Tutorial 07

Create an agent from scratch

Why this matters

In Tutorial 01, we said the Admin Agent’s job is helping you build the agents that handle your business’s actual work. This is that moment. Every business has work that keeps slipping — the research nobody has time for, the follow-ups that fall through cracks, the roles you’ve been meaning to fill. Today you build the first agent that picks one of those up. Not “an AI assistant” — a specific teammate, with a specific job, asked to do specific things in specific ways.

You describe the work you want offloaded; the Admin Agent asks the right questions, builds the agent for it, and points you at the right places in Auxot to wire up everything that agent needs. By the end of one conversation you have a working custom agent, named and configured. Then you give it work and it does it.

Quick start

1. Sign in — open Auxot in your browser and log in.
2. Open chat with the Admin Agent — click Chat in the left menu, make sure the agent picker reads “Admin Agent.”
3. Describe the work you want offloaded — type something like “I want an agent that drafts customer support replies in our brand voice” and press Enter.
4. Answer the Admin Agent’s questions — it will ask what tools the agent should have, any rules it should follow, and what to call it. Two or three exchanges, usually.
5. Confirm — the Admin Agent proposes the full configuration. Say “yes, create it” (or whatever feels natural). The agent is created on the spot.

Done? Your new agent is now in Settings → Agents — and selectable from the agent picker in chat. Send it a message to verify it works.

The agent can do that?

You built one agent. These three prompts make sure it’s actually doing the work — and getting better at it.

1. Have your new agent describe its own job back to you

Open chat with the agent you just built and ask:

In two or three sentences, describe what you're for and what you'll never do. Then list the three kinds of questions you're best at answering. Be specific.

Why it’s non-obvious: This is your sanity check. If the agent’s answer matches what you wanted, you’ve built it right. If it doesn’t, you’ve found exactly which part of the description or context files needs tightening — and you can fix it in two minutes (Tutorial 05 covers the editing). Most people skip this step and end up six conversations later realizing the agent has been confidently doing the wrong job.

2. Have the Admin Agent recommend the next agent to build

Once your first agent is working, head back to chat with the Admin Agent and ask:

I just built [agent name and one-line job]. Looking at the kinds of work that get done in a [your business — e.g., "small marketing consultancy"], what's the next agent I should build to keep getting more out of Auxot? Recommend one specific agent — name, description, what context files it would need — and tell me why it's the next one.

Why it’s non-obvious: Most people stop after their first agent because the second one feels like another full setup. The Admin Agent’s specialty is exactly this — recommending the next agent based on what you’ve already built and what kind of business you run, with a description specific enough that you could create it in one more conversation. You go from “I built an agent” to “I have a small team of agents” three weeks faster than figuring it out yourself.

3. Build the agent that improves your other agents

Inverted-usage move. Once you have two or three custom agents, ask the Admin Agent:

Build me an agent whose job is reading the descriptions and context files of my other agents and telling me where they're vague, where they overlap, and where any description could be tightened. Call it "Agent Reviewer." Give it a clear job description and make it ready to use.

Why it’s non-obvious: You don’t have to do agent housekeeping yourself. Build an agent that does it for you, and run it once a month. This is what becomes possible once the first agent is built — you’re not just delegating customer emails or contract reviews, you’re delegating the meta-work of keeping your agent system clean.

Go deeper

Picking a good first agent

A useful agent has a clear sense of what work it takes on, what voice it uses, and what it should never do. Scope can be narrow (one specific recurring task) or broad (a role with several related tasks) — both work. The fix when an agent feels generic is rarely “narrow the scope.” It’s “say what the agent should do, in what voice, and what it should never do.” Tutorial 05 has examples of descriptions that work at both scopes.

If a single agent’s description starts feeling like “and also…” over and over, that can be a sign to split it into two more focused agents — not because broad scope is wrong, but because the constraints stop fitting into one description.

How the Admin Agent actually creates the agent

When the Admin Agent says “I’ll create it now,” what happens behind the scenes: it makes a single internal tool call that writes the agent’s name, description, instructions, preferred AI model, attached context files, and tool policy at the same time — atomically. Either everything lands, or nothing does. The agent appears in your list with everything connected.

Troubleshooting

• The Admin Agent kept asking questions and never created the agent. Sometimes the conversation runs longer depending on how much specificity you brought. If you’ve been at it for five exchanges and want to just create something, say “propose the configuration now and create it.” The Admin Agent will lock down what it has and create the agent.
• The agent answers in the wrong tone or style. Its description or attached context files need work. See Tutorial 05.

