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 does.

While your import runs#

Pick your pages on the create flow's third screen and the import 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.

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 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 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.

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 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 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 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 queue still lists what's waiting on every agent; each row opens that agent's page, here.