Skip to main content
Intempt
Coming soon

AI inbox triage

Classifies inbound messages received through a webhook by intent, such as sales, support, billing, partnership, or spam. Routes each message to the appropriate team and can create a follow-up task.

Authored by Intempt Technologies

Recipe curators

Agentic workflow

Coming soon

9 steps Blu runs end to end. It drafts a plan and nothing runs until you approve it.

  1. 1

    Catch every inbound message

    Coming soon

    Blu builds a step

  2. 2

    Work out what they want

    Coming soon

    Blu builds a step

  3. 3

    Send it to the right team

    Coming soon

    Blu builds a step

  4. 4

    Match them to an account

    Coming soon

    Blu builds a step

  5. 5

    Draft the first reply

    Coming soon

    Blu builds a step

  6. 6

    Give the AE the whole picture

    Coming soon

    Blu builds a step

  7. 7

    Queue the support questions

    Coming soon

    Blu builds a step

  8. 8

    Ask a human when unsure

    Coming soon

    Blu builds a step

  9. 9

    Publish and audit the calls

    Coming soon

    Blu builds a step

About this recipe

When to use it

Inbound mixes sales, support, billing, and spam in one inbox, and someone has to sort it before anyone can act. This classifies intent automatically and routes it, drafting a first response along the way.

What it delivers

Classifies inbound conversations (email, chat, form) by intent - sales, support, billing, partnership, or spam - routes each via a multi-split to the right team, and drafts an appropriate first response.

How you prompt this

Describe the outcome in your own words and Blu Agent maps it to this recipe, or run it by name. It drafts a plan first and nothing runs until you approve it.

Tell Blu Agent what you want

“Classifies inbound messages received through a webhook by intent, such as sales, support, billing, partnership, or spam. Routes each message to the appropriate team and can create a follow-up task.”

recipe.md preview

Built from the published catalog. Blu Agent's full step prompts load in your workspace when you run it.

Sign up to read the full recipe.md and run it with Blu Agent.

Sign up to see the full recipe

Inputs & outputs

What the recipe needs before it runs, and what it leaves in your workspace.

Inputs

  1. Nothing declared beyond an Intempt workspace. Blu asks for anything else