Skip to content

Creator and brand intelligence for a

Show the page for a

Catch it before your client does.Know your roster before the brand asks.

Tellsight is built to read the posts, comments and ad comments around your creators on Instagram, Meta and TikTok, check what it read against that client’s rules, list what it could not read, and give your team one queue to decide from.

Tellsight is built to read your creators’ posts, their comments and the comments on their partnership ads, on Instagram, Meta and TikTok, to check them against each partner’s rules, and to turn what your team decides into a summary the partner can read before the deal.

Request accessSee how it works

Access is by request.

The Tellsight review inbox for a media agency. A queue of flagged comments and posts sorted by risk, with one ad comment open beside it: the exact quote, the ad it was left on, and the buttons to accept, dismiss or escalate. Above the queue, a line says what the scans did not read: gaps in 447 sources, from audio tone and unsampled video frames to stories, private or deleted posts, and anything outside a scan’s date window.
  1. Queues with an owner and a deadlineAssigned to me, unassigned, escalated, and past the 48-hour review deadline.

  2. Evidence stays with the findingThe exact quote, the ad it was left on, and a link to the original.

  3. A person decidesAccept, dismiss or escalate. Tellsight is built to flag, never to decide for you.

Review inbox, Northlight Collective.

The Tellsight roster for a talent agency. 3,323 findings across 2,405 creators await a decision, split by risk, beside a list of what the scans did not read and the partners with findings waiting.
  1. Who needs a decisionFindings across the whole roster, split by risk, with the ones past 48 hours counted.

  2. What was not readSources never read or read with a gap will be listed. Unreviewed is not the same as low risk.

  3. Each partner’s own rulesA creator will be checked against the rules of the partner the deal is with.

Roster, Quillfeather Talent.

The problem at scale

4,693,863comments in 30 daysAcross the 503 client brands of the example media agency on this page.

5,005creators on one rosterWith 9,507 sources between them, at the example talent agency on this page.

Nobody reads four million comments. So the one that matters reaches your client first.Nobody rereads five thousand creators before every deal. So the partner finds it after the contract is signed.

The work today, then how Tellsight is built to do it

  1. Today: A spreadsheet of creators and links

    How Tellsight is built to do it: Creators imported from a file, or pasted in, once

  2. Today: Profile checks by hand before each campaign

    How Tellsight is built to do it: Scans checked against each client’s own rules

  3. Today: Comments read when someone has the time

    How Tellsight is built to do it: Comments and ad comments read for you, with every gap listed

  4. Today: Screenshots pasted into a chat

    How Tellsight is built to do it: The quote, the source link and what was read, kept with the finding

  5. Today: A recap written from memory

    How Tellsight is built to do it: A recap built from the scan record

  1. Today: The roster in a spreadsheet, links in a column

    How Tellsight is built to do it: The roster imported from a file, or pasted in, once

  2. Today: A scroll through a creator’s profile before each pitch

    How Tellsight is built to do it: Each creator checked against the rules of the partner the deal is with

  3. Today: Comments read when someone has the time

    How Tellsight is built to do it: Comments and ad comments read for you, with every gap listed

  4. Today: Screenshots sent to the brand’s team

    How Tellsight is built to do it: The quote, the source link and what was read, kept with the finding

  5. Today: A reassurance written from memory

    How Tellsight is built to do it: A partner summary built from the scan record

01Find

Built to read what your team can’t get to. And to check it against that client’s own rules.And to check it against that partner’s own rules.

Posts, reels and videos with their captions. The comments under them. Partnership ads and Spark Ads, and the comments people leave on those. Only on the accounts you choose.

Instagram

Instagram accounts

  • Posts and reels on the accounts you choose, with their captions
  • Public comments on those posts

Meta

Ad accounts and Facebook Pages

  • Partnership ads on Facebook and Instagram that run from the ad accounts you choose
  • Comments on those ads
  • Posts on the Pages you choose, and the comments on them

TikTok

Creator accounts, and the ad accounts behind creator ads

  • Videos on the creator accounts you choose, with their captions
  • Comments on those videos
  • Spark Ads that run from the ad accounts you choose, and the comments on them

The comments under the ad, not only the post.

A partnership ad collects comments the creator’s own post never sees. Tellsight is built to read them, keep the ones it flags and count the rest, so the number read is always on the page.

Only the text of comments will be read.

