Reels Power-Law Performance Auditor
Audits short-form video performance across a roster of creator accounts using a power-law model. Each Monday it loads the last 28 days of reels from Airtable, computes each video's view multiple against the account's trailing median, classifies accounts as Strong, Normal, or Weak, and isolates viral outliers above a configurable multiplier. For each outlier it extracts frames, transcribes the on-screen captions, and groups the opening lines into hook frameworks (curiosity, contrarian, listicle, story, demo). The agent ships one HTML email per run with per-account tier tables, outlier cards including thumbnail, caption, and detected hook, and a roll-up of hook frameworks that worked this period.
Agent snapshot
Built for media publishing work, not a generic template.
1
template use
1
catalog view
2
integrations used
2
labels matched
Sample input
Build an agent to reels Power-Law Performance Auditor. Use Google Sheets and Gmail. Focus on operations. Return a ready-to-review result after each run.
Sample output
Every Monday, pulls reel metrics across all managed creator accounts from Airtable, scores videos against each account's own median, tiers accounts Strong/Normal/Weak, flags viral outliers, transcribes their burned-in captions, and emails an HTML report with hook frameworks.
Workflow brief
Where Reels Power-Law Performance Auditor fits in a media publishing automation system
Reels Power-Law Performance Auditor is designed for a specific recurring job: audits short-form video performance across a roster of creator accounts using a power-law model. Each Monday it loads the last 28 days of reels from Airtable, computes each video's view multiple against the account's trailing median, classifies accounts as Strong, Normal, or Weak, and isolates viral outliers above a configurable multiplier. For each outlier it extracts frames, transcribes the on-screen captions, and groups the opening lines into hook frameworks (curiosity, contrarian, listicle, story, demo). The agent ships one HTML email per run with per-account tier tables, outlier cards including thumbnail, caption, and detected hook, and a roll-up of hook frameworks that worked this period. The agent page keeps the workflow concrete by showing the connected apps, the input a team can give Twin, and the output the run is expected to produce.
A team can start from this public template, adjust the instructions, connect the relevant accounts, and schedule the agent once the review path is clear. That makes it useful for repeatable work where the same research, update, summary, or follow-up needs to happen again.
In this setup Twin uses Google Sheets and Gmail as source systems, action targets, or reporting destinations. The agent can combine those tools with browser automation and API calls when the workflow crosses systems.
What this agent automates
This run includes 8 concrete steps from the published agent data.
Read every row from the configured Airtable base/view containing reels, accounts, view counts, post dates, and video URLs published in the last lookback window
Group reels by account, compute the trailing median views per account, then compute each reel's view multiple (views / account_median)
Tier each account by its top-quartile multiple: Strong above the strong threshold, Weak below the weak threshold, otherwise Normal
Select reels whose multiple is above the viral threshold, dedupe against reels already analyzed in the agent database, and cap at the per-run outlier limit
For each new outlier, scrape the video URL, sample evenly-spaced frames, run OCR on the burned-in captions, and stitch them into the full subtitle script
Use Twin AI to label the opening line of each outlier with a hook framework from the configured list
Integrations used
Reels Power-Law Performance Auditor connects Google Sheets and Gmail.
Google Sheets
Connected in this agent
Gmail
Connected in this agent
Similar agents
More agents for related media publishing workflows
These pages share industry labels, use-case labels, or connected apps with Reels Power-Law Performance Auditor. They create crawlable paths between templates that buyers are likely to compare together.
Niche Deal Aggregator
Media Publishing
Twin scrapes your audiobook deal sources on a daily cadence, captures title, author, cover, price, source, and deal link for offers under $10,...
View agentCandidate Intake Operator
Recruiting Hr
A lightweight ATS-in-a-box for teams that recruit out of email and LinkedIn. The agent watches inbound messages for resumes and candidate context,...
View agentJV Dispositions Operator
Real Estate
An always-on dispositions co-pilot for real estate wholesalers. It catches JV deal forwards in your inbox, parses the property and JV-source...
View agentProbate Outreach Kit Builder
Real Estate
This agent monitors a probate leads spreadsheet for new entries, then for each new lead generates three sanitized outreach artifacts: a...
View agentRestaurant Reputation Analyst
Hospitality Tourism
A reputation operator for restaurant owners. On the 1st of each month, it pulls new Google Maps and TripAdvisor reviews from the past 30 days,...
View agentTenant Onboarding Pipeline Operator
Real Estate
Continuously monitors your intake source for new applicant submissions, scores each one against budget, location, and lifestyle criteria, appends...
View agentInvestor Update Composer
E Commerce Retail
Closes the books on the prior month by pulling invoice data from your accounting platform, computing Net Orders, Net Sales, Average Ticket and YTD...
View agentGhost Job & Scam Auditor
Recruiting Hr
An on-demand forensic auditor for job seekers and career coaches. Submit a job posting URL, a recruiter outreach email, or a pasted job...
View agentClone Reels Power-Law Performance Auditor
Start from the exact agent behind this page, then adapt the prompt, apps, and review steps to your media publishing workflow.
Plans start at €20/mo