MARKETING
Quarterly UTM Registry Cleanup Agent
An agent that quarterly cross-references the Coda naming registry against actual UTM usage in BigQuery, proposes retiring dead values, merging duplicates, and documenting orphan…
How it runs
The automated pipeline, trigger to output.
- TriggerQuarterly schedule kicks off the cleanup agent
- ActionPull full registry from Coda and usage from BigQueryBigQuery
- LogicClassify each value as active, dead, duplicate, or orphan
- ActionPost retire/merge/adopt recommendations to Slack for sign-offSlack
- OutputApply approved edits back to the Coda registryCoda
What it does
Keeps the registry itself honest over time. The agent compares what the registry says is allowed against what's actually being used, then reasons about the gaps: values defined but never used, near-duplicate entries that should merge, and live tags that exist in traffic but never made it into the registry. It writes up a tidy set of recommendations rather than acting blindly.
When to use it
Run it once a quarter when registry rot has set in and nobody remembers why half the entries exist. It does the tedious archaeology of reconciling intent against reality so a human only has to approve the conclusions.
How it works
- 1A scheduled quarterly trigger starts the agent.
- 2It pulls the full registry from Coda and a quarter of distinct UTM usage from BigQuery.
- 3The agent reasons over both sets to classify each value as active, dead, duplicate, or orphan.
- 4It drafts specific recommendations: retire, merge, or formally adopt.
- 5The proposal is posted to Slack for sign-off, and on approval the agent applies the agreed edits back to the Coda registry.
Set it up
What you configure once, before turning it on.
- 1Connect CodaDocs, packs, automations.
- 2Connect BigQueryDatasets, queries, schemas.
- 3Connect SlackChannels, DMs, threads, mentions.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Marketing workflows
Agentic UTM Taxonomy Steward: Detect, Explain, and Propose Fixes
An agent reviews the full backlog of campaign links in Airtable, reasons about taxonomy drift beyond rigid rules, drafts standardized replacements for malformed UTMs.
Slack UTM Check: Paste a Link, Get an Instant Verdict
Lets marketers drop a tracking URL into a Slack channel and get an immediate threaded reply that says whether the UTMs are valid, what is wrong, and a corrected suggestion.
Backlink Outreach Drafter for Verified Mentions
Picks verified, high-authority unlinked mentions from Airtable, drafts a personalized backlink-request email for each.
Source-Authority Verifier for Mention Provenance
Takes a queue of detected brand mentions and runs an agent that verifies whether each source is a legitimate, authoritative publisher versus a scraper or syndication copy.
Unlinked Brand-Mention Detector with Authority Scoring
Scans the web for fresh brand mentions, filters to ones that name you without linking back, scores the publishing domain's authority.
Weekly Brand-Mention Provenance Digest to Notion
Aggregates the week's tracked mentions from Airtable into a single summarized report covering new opportunities, authority distribution, and outreach progress.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.