A partnership ad in Tellsight. 107 comments were read and 7 flagged: 1 medium risk and 6 low risk, each listed with its quote, the commenter’s handle and a button to open the evidence.A partnership ad in Tellsight. 107 comments were read and 7 flagged: 1 medium risk and 6 low risk, each listed with its quote, the commenter’s handle and a button to open the evidence.
Ad, Northlight Collective.
A Spark Ad in Tellsight that features one of a talent agency’s creators. 127 comments were read and 1 flagged as high risk, listed with its quote, the commenter’s handle and a button to open the evidence.A Spark Ad in Tellsight that features one of a talent agency’s creators. 127 comments were read and 1 flagged as high risk, listed with its quote, the commenter’s handle and a button to open the evidence.
Ad, Quillfeather Talent.

Rules in the client’s own words.Rules in each partner’s own words.

Every brand has its own policy, written in plain language: what counts as high, medium and low risk for that brand alone. Each save is a new version, and a report will name the version its findings were checked under.

Every partner has its own rules, written in plain language: what counts as high, medium and low risk for that partner alone. Each save is a new version, and a partner summary will name the version a creator was checked under.

A brand policy in Tellsight. Plain-language instructions for what counts as high, medium and low risk for one client brand, beside the list of saved versions v1 to v3 and who saved each.A brand policy in Tellsight. Plain-language instructions for what counts as high, medium and low risk for one client brand, beside the list of saved versions v1 to v3 and who saved each.
Brand policy, Fernhollow Tea.
A partner policy in Tellsight. Plain-language instructions for what counts as high, medium and low risk for one partner, beside the saved version v1 and who saved it.A partner policy in Tellsight. Plain-language instructions for what counts as high, medium and low risk for one partner, beside the saved version v1 and who saved it.
Partner policy, Pellwick Pantry, at Quillfeather Talent.

Built to tell you what it didn’t read.

A clean screen is only worth something if you know what was behind it. A source that failed, a video read from its transcript and sampled frames, a busy post whose comments were capped: each gap will be listed where you would otherwise assume the best. Three lines from Tellsight’s own screens:

  • Anything not read is unreviewed, not low risk.

    Printed on Reports

  • Unknown severity means the content could not be read or classified. It is not low.

    Printed on the Overview

  • Unknown severity is unclassified, not low.

    Printed on the Roster

  • What was not read is unknown, not zero.

    Printed on Signals

02Decide

One queue. A person decides. The evidence is already attached.

Findings will arrive sorted by risk, each with the exact quote, the rule it may break and what was and was not read. Accept it, dismiss it or escalate it. Try it on four findings.

Review inbox

4 of 4 waiting

Try it · nothing is saved

TS-1040

Creator post (caption) flagged for Oddment Home

Teo Marsh

Exact quote, by @teomarsh.demo

“Light this one an hour before bed. It's guaranteed to cure insomnia, science says so.”

Brand rule
Conflicts with a brand rule: No health or medical claims
What was read
Text and Image. No gap recorded.
Generated explanation, written after the flag
The sponsored caption states the candle is guaranteed to cure insomnia. Oddment policy v2 prohibits health or medical claims, so the positive tone does not make this suitable.

Your decision

Review inbox

4 of 4 waiting

Try it · nothing is saved

TS-3003

Creator post (video transcript) flagged for Brackenmoor Cycle Supply

Cal Arroyo

Post caption: “Quick spin before the rain.”

Exact quote, by @calarroyo.demo

“No helmet today, it's only a short ride down the hill.”

Partner rule
Conflicts with a partner rule: No talk of riding without a helmet
What was read
Extracted transcript only. Original audio and full video were not analyzed.
Generated explanation, written after the flag
The creator says on the transcript that they are riding without a helmet today. Brackenmoor rules v1 ask partners not to talk about riding without one, and make a break of that rule medium risk. The video was not analyzed, so whether a helmet is worn on camera is unknown.

Your decision

The review inbox with seven findings selected. The bar at the foot offers Accept, Dismiss and Escalate for 4 of them and reads: 3 held back, 1 high risk, 1 not fully read, 1 where the explanation isn’t supported. Each is decided on its own.The review inbox with seven findings selected. The bar at the foot offers Accept, Dismiss and Escalate for 4 of them and reads: 3 held back, 1 high risk, 1 not fully read, 1 where the explanation isn’t supported. Each is decided on its own.
Review inbox, Northlight Collective. Seven selected: four can be decided together, three are held back.
A talent agency’s review inbox with seven findings selected. The bar at the foot offers Accept, Dismiss and Escalate for 2 of them and reads: 5 held back, 1 high risk, 1 not fully read, 3 where the explanation isn’t supported. Each is decided on its own.A talent agency’s review inbox with seven findings selected. The bar at the foot offers Accept, Dismiss and Escalate for 2 of them and reads: 5 held back, 1 high risk, 1 not fully read, 3 where the explanation isn’t supported. Each is decided on its own.
Review inbox, Quillfeather Talent. Seven selected: two can be decided together, five are held back.

