---
title: "An agent's Overview"
description: "How complete one agent is, what to do next, and the box that teaches it."
source: https://hiy.ai/docs/agent-overview
---

# An agent's Overview

Open an agent — from the **Agents** list or the switcher — and this is the page it lands on. Everything here is about **that one agent**: no number on it covers your account, and none of them can, which is why nothing on this page carries a "across all 3 of your agents" line the way [your Dashboard](/docs/overview) does.

## While your import runs

Pick your pages on the create flow's third screen and the
[import](/docs/sources) starts there — you don't wait on it, and the flow
doesn't hold you. It reports on
itself here, and this panel is the only place that shows both halves of it.

**There are two jobs, the first one finishing is not "ready", and the second
one waits for you.** An import used to start indexing by itself the moment the
last page landed. It doesn't any more: a site holds plenty you would not want
your agent answering from, and the moment to say so is when you can see what
actually came in. So reading is automatic and indexing is yours to start.

| What you see | What is happening | Can it answer yet? |
| --- | --- | --- |
| **Reading your pages** | Every page is being fetched and its text pulled out. The count is real: pages walked, out of pages found. | No |
| **Indexing your material** | What was read is being turned into something answers can be built from. This is usually the longer half, and it is the same panel you'll see for any [training](/docs/training) run. | No — it keeps answering from what it already had |
| **Ready when you are** | The pages are stored and counted, and nothing is folding them in — this is where an import now stops and waits for you. A **Train on these** button is here, and it shows the word count before anything is spent. | No |
| **In, and answering** | Both jobs are done. | Yes |

**Reading fast does not mean ready soon.** On a real import, the reading
finished in about seven minutes and the indexing took another twenty-four. The
panel never says "indexed" until the second job has actually landed — that is
the whole reason it shows two phases instead of one.

**You can close the page.** Both jobs run on our servers. Come back and this
panel picks up where it is; it is not a progress bar that only exists while you
watch it.

**"Ready when you are" is normal, not an error.** It is where every import
ends: the pages are stored and counted, and they go in when you say so. (It is
also what you see when this month's [trains](/docs/training) are used up —
same panel, same pages waiting, and **Train now** tells you which of the two
you are looking at.)

**Walking away doesn't lose it.** An import you never came back to is picked up
by the overnight [train](/docs/training) like any other waiting change, so an
agent cannot quietly end up knowing nothing because a tab was closed.

### What didn't make it

Not every page comes back. A page whose text is drawn by JavaScript often has
nothing readable in the HTML we fetch; a dead link answers nothing at all. Any
page that didn't make it is listed here with its address and a short reason —
grouped, so eleven empty pages read as one fact about your site rather than
eleven separate mysteries.

**Try them again** re-runs just those pages as a fresh import, which waits to
be trained like any other import does. Once a page has been added — by the retry,
or by hand — it stops being listed. The panel stays for a day after the import
finishes so a failure is still there the next morning, then Knowledge and Train
own it.

### What you said you'd also bring

Setting the agent up asks where else your material lives. A site or a channel is
an address we can fetch, so those two are the import above. **Files, what your
assistant knows about you, and your lists can't be fetched for you** — a file
needs uploading, an assistant export needs you to review it fact by fact before
anything is kept, and a list is rows you type.

So they're asked for here instead, right under the import, with a button
straight to the place each one happens. Each disappears the moment you've
brought it, and if you didn't mention any of them there's nothing here at all.

## The setup bar

Six segments and a percentage, over the six things that turn a new agent into one people are actually talking to.

| Stage | Worth | Done when |
| --- | --- | --- |
| Claim your address | 10% | You made the agent — so nobody ever sees 0% |
| Add one strong source | 30% | One source exists |
| Ask it a question | 15% | You've tested it in the private chat |
| Teach it something it missed | 15% | You've saved a correction, or answered a queued question |
| Publish | 20% | It's published **and** cleared review — reachable, not just flipped |
| Share or embed it | 10% | You've shared it, or somebody has had a conversation with it |

**The segments are not equal widths**, and that's deliberate: each one is as wide as it is worth. What you see filled *is* the percentage, so the picture and the number can't tell you different things.

**Publishing doesn't count until it's reachable.** A published agent waiting on its identity check is live in your settings and a 404 to everyone else, so those 20 points wait for the clearance — the same rule the checklist below the bar has always used.

**It's a checklist, not a score.** Every point is attached to a step you can name, tick, and see ticked in the list underneath. hiy doesn't grade how *good* your agent is out of 100 — there's no honest denominator for that, which is why the readiness reading further down is still a sentence and not a number.

**If it can't be read, no bar is drawn.** A figure nobody could load is not a zero, and printing one would be inventing it.

## Set it loose

The same six stages as a list, with the first unfinished one open and a button that goes straight to where it happens. It disappears when all six are done, and it never comes back.

If the stages couldn't be loaded, the panel says so in one line rather than vanishing — a missing next step you can't see is worse than an error you can.

## Where this agent stands

A plain reading — *nothing learned yet*, *not published*, *learning your voice*, *getting there*, or *in good shape* — with the single most valuable next thing as a button, and the rest listed after it.

This asks a different question from the bar above it. The bar asks **have I finished setting this loose**, which is a checklist with six boxes. This asks **how good is it**, which is a judgement over your material, your voice and your scope — so it stays a sentence.

## Your hiy

Whether this agent is reachable, and the controls that change that: copy the link, get the embed, publish, or unpublish. The wording follows the agent's kind — a Support Agent is reached through your own site rather than at a public address, and a Team Agent has no public page at all.

A draft with nothing to answer from is told **what's missing** where the button would be, rather than being offered a press that would be refused. If everything you've added is held back, or your first import is still queued, it says that instead — those need opposite next actions.

## Recent conversations

The last four conversations **this agent** had, newest first — the visitor's
first question, how many messages it ran to, and when. [Activity](/docs/activity)
opens any of them in full, and covers every agent rather than this one.

It sits directly above the teach box on purpose: the questions in that box are
the ones these conversations couldn't answer.

**A Team Agent has no such section, and that is the promise rather than an
omission.** [Team Agents](/docs/team-agents) keep no per-conversation trail —
your colleagues are told so, and nothing in hiy will show you one, here or
anywhere. You are not shown an empty box either, because an empty box would
suggest the trail exists and is merely missing today. Insights still counts what
a Team Agent answered, and which topics came up; what it never produces is a row
per conversation. [What hiy can and can't see](/docs/for-visitors) is the whole
statement.

## The teach box

Unanswered visitor questions land here. Answer one in your own words and it becomes an authoritative correction your agent uses from then on; dismiss it and the question closes without one.

**It lives on this page, not on your Dashboard, and that's a correctness fix rather than a tidy-up.** Answering writes a correction against *this* agent. On an account-wide page a pooled queue would have taught whichever agent happened to be selected — so the queue sits on the page that names the agent it belongs to. Your Dashboard's [**Needs you**](/docs/overview) queue still lists what's waiting on every agent; each row opens that agent's page, here.

- **Since you last looked** — New conversations, people waiting for a reply, and questions queued — counted since your previous visit, for this agent. Per-device, because it's a recency cue rather than an account setting.

- **Awaiting review, and not approved** — Both states get a panel at the top of this page saying who can't reach the agent yet and what actually happens next. Neither promises you an email.

- **Starting points** — With no sources yet, one field sits above the checklist so the first source can be added from here. It disappears the moment one exists.

- **No money on this page** — Your plan, your usage and your trial countdown are account facts, so they live on [your Dashboard](/docs/overview). Four agents each showing the same trial banner is one deadline shouted four times.