Variations & edge cases

• Free tier: unlimited custom agents. The only thing Free tier can’t do is split them across multiple teams (Free is single-team).
• Visibility scope: on Business and Enterprise, agents can be Team-scoped (only that team sees them) or Org-scoped (everyone in the org). Set this on the agent’s detail page after creation.
• Editing later is fast. Everything about the agent — description, attached context files, tool policies, name — is editable on its detail page. Auto-save means no Save button.
• Deleting an agent. Settings → Agents → trash icon on the row. Deleted agents are gone permanently; the chat threads with that agent stay (they’re tied to your user, not to the deleted agent).
• The Admin Agent itself is locked. You can’t create “another Admin Agent” — it’s the one built-in agent that ships locked. To get an Admin-Agent-shaped agent that you control, build a custom agent with a similar job description and similar context files.

Walkthrough

There are two ways to create an agent in Auxot:

• The Admin Agent path (recommended). You chat through it. The Admin Agent asks the right questions, writes the agent’s description and instructions for you, and creates it on the spot.
• The Settings UI path (faster, less guided). Best when you already know exactly what you want. Covered as a single paragraph at the end since it overlaps heavily with Tutorial 04 (context files), Tutorial 05 (description), and Tutorial 08 (tool policies).

Path A: Build it through the Admin Agent

Step 1: Open chat with the Admin Agent

Click Chat in the left menu. Make sure the agent picker at the top reads “Admin Agent.”

Step 2: Describe the work you want offloaded

Don’t worry about phrasing it perfectly — the Admin Agent’s job is to ask the questions that turn your description into a real agent. Something like:

• “I want an agent that drafts customer support replies in our brand voice.”
• “I need an agent that reads our weekly leadership minutes and tells me what’s drifting.”
• “I want an agent that reviews contracts for compliance with our standard terms.”

The more concrete, the better. “I want a marketing agent” is too vague — what kind of marketing? Who for? What does it produce? The Admin Agent will ask if you start vague, but the conversation goes faster when you bring the specifics with you.

Step 3: Answer the Admin Agent’s questions

This usually takes two or three exchanges. The Admin Agent works through:

• What it should do — the agent’s actual job. The Admin Agent will sharpen what you said in Step 2 into a one-line description.
• What tools it should have — does it need to read external websites? Send Slack messages? Look up data in your CRM? The Admin Agent shows what’s available and helps you pick.
• What it should never do — hard rules, escalation paths, things that would get a new hire fired on day one.
• What to call it — a clear name that anyone scanning the agents list will recognize.

Tip: Treat each exchange like you’re hiring a new employee. What would the new hire need to know on day one? What would get them fired? That’s the level of specificity that produces agents that actually work. If the Admin Agent proposes something that doesn’t fit, say so — it’s a conversation, not a form.

Step 4: Confirm the configuration

When the Admin Agent has enough, it proposes the full configuration: name, description, instructions, tools, anything else relevant. Read it. If it looks right, say “yes, create it” (or anything similar — the Admin Agent picks up on intent, not magic words). The agent is created on the spot. The Admin Agent will tell you it’s done and where to find it.

Step 5: Find your new agent and test it

Two places it now lives:

• Settings → Agents — your new agent appears in the agents list. Click it to see and edit anything.
• Chat picker — the new agent is selectable in the agent picker at the top of the chat window.

Open chat with your new agent and try it on a real task. If the answers feel off, head to Tutorial 05 to refine the description and attached context files.

Tip: If you want this agent to always use a specific model (Claude, GPT-4, your local GPU), tell the Admin Agent when you’re setting it up — it sets the preferred model at creation time.

Path B: Build it through Settings → Agents

Click Settings → Agents → +Add Agent, fill in Name, Description, and Team, and click Create. The agent appears on its detail page where you wire up the rest: description (Tutorial 05), context files (Tutorial 04), and tool policies (Tutorial 08). The agent is chattable from the moment you click Create — it just won’t have specialized knowledge or instructions until you wire those up. Faster than Path A, but only worth it when you already know exactly what you want.

What’s next

• → Tutorial 04: Add your first context file — if your new agent doesn’t have any business knowledge yet, this is the next step.
• → Tutorial 05: Give your agent its job description — refine the description as you learn what your new agent does well and where it drifts.
• → Tutorial 08: Define a tool policy — give your agent real-world capabilities (search, code, internal APIs) on top of its context files.

Reference

• Pages in Auxot: Chat, Settings → Agents
• Two creation paths: Admin Agent (chat-driven, recommended) | Settings → Agents → Add Agent (form-based, faster)
• Required at creation: Name. Everything else can be filled in later.
• Admin Agent path also sets: Description, instructions, preferred AI model, context files, tool policy — all in one atomic call
• See also: Tutorial 04: Add your first context file, Tutorial 05: Give your agent its job description, Tutorial 08: Define a tool policy