Clear the routine ones together. The serious ones wait their turn.

Select a run of findings and accept, dismiss or escalate them in one move. Anything high risk, of unknown risk, not fully read, or with an explanation that does not support the flag is held back and decided on its own.

48 h
The review deadline. A finding is marked Due soon at 24 hours and Overdue once it has passed.
6 queues
Assigned to me, Unassigned, Escalated, Past the deadline, Not fully read and All waiting.
X
The key that selects a row. Shift and X selects a range, and / goes to search.
30 days
How long evidence will be kept with a finding. Each one will show the day it expires.

03Report

The recap is built from the record. Not from memory, and not from screenshots.

When the client asks what happened on the campaign, the answer will already be written: what was found, what your team decided, what is still waiting and what was never read.

When a brand asks about a creator before signing, the record will already be written: what was checked, under whose rules, what was raised, what your team decided and what was never read.

A brand safety recap in Tellsight for one client brand: 6 findings, of which 2 are waiting for review, 2 were confirmed and 2 dismissed; 2 of 5 scans finished with no gap; then the findings by risk level and by outcome, and the scan record. Buttons to save the recap, print it and preview a CSV.A brand safety recap in Tellsight for one client brand: 6 findings, of which 2 are waiting for review, 2 were confirmed and 2 dismissed; 2 of 5 scans finished with no gap; then the findings by risk level and by outcome, and the scan record. Buttons to save the recap, print it and preview a CSV.
The CSV preview of the same recap in Tellsight: 29 rows, among them the client brand, when it was generated, the summary, the scans that finished with no gap, what was not read, the findings by risk level and by outcome, the sample and the policy version.

For the client: a brand safety recap.

One client brand per report, with the scan record beside it: the dates read, the policy version and what could not be collected. Save it as it stood that day, or print it.

The same record, as rows.

The CSV preview lists every count in the recap with its caveat beside it: what was read, what was not, and the policy version it was checked under.

Reports and the CSV preview, Northlight Collective, after four of the brand’s findings were confirmed or dismissed.

A check against one partner’s rules in Tellsight: 5 findings, of which 2 are waiting for review, 1 was confirmed and 2 dismissed; 2 of 3 scans finished with no gap; then the findings by risk level and by outcome, and the scan record. Buttons to save the recap, print it and preview a CSV.A check against one partner’s rules in Tellsight: 5 findings, of which 2 are waiting for review, 1 was confirmed and 2 dismissed; 2 of 3 scans finished with no gap; then the findings by risk level and by outcome, and the scan record. Buttons to save the recap, print it and preview a CSV.
A partner summary in Tellsight, from a talent agency to a brand, for one creator: the date window, the sample size, collection gaps, the rules version, who checked it, and the findings raised and reviewed.

For the partner: a summary they can read.

What a brand would read about a creator’s check. Reviewer notes, who decided each finding and checks against other partners are left out.

For your team: one report per partner.

Every creator checked against that partner’s rules, with the scan record beside it: the dates read, the rules version and what could not be collected. Save it as it stood that day, print it or preview it as a CSV.

Reports and a partner summary, Quillfeather Talent, after three of the partner’s findings were confirmed or dismissed.

04Lead

What leadership will open on Monday. Every brand and creator on one screen, not one queue at a time.Every creator and partner on one screen, not one check at a time.

Built for the agency that runs hundreds of brands and thousands of creators in one workspace.Built for the agency that runs thousands of creators and hundreds of partners in one workspace.

What is waiting, by risk and by client.

The Overview counts every finding that awaits a decision, by severity and status, and ranks the client brands with the most waiting.

The Tellsight overview: 3,328 findings await a decision across all client brands, in a table of severity by status, above the client brands with the most waiting.The Tellsight overview: 3,328 findings await a decision across all client brands, in a table of severity by status, above the client brands with the most waiting.

How people talk about your brands.

Signals shows the share of classified comments that were negative, mixed, neutral or positive, and says how many comments were left out of the count and why.

Tellsight Signals: 14% of classified comments about the workspace’s client brands were negative, with the split between negative, mixed, neutral and positive.Tellsight Signals: 14% of classified comments about the workspace’s client brands were negative, with the split between negative, mixed, neutral and positive.

Who else gets named in your comments.

Built to watch competitors for each client brand and show when one is named more often in the comments on your own content.

