Turning training on and managing access

Training is off in a new workspace. Nobody sees a thumbs-up, a comment chip or a Train button until an admin turns it on — one checkbox, and the controls appear for everyone immediately, with no need to sign out and back in.

This guide is the admin side of the loop: switching it on, understanding exactly what switching it off does, giving your team access to the review surfaces, and shaping how the Curator interprets what people write. If you are here to leave a correction rather than to configure the feature, read Your first correction, step by step instead.

Two independent gates

Almost every "why can't they see it?" question here comes from confusing two separate controls. They are not the same setting and they do not substitute for each other:

flowchart TD
    A["Can this person train an agent?"] --> B{"Workspace switch:<br/>Agent Feedback &amp; Training"}
    B -->|Off| C["Nobody sees any controls.<br/>Not a permission problem."]
    B -->|On| D["👍 👎 and comment chips appear<br/>for EVERY signed-in person"]
    D --> E["Train the AI shows what THEY taught<br/>— no permission needed"]
    D --> F{"Role permission:<br/>quality:events:read"}
    F -->|Missing| G["Quality Events refuses to open.<br/>Fix the ROLE, not the switch."]
    F -->|Held| H["Training threads opens —<br/>the whole team's corrections, read-only"]
    H --> I{"Role permission:<br/>quality:events:manage"}
    I -->|Held| J["Can also resolve OTHER people's threads,<br/>promote, dismiss, mute topics"]

The switch is workspace-wide and is what this page turns on. The two permissions are per-role and live in Roles & Permissions.

What you'll need

Tenant admin on the workspace. The settings pages below are admin-only; everything under Give your team the team view also needs the ability to edit roles.
Nothing else. Training needs no sending domain, no phone number, and no connected model of your own — it runs on the agents you already have.

Turn training on

Path: top bar → Settings → Agents & AI → Agent Feedback & Training

The navigation is a bar across the top of the app; there is no sidebar. Under Agents & AI you will find eight settings — the one you want is Agent Feedback & Training, described as "Let your team correct agents on the words they said".

The Agents & AI section of tenant settings. The Agent Feedback & Training row shows a status of On, and Curator Prompt below it reads Customized.

Open Agent Feedback & Training.
Tick Enable Agent Feedback & Training.
Wait for the confirmation line. When it turns on it reads, in full: "Training is on. Thumbs and comment controls now show on agent conversations, and corrections flow to Train the AI and Quality Events."

That is the whole task. The controls appear for every signed-in person straight away — the page refreshes your workspace's settings for you, so nobody has to sign out and in again.

The Agent Feedback & Training settings page, with the Enable Agent Feedback & Training checkbox ticked, the explanatory sub-text, and the What this turns on list.

Confirming it is on

Two places tell you, and they should agree:

The settings list shows a status of On beside Agent Feedback & Training (visible in the first screenshot above).
The checkbox on the page itself is ticked.

If the page shows an error such as "Failed to fetch agent feedback setting", the control is disabled and offers Retry. That is deliberate: a failed read must not render as an unticked box, because you could then save a value you had never actually seen. Click Retry rather than ticking anything.

What "off" actually does

Turning training off is safe and reversible, but it is worth knowing precisely what it does — the confirmation line is deliberately specific:

"Training is off. The training controls are hidden; existing threads and quality events are kept."

Turning training off	Effect
👍 / 👎 on agent messages	Hidden, on every surface — calls, chat, SMS, email, task runs
The highlight-to-comment chip	Hidden
The Train button on a conversation	Hidden
Threads your team already submitted	Kept, and still readable on Train the AI
Knowledge already published from corrections	Kept — nothing is unpublished or deleted
Quality events already recorded	Kept

A voice call transcript with training switched off: the agent messages carry no thumbs-up, thumbs-down or comment control, and the Train button is gone from the header.

So switching off stops new corrections being captured. It does not erase what your team has already taught, and turning it back on restores every control exactly as it was.

It applies workspace-wide and immediately. There is no per-agent or per-team override. If you switch it off while colleagues have conversations open, their controls disappear on the next page load.

