Create an agent

Say what the agent should do and when. The AI in your project's Studio turns your words into steps and code and saves a draft. A draft never runs on its own, so you can try and change it freely.

Before you startCopy Anchor Link

• A project you can edit. The agent uses that project's data access.
• Data the project can reach: a table in Nexus, a folder in Object Storage, or a web address.
• Building needs no admin. Taking it live does (see Try, go live and pause).

Describe a new agentCopy Anchor Link

Open AgentsCopy Anchor Link

Go to Agents and select New agent. You can also open a project and use its Agents tab.

Pick the projectCopy Anchor Link

Choose the Project. Its data and access come from there.

Say what it should do, and whenCopy Anchor Link

In What should it do, and when?, name the data, what to do with each item, where to save the result, and when to start. For example:

Every morning at 7, read yesterday's rows in sales.orders, have AI flag any order that looks unusual with a one-line reason, ask me, then save the flags to sales.order_flags.

Select Ask the AI.

Let the AI build the draftCopy Anchor Link

The Studio AI writes the steps and code and saves a draft. If the Studio is not running, the app says Queued until the Studio opens.

Check the draftCopy Anchor Link

Open the agent to see its steps as a flow and what starts it. Click a step for its instruction, query, table, retries and time limit.

description: Summarise a table every morning
trigger:
  schedule: {at: "08:00"}
inputs:
  table: {type: string, default: my_table, description: The table to summarise}
steps:
  - {id: rows, kind: code, run: read_rows.py}
  - id: summary
    kind: ai
    needs: [rows]
    prompt: Summarise these rows for a busy manager in five short bullet points. Point out anything unusual.
result: summary

from klarety import Nexus, step

table = step.inputs()["table"]
if not table.replace("_", "").replace(".", "").isalnum():
    raise ValueError(f"{table} is not a table name")
with Nexus.connect() as lakehouse:
    rows = lakehouse.sql(f"select * from {table} limit 200").rows
step.output([dict(row) for row in rows])

klarety agent check daily-summary --project PROJECT_ID
klarety agent save daily-summary --project PROJECT_ID

nx.agents.ask_ai("PROJECT_ID", "Every hour, copy https://api.example.com/items into a table")

Change an agentCopy Anchor Link

What you see when it workedCopy Anchor Link

The agent appears under Not live yet, marked Draft, with Starts once live on automatic starts. Next, Try it runs the draft once, now.

Write a good descriptionCopy Anchor Link

• Name your data exactly: the table, the folder, or the web address.
• Say when it starts: a time and days, "when files arrive in invoices/", or "only when I press Run".
• Say where the result goes: a table, a file, or just a short summary.
• Ask for a check before anything important. Saying "ask me before saving" adds an Asks you first step.

If something goes wrongCopy Anchor Link

• "No project you can edit yet": you are not an editor of any project. Create a project or ask its owner.
• The request waits: the Studio is not running. The AI starts on it when the Studio next opens.
• klarety agent check reports a problem: the YAML has a mistake, and the answer says what. Fix the file and check again.
• "name the project with --project, or run this in its Studio": outside a Studio, pass --project.

Where to go nextCopy Anchor Link

• Templates
• Try, go live and pause
• Runs and approvals