Tellsight Competitors: one watched competitor was named in 770 comments about a client brand, up from 429, beside the competitor with the most negative audience.Tellsight Competitors: one watched competitor was named in 770 comments about a client brand, up from 429, beside the competitor with the most negative audience.

Overview, Signals and Competitors, Northlight Collective.

Who was read, and who was not.

The Roster sorts every creator by state: who needs a decision, whose scan failed, who was only partly read and who has no open findings.

The Tellsight roster for a talent agency: 5,005 creators by state. 2,405 need a decision, 67 failed, 7 had nothing read, 271 were partly read and 2,254 have no open findings, above the creators who need a decision, highest risk first.The Tellsight roster for a talent agency: 5,005 creators by state. 2,405 need a decision, 67 failed, 7 had nothing read, 271 were partly read and 2,254 have no open findings, above the creators who need a decision, highest risk first.

One creator, against one partner’s rules.

A creator’s check counts what was read, lists the findings against that partner’s rules and keeps the scan record beside them.

A creator’s check in Tellsight: a completed scan that read 204 captions and comments and 31 images from posts in a 30-day window, above the findings against one partner’s rules.A creator’s check in Tellsight: a completed scan that read 204 captions and comments and 31 images from posts in a 30-day window, above the findings against one partner’s rules.

How people talk about your partners.

Signals shows the share of classified comments that were negative, mixed, neutral or positive, and says how many comments were left out of the count and why.

Tellsight Signals for a talent agency: 15% of classified comments about the workspace’s partners were negative, with the split between negative, mixed, neutral and positive.Tellsight Signals for a talent agency: 15% of classified comments about the workspace’s partners were negative, with the split between negative, mixed, neutral and positive.

Roster, a creator’s check and Signals, Quillfeather Talent.

Two kinds of agency

One workflow. Set up for the way your agency works.

Show the whole page for a
SettingMedia agencyTalent agency
You work byClient brandCreator roster
You open onA review queue, by client brandThe roster: who needs a decision
Brands areClients, each with its own policyPartners, each with its own rules
What goes outA brand safety recap for the clientA partner summary before the deal

How checking works

Four questions your client will ask you.Four questions a brand will ask you. Here is what you can tell them.

  1. 01

    What will it read, and what will it leave alone?

    Only the accounts, Pages and ad accounts you choose. It will not read:

    • Direct messages
    • Messages sent to a Page
    • Drafts, archived posts and private videos
    • Billing and payment details
    • Audiences and targeting
    • Anything on an account you did not choose
  2. 02

    How will something get flagged?

    Tellsight AI is built to check what was collected against the policy you wrote for that brand and flag what may break it. An explanation will be written afterwards, as a separate step that classifies nothing. When the explanation disagrees with the flag, the finding will say so. Now and then an item cannot be checked, for example when a safety filter blocks an image before it is read. That item will stay unchecked, the report will list it as a gap, and it will never be counted as low risk.

  3. 03

    Who makes the call?

    A person on your team, every time. Nothing is confirmed or dismissed until someone accepts, dismisses or escalates it, and a report counts what was reviewed by a person separately from what is still waiting.

  4. 04

    What can’t it read?

    Audio tone, video frames that were not sampled, stories, and private or deleted posts. A check will cover a set span of dates: anything posted outside it will not be read, and the report will show the dates. Video will be read from its transcript and sampled frames only. Sometimes neither can be had: then the video will not be read, and the report will say so. When the comments on a busy post are capped, the report will say how many were read, and of about how many when the total is known. When it is not, it will say the total is unknown.

Questions

Asked before you start.

Will Tellsight decide what is safe?

No. It is built to flag content against the policy you wrote for each brand and show the evidence. A person accepts, dismisses or escalates every finding, and high-risk findings cannot be decided in bulk.

Which platforms will it read?

Instagram, Meta and TikTok: posts, reels and videos with their captions, the comments on them, and partnership ads and Spark Ads with their comments. Only on the accounts, Pages and ad accounts you choose. That is what it is built to read.

How long will evidence be kept?

For up to 30 days after it is collected. It will be removed sooner if you delete it, or if the source it came from allows less time. Each finding will show when it was collected, when it was analyzed and the day its evidence expires.

Catch it before your client does.Know your roster before the brand asks.

Request access

Access is by request. Bring a list of creators.

How setup is built: five steps to a first scan

  1. Workspace. Name your agency and say which kind it is.

  2. Brand and policy. Add your first brand and write what it allows.

  3. First creators. Import a file, or paste handles or post URLs.

  4. Connect. Connect the platforms those creators are on.

  5. Scan. Start the first scan. What it flags will land in the review inbox.