Give your team the team view

This is the step most workspaces miss, and the symptom is specific: a colleague opens Quality Events and gets a full-page

You don't have access to this page Your role doesn't include it. A workspace admin can grant access — it's a per-role setting…

A team member's view of Quality Events before the permission is granted: a full-page notice explaining that their role does not include this page and that an admin can grant access.

That message is accurate, and it is a role setting, not the training switch. Turning training on does not by itself let people see what the team has submitted. Two different things are involved:

Surface	What it shows	What it needs
Train the AI (`Agents → Workflows → Train the AI`)	Only what you submitted, and what became of it	Nothing — every signed-in person can open it
Quality Events → Training threads	What everybody submitted	`quality:events:read`
Mark resolved / Reopen on someone else's thread	Closing a colleague's thread	`quality:events:manage`

Why a long-standing workspace may be missing it

The Member, Viewer and Manager role templates all include quality:events:read. But default roles are created once, when the workspace is created, and are never rewritten afterwards. A workspace that existed before this permission was introduced therefore has roles that predate it — the template says one thing, the role in your workspace says another.

Check before assuming. It takes a few seconds.

Path: top bar → Settings → Roles & Permissions

Find the role in the list — Member is the default one most people hold.
Click the pencil icon to edit it.
Scroll to the QUALITY section.
Look at View Quality Events (quality:events:read).

The role permission editor open on the Member role, showing the QUALITY section with View Quality Events and Manage Quality Events both unticked.

If it is unticked, that is your answer. Tick View Quality Events and click Save Changes.

Grant read, not manage. quality:events:manage also lets someone resolve other people's threads, promote and dismiss events, mute topics and change the anonymised-sharing setting. Most teams want everyone to see the team's corrections and only reviewers to act on them, which is read without manage.

What your team sees afterwards

Once the role carries quality:events:read, three things appear for those people, immediately:

Quality Events joins their Agents → Workflows menu.
A Team training link appears in the header of their Train the AI page.
The Training threads tab opens and lists everybody's corrections.

A team member's Train the AI page after the permission is granted, with a Team training link now present in the header.

They still get no Mark resolved or Reopen buttons anywhere on that page — not even on their own rows — because the team view is uniformly read-only without quality:events:manage. They close their own threads from their own Train the AI page instead.

A member's view of the Training threads tab: eighteen threads including other people's, with no Mark resolved or Reopen buttons anywhere.

Shape how the Curator reads corrections

Path: top bar → Settings → Agents & AI → Curator Prompt

The Curator is the AI that reads each correction and decides whether it is a durable business fact, a change to how an agent speaks, or a one-off detail. This page is where you influence that judgement. It appears in the settings list only once training is enabled.

The page gives you the model in use, its reasoning effort, and:

Load built-in default — pull the shipped prompt into the editor as a starting point.
Save prompt — store your version. The list then shows Customized.
Clear override — go back to the built-in prompt.

The built-in default is shown read-only alongside your version, so you can always see what you have changed relative to it.

Change this sparingly. The built-in prompt is what makes receipts consistent and keeps one-off details out of your knowledge base. A good reason to edit it is house vocabulary — telling the Curator what your business calls things. A bad reason is trying to force every correction to become knowledge; that is what fills a knowledge base with sentences that were only ever true once.

Troubleshooting

"Nobody can see any thumbs or comment chips." Training is off, or was switched off. Settings → Agents & AI → Agent Feedback & Training, and check the status reads On.

"A colleague gets 'You don't have access to this page' on Quality Events." A role permission, not the training switch. Follow Give your team the team view above and check quality:events:read on their role.

"Someone can see the Training threads tab but has no Mark resolved buttons." Working as intended. That page is read-only without quality:events:manage, including on their own rows. They can resolve their own threads from Agents → Workflows → Train the AI.

"A correction was filed as 'one-off' and I expected it to become knowledge." Also working as intended, and usually correct — see What happened to your feedback. If it keeps happening on corrections that really are durable facts, that is a signal to look at the Curator Prompt.

"The Curator Prompt entry is missing from settings." It is only listed once training is enabled. Turn training on first.

Next steps

Reviewing what your team teaches — the day-to-day reviewer workflow, and how much your agents may publish on their own.
Quality Events and the Curator queue — the full quality stream, topic muting, and approving a prompt change.
Training your AI agents — the hub, including what your team sees in each role.