OTHER
RMA email intake with AI photo-condition triage
Turns inbound return-request emails in Front into structured RMA records, classifies attached product photos by damage severity.
How it runs
The automated pipeline, trigger to output.
- TriggerNew return-request conversation in FrontFront
- ActionDownload photo attachments from the emailFront
- ActionClassify photo condition with Hugging Face vision modelHugging Face
- LogicMap condition grade to disposition (refund/repair/inspect/deny)
- ActionCreate structured RMA record in AirtableAirtable
- ActionTag Front conversation with dispositionFront
- OutputPost triaged RMA summary to SlackSlack
What it does
When a customer emails a return request into a Front inbox, this workflow pulls the message and any attached product photos, runs the images through a Hugging Face vision model to grade physical condition (like-new, used, cosmetic damage, defective), and creates a structured RMA row in Airtable with the verdict. It then tags the Front conversation and posts a triage summary to Slack so the returns team knows what landed and where it should go.
When to use it
Use it when returns arrive as free-form emails with photos and a human has to eyeball each one before deciding refund vs. repair vs. reject. It removes the manual photo review and the copy-paste into your RMA tracker.
How it works
- 1A new tagged conversation in Front fires the trigger.
- 2The flow extracts the sender, order reference, and downloads photo attachments.
- 3A Hugging Face image-classification model scores each photo for condition and damage type.
- 4A logic branch maps the score to a disposition (refund / repair / inspect / deny).
- 5An Airtable record is created with the RMA number, condition grade, and disposition.
- 6The Front conversation is tagged with the disposition for the agent.
- 7A Slack message delivers the triaged summary to the returns channel.
Set it up
What you configure once, before turning it on.
- 1Connect FrontShared inbox, conversations.
- 2Connect Hugging FaceModels, datasets, spaces — the open-source hub.
- 3Connect AirtableBases, tables, views, automations.
- 4Connect SlackChannels, DMs, threads, mentions.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Other workflows
Sync IVR Prompt Registry in Airtable to Fresh ElevenLabs Audio
Runs nightly against an Airtable IVR prompt registry, finds rows whose script text changed since last synthesis, regenerates only those ElevenLabs clips.
Agent-Driven Full IVR Re-Voicing for a Rebrand
An agent takes a rebrand brief from Notion, audits every IVR prompt for old naming, rewrites and re-synthesizes the affected ones with ElevenLabs, archives them to Dropbox.
Regenerate IVR Voice Prompts When Notion Naming Doc Changes
Watches a Notion product-naming page and, whenever a product or feature name changes, regenerates the affected ElevenLabs IVR audio prompts and saves the new MP3s to Dropbox.
Pre-register a visitor, email a QR badge, and alert the host on arrival
When a host submits a visitor pre-registration form, this creates a visitor record, emails the guest a scannable QR badge with arrival instructions.
Sweep stale visitor check-ins, auto-checkout, and flag overdue guests
On a recurring schedule this finds visitors still marked on-site past their expected departure, auto-checks-out anyone past end-of-day.
Slack-Approved IVR Re-Voicing After a Product Rename
On demand from Slack, drafts updated IVR prompt scripts for a renamed product, posts them for human approval.
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.