Festi Harness AI agent harness: Agent Mode calls the agents.list tool and shows the agents of the project as a table in the conversation

Why You Need an AI Agent Harness, Not Just a Chat Window

A chat bot that can call tools is easy to demo and hard to trust. Once an assistant can change records, start pipelines or message other systems, every question an engineering lead asks is about control:

  • Which tools can it use, and in which project?
  • Does it act with its own rights or with the rights of the person who asked?
  • What happens when a tool returns text that looks like an instruction?
  • Who approves a delete, a payment or a message to an outside service?
  • What did it do, step by step, and what did it cost?

An AI agent harness answers those questions in code, not in a prompt. Festi Harness wraps every model turn and every tool call in rules that the model cannot talk its way around, so your team can let an agent operate internal tools without handing it the keys.

What the Festi AI Agent Harness Does

Acts Only Through the Tools It Is Given

A run sees only the tools that pass the harness rules. A platform tool must declare that it is meant for Agent Mode, carry a known risk level and have an input schema the harness can check. A project can narrow the list further with an allowed list of its own. Generic platform methods that would let a model reach anything are refused by name.

Works With Your Permissions, Inside One Project

Every tool call is made as the signed in user, in the project of the conversation, with a short lived delegation token that the host application signs. If the user cannot do something, the agent cannot do it either. A call that names a different project is refused before it leaves the harness.

Asks a Person Before Anything Risky

Each tool has a risk level, from read only through writes and deletes to external communication, financial and admin actions. A project decides what a person is asked about. Without a policy, a read runs on its own and every other risk level asks a person. A tool can also declare its own rule. A risky call stops the run and shows an approval card. The run continues only after someone approves it, and an approval answered in another browser tab is picked up too.

Treats Tool Output as Data, Never as Instructions

Text that comes back from a tool, or from another agent, is fenced between marked boundaries before the model reads it. The closing marker carries a one time value, so a tool result cannot fake the end of the fence. An instruction hidden in a web page, a record or an agent answer stays data, and the model never follows it. Long results are cut for the model, and the full result is kept as an artifact.

Reports Refusals Plainly

When a tool refuses a call, for example because the user lacks permission or the input is invalid, the harness stores the reason and gives it to the model. A refused call is never repeated automatically, and the agent tells the user what was refused instead of looking for a way around it.

Keeps Secrets Out of the Record

A platform tool can mark an argument as secret. The real value goes to the tool call and nowhere else: the stored tool call, the approval card, the conversation and the live stream all show a mask instead.

AI agent permissions in Festi Harness: Agent Mode refuses a request for another project, and a failed tool call is explained plainly to the user

Shows Results Instead of Repeating Them

Tool results can render as tables on screen, so the assistant does not have to repeat a list of records in its own words. The user sees the data, and the answer stays short.

AI Agent Harness Guardrails You Can Measure

Every run has limits, and the host can tune them per project. The defaults:

GuardrailDefault per run
Model turns25
Tool calls50
Run time30 minutes
Tokens400,000
Cost2.00 per run and 25.00 per project per day, when a model price list is configured
Identical tool calls in a row3, then the loop detector stops the run

When a run reaches a limit it stops and says so in the conversation, rather than running up a bill in the background.

Multi Agent Work and Background Jobs in One Conversation

Real operations work rarely finishes in one reply. Agent Mode can hand a task to another agent on the platform, wait for it, read its answer and relay the questions that agent asks back to the user.

Festi Harness agent runtime: Agent Mode hands a task to another agent and relays the agent's question to the user

A tool can also start work in the background, such as a data pipeline or a long running agent task. When that work ends, the result comes back into the same conversation. If no run is active at that moment, the AI agent harness starts one to read the result and explain it, including what went wrong and what would fix it when the work failed.

AI agent harness background job: a finished agent task reports its result back into the Agent Mode conversation

How the AI Agent Harness Works

Festi Harness runs next to the host web application as three small processes, with the database as the single record of everything that happens.

  1. A message becomes a run. The user writes in Agent Mode. The host application queues a run and seals a delegation token for it.
  2. A supervisor starts one worker per run. The supervisor claims queued runs and starts a separate worker process for each one, so a fault in one run cannot stop another.
  3. The worker drives the model and the tools. It calls the model, checks each tool call against the rules above, asks for approval where the policy requires it, calls the tool over MCP and stores every step before it publishes it.
  4. The browser follows live. An event gateway streams each step to the browser over Server Sent Events. A browser that reconnects gets the stored events first and then the live ones, so nothing is lost.
  5. Recovery is built in. Workers renew a lease while they run. If a worker dies, the supervisor takes the run over and tries again a limited number of times, and runs that nothing carries any more are ended with a clear reason.

An Agent Runtime That Works With Your Models and MCP Tools

Models

Anthropic, OpenAI and Gemini protocols, plus model servers of your own that speak one of them, including a model server on your local network. The model library sits behind one interface, so changing a provider never touches the run logic.

MCP Tools

The worker is an MCP client. It calls the platform's own MCP endpoint, and each project can register outside MCP servers. A registered server gets its own credential, never the user's delegation token, and every call to it needs an approval.

Audit

Threads, messages, runs, steps, tool calls, approvals, notices and events are stored in MySQL or MariaDB tables. Each run records its cost.

Stack

A PHP 8.2+ package that a Festi host application installs, with MySQL 8.0+ or MariaDB 10.11+, RabbitMQ for live events and Swoole for the event gateway.

Festi Harness builds on the same foundations as the rest of Festi, including Web API Services and Asynchronous PHP Services and Daemons.

Who the AI Agent Harness Is For

Engineering Leads and CTOs

You want AI agents to take routine operations off your team without creating a new risk surface. The harness gives you permissions, approvals, budgets and an audit trail that you can explain to security and to the business.

Platform and DevOps Teams

You run the internal tools and the dev platform. Agent Mode lets people start pipelines, check jobs and query data in plain language, while every call still passes through the same permissions and project boundaries as the user interface.

Teams Building on Festi

Festi Harness ships as part of the Festi Agentic AI Platform. Your platform publishes tools over MCP with a risk level and an audience, and the harness takes care of the run, the approvals, the stream and the recovery.

AI Agent Harness Use Cases

  • Operate the data platform by chat: "Run the evaluation pipeline on last week's dataset and tell me when it is done." The job runs in the background and reports back into the conversation.
  • Coordinate agents: ask Agent Mode to hand a research or coding task to a specialised agent, then answer that agent's questions without leaving the thread.
  • Answer questions from live data: list records, compare runs or check job status, with the result shown as a table.
  • Controlled changes: let the assistant prepare a change and approve it on a card before it is made.

The Festi Coder Model and the AI Assistants and Automation Tools cover the model and assistant side of the same platform. For a platform built and run this way, read the Harvesting Data Platform case study.

AI Agent Harness FAQ

Festi Harness is the AI agent harness of the Festi Agentic AI Platform. It runs Agent Mode: it turns a user's message into a run, drives the language model and the platform tools, asks a person before risky actions and streams every step to the browser.
An AI agent harness is the runtime around a language model that decides which tools the model can use, checks every call, enforces limits, records what happened and recovers when something fails. The model proposes actions, and the harness decides whether they run.
No. Every tool call runs with the permissions of the signed in user, inside the project of the conversation. A call that targets another project is refused.
Tool results and answers from other agents are fenced as untrusted data before the model reads them, with a closing marker that a tool result cannot fake. The model treats that text as information, not as instructions.
Anthropic, OpenAI and Gemini protocols, plus your own model servers that speak one of them. Tools come over MCP, from the platform's own endpoint and from MCP servers a project registers.
Festi Harness comes with the commercial Festi Agentic AI Platform subscription.
Each project decides. Tools carry a risk level, and the project's approval policy says which levels need a person. Without a policy, a read runs on its own and every other risk level asks a person. A tool can also declare its own rule, and calls to registered outside MCP servers always need an approval.

Put Your AI Agents on a Harness

Festi Harness is part of the Festi Agentic AI Platform, which is in early access. Tell us which internal tools you want an agent to operate, and we will show you Agent Mode working on them with your permissions and approvals in place.