Documentation Index
Fetch the complete documentation index at: https://docs.adclear.ai/llms.txt
Use this file to discover all available pages before exploring further.
Overview
Every comment you respond to in Adclear does two things at once. It moves your promotion forward, and it teaches Adclear’s agents what compliance looks like in your organisation. Skip a response, leave a one-line reaction, or click through without context, and the agents do not learn. The mechanics of commenting are covered in the Marketing User Guide and the Compliance User Guide. This guide focuses on why how you respond matters, and how to make sure the right people hear about issues.Throughout this guide we use submitter for the person uploading a promotion, and reviewer for the person assessing it. The two roles interact with comments differently, and that difference matters.
Before You Start
You will need the right access to do any of this. The table below shows who can submit, who can review, and where to look for full role detail.| You need to… | Minimum role | Where it is covered |
|---|---|---|
| Upload a promotion and respond as the submitter | Marketing, Marketing Admin, Compliance, Compliance Admin, Legal, or External Influencer | Marketing User Guide |
| Review a promotion and respond as the reviewer | Compliance or Compliance Admin | Compliance User Guide |
| Resolve an escalation | Legal | How Roles Work |
Tag @adclear-support on a comment | Any role with access to the promotion | This guide |
| Open the Get Help bot to log a question, bug, or feature request | Any logged-in user | This guide |
Why Your Comments Matter
Adclear is not a static rules engine. It is a set of agents that get sharper every time someone tells them whether a flag was right or wrong, and why. The “why” is the part most teams miss, and it is the part that actually trains the agents. Three things happen every time you click a response button:The promotion moves forward
Your response unblocks the next step. The reviewer can decide, the submitter can resubmit, or the asset can be approved.
The other person gets context
Submitters see why a flag matters. Reviewers see why a dispute is reasonable. Without context, both sides have to guess.
The agents learn
Adclear’s agents watch the response, the reasoning, and the outcome, then adjust how they flag similar content in future.
The agents are weighted toward reviewer responses
This is the most important thing to understand about how Adclear learns. When a submitter and a reviewer disagree on a comment, the reviewer’s response carries more weight in how the agents adjust. That has two practical consequences:- Submitters cannot quietly silence a flag. Disputing a regulatory comment without supporting context simply sends it to the reviewer to adjudicate. The reviewer’s call is what counts.
- Reviewers carry the responsibility for shaping the agents. A reviewer who clicks through with no rationale is not just slowing down the next reviewer. They are missing the chance to teach Adclear something it can reuse on every future promotion.
How Each Side Responds
The three response options look similar between submitter and reviewer, but they mean different things, and the buttons are labelled differently for a reason.- Submitter responses
- Reviewer responses
When you have uploaded a promotion and Adclear has flagged something, you have three options:
| Button | What it means | What happens to the comment |
|---|---|---|
| Agree - Will Action | You agree with the flag and will make the change in the next version | Comment moves to the Actioned tab. You are expected to address it before resubmitting |
| Dispute | You disagree with the flag and do not intend to change the promotion | Comment stays visible with a Disputed status. The reviewer will see it and decide |
| Reply | You are adding context or asking a question without changing the comment’s status | Comment stays open. Useful for clarifying before deciding to action or dispute |
“Agree - Will Action” and “Dispute” both require substantive context. A one-line “yes” or “no” is not enough. See What Strong Feedback Looks Like below.
What Strong Feedback Looks Like
Before getting into specific examples, it helps to know what a strong response is doing. Whether you are a submitter or a reviewer, the same eight dimensions apply. A response that hits more of these is one that the agents can actually learn from, and that the next person reading the comment can rely on.| Dimension | What a strong response does | Why it helps the agents learn |
|---|---|---|
| Justified disagreement | Explains why a flag is incorrect or over-applied | Teaches boundary calibration and reduces false positives in future |
| Contextual awareness | References audience, timing, channel, or market norms | Helps agents learn situational interpretation |
| Regulatory grounding | Anchors feedback to identifiable standards or principles (e.g. COBS, FCA Handbook) | Improves rule-mapping precision |
| Harm reasoning | Explains how (or why not) consumers could be misled or harmed | Strengthens risk modelling |
| Proportionality | Distinguishes material issues from immaterial ones | Prevents over-enforcement on minor concerns |
| Completeness | Identifies missing required information | Helps agents understand where gaps in a rule exist |
| Constructive remediation | Suggests what should change or be added | Enables corrective learning rather than just rejection |
| Nuanced judgement | Recognises grey areas or uncertainty | Encourages probabilistic reasoning instead of absolute calls |
Strong feedback in practice
Compare the two columns below. Same comment, two very different signals to the agents.Weak (do not do this)
Submitter disputes: “disagree, not needed”Reviewer dismisses: “not required”Reviewer agrees: “please change”None of these tell anyone, human or agent, why. The agents cannot generalise from them, and the next person to read the comment has to start from scratch.
Strong (do this)
Submitter disputes: “Our latest tone of voice guidelines allow ‘easy to utilise’ in the context of our mobile app, not in terms of ease of investing. Asset stays as is.”Reviewer dismisses: “Dismissed. The phrase refers to in-app features being utilised, not investment products. In line with our tone-of-voice agreement on being clear and not misleading, the statement remains.”Reviewer agrees: “Agree. A ‘capital at risk’ warning is required for any paid promotion of an investment product targeting retail clients per COBS 4.2.1R.”
What Goes Wrong Without Context: Three Examples
These are the failure modes we see most often. Each one has a hidden cost for the team, for the audit trail, and for what Adclear’s agents are able to learn.1. Submitter disputes with no rationale, so the reviewer cannot tell whether to push back or let it go
1. Submitter disputes with no rationale, so the reviewer cannot tell whether to push back or let it go
The Adclear comment: “The word ‘easy’ may trivialise the nature of investing, which carries inherent risk. Consider revising in line with COBS 4.2.1R requirement that communications are fair, clear and not misleading.”What the submitter does: Clicks Dispute and writes “not needed.”The cost:
- The reviewer opens the promotion and sees a disputed flag with no reasoning. They now have to either guess what the submitter meant, risking approving something they should not, or kick it back with a question, adding a full review cycle.
- The agents see a dispute with no signal and learn nothing. The next promotion with the same flag will trigger the same back and forth.
- The audit trail shows a disputed compliance flag with no documented justification.
2. Reviewer agrees with no comment, so the agents never learn *why* the rule applied
2. Reviewer agrees with no comment, so the agents never learn *why* the rule applied
The Adclear comment: “Promotion mentions potential returns without an accompanying capital-at-risk warning.”What the reviewer does: Clicks Agree - Please Action and writes nothing.The cost:
- The submitter sees an agreement but does not know what to fix or how. They guess, resubmit, and frequently get hit with a second round of comments because the fix did not address the underlying concern.
- Adclear records a confirmation but has no language to associate with the rule. When a similar promotion comes through next week, the agents may explain the flag less clearly to the next submitter, because there is nothing in the training signal to draw from.
- You have lost the chance to make the rule more precise. With a comment, future explanations of the same flag can cite your reasoning back to the submitter.
3. Reviewer dismisses with no rationale, so the agents are told they are wrong but not how to be right
3. Reviewer dismisses with no rationale, so the agents are told they are wrong but not how to be right
The Adclear comment: “The word ‘utilise’ may not comply with tone-of-voice guidelines requiring simple, accessible language.”What the reviewer does: Clicks Dismiss and writes “not applicable.”The cost:
- The submitter sees a dismissed flag and assumes Adclear is unreliable on this kind of issue. They start to ignore similar future flags themselves rather than addressing them, and the tool’s credibility erodes for them.
- The agents learn “this kind of flag was wrong” but have no signal about why, so they may swing the other way and stop flagging similar content even where they should. The reviewer holds the foundational knowledge of what is compliant. If they do not share their reasoning, the agents cannot absorb it.
- There is no defensible record of why the dismissal was correct.
When the Comment Itself Is the Problem: Notifying Adclear
Sometimes the issue is not whether a flag is right or wrong. It is that Adclear has misread the promotion entirely, missed something it should have caught, or there is a bug in the tool. There are three ways to notify the Adclear team, and each is for a different situation.1. Tag @adclear-support on a specific comment
Use this when Adclear has flagged something incorrectly. For example, the agents are misreading a word, applying a rule that does not fit, or referencing content that is not actually in the asset.
Tag @adclear-support and explain
Use the
@ symbol to tag @adclear-support and add specific context. For example: “This is misreading the promotion, the word ‘utilise’ does not actually appear in the asset.”2. Add a sticky comment for something Adclear missed
Use this when Adclear has missed a feature or element of the promotion that should have been flagged. There is no existing comment to reply to.Click the + comment icon (top right of the asset viewer)
This is the sticky-comment tool. It lets you place a marker anywhere on the asset.
Drop the marker on the relevant element
For example, on a rocket image in an investments ad: “Rockets should not be used here as they trivialise investment risk.”
3. Use the Get Help bot for questions, bugs, and feature requests
Use this for anything not specific to a single comment. General questions, suspected bugs in the tool, or feature ideas. The Get Help button is in the top right of any promotion (and also via the chat icon in the bottom left). It opens the Adclear support bot, which categorises your message into one of three flows:I have a question
For “how do I…” or “why is this…”. Quickest path to an answer.
I found a bug
For broken behaviour, errors, or things not working as documented.
I want a new feature
For ideas and improvements. These feed into the product roadmap.
Picking the right category matters. Each one has a different intake flow and triage path. Choosing “bug” for a feature request slows your response down.
Quick Reference
A printable summary of who does what.- If you are a submitter
- If you are a reviewer
| When you… | Click | And add… |
|---|---|---|
| Agree with the flag and will fix it | Agree - Will Action | What you are changing and why |
| Disagree and will not change the promotion | Dispute | The specific reason: context, rule, policy |
| Need clarification before deciding | Reply | The question you need answered |
| Spot Adclear has misread something | (any reply) | Tag @adclear-support with what it got wrong |
| Spot something Adclear missed | Sticky comment via + icon | Where, what, and tag @adclear-support |
| Have a general question or bug | Get Help button | Pick the right category in the bot |
Frequently Asked Questions
If I am a submitter and I dispute a flag, do the agents learn from that?
If I am a submitter and I dispute a flag, do the agents learn from that?
For tone-of-voice and non-regulatory flags, yes. Submitter responses contribute, especially when patterns emerge. For regulatory flags, the agents are weighted toward the reviewer’s response. A submitter dispute alone will not change how Adclear flags similar content. The reviewer’s agreement or dismissal carries the regulatory training signal.
Why does 'Relevant - Not Required' exist if I can just dismiss?
Why does 'Relevant - Not Required' exist if I can just dismiss?
They train the agents in opposite directions. Dismiss says “the flag was wrong.” Relevant - Not Required says “the flag was sensible, but this context is an exception, please learn the exception.” If you dismiss flags that were actually relevant, the agents will eventually stop flagging similar content even when they should, because you have told them the flag itself was incorrect.
What is the minimum I need to write in a comment?
What is the minimum I need to write in a comment?
Enough that someone reading it next week, without you in the room, can understand both the decision and why. As a rule of thumb: name the context (what the promotion is, what channel, what product), name the rule or policy that justifies the call, and avoid one-line responses like “agreed” or “not needed.” See What Strong Feedback Looks Like for the full set of dimensions.
What is the difference between tagging @adclear-support and using the Get Help bot?
What is the difference between tagging @adclear-support and using the Get Help bot?
@adclear-support ties your message to a specific promotion and a specific comment. Use it when the issue is about how Adclear flagged (or did not flag) something on that asset. The Get Help bot is for everything else: general questions, suspected bugs across the tool, or feature requests. Both notify the Adclear team. The difference is whether the context is the asset or the tool.Can I email Adclear directly instead of using the bot?
Can I email Adclear directly instead of using the bot?
The bot and
@adclear-support are more efficient for us to triage. When you raise something through either channel, the context, user information, and the specific promotion or comment are pinned directly to the request, so we can pick it up and act without needing to chase down the background. Direct emails strip that context and slow the response down.What if I disagree with the reviewer's decision after they have responded?
What if I disagree with the reviewer's decision after they have responded?
The reviewer’s decision ultimately stands. They hold the keys to your organisation’s policies and are the foundational source of what is compliant in your context. Disagreements should usually be resolved through comments and conversation on the promotion itself, not by overriding the decision.
When does escalation come into play, then?
When does escalation come into play, then?
Escalation is by exception, not a routine route. It is used when there is genuine grey area that needs legal or specialist input, or where a marketing admin needs to formally accept risk on a specific change request. It is not a way to challenge a reviewer’s standard call.The Escalate button is also not enabled for every organisation. If your workspace does not show it, escalations are not part of your configured workflow. Speak to your workspace admin or contact Adclear support if you think it should be enabled.
Related Guides
Marketing User Guide
Full mechanics of uploading, choosing the right upload type, and submitting promotions for review.
Compliance User Guide
Full mechanics of reviewing promotions, making decisions, and handling escalations.
How Roles Work
Permissions, role definitions, and how to choose the right role for a team member.
Promotion Statuses
Every status a promotion can be in and who acts next at each stage.
Still need help?
Tag@adclear-support on the comment in question, drop a sticky comment with a tag for missed flags, or open the Get Help bot from the top right of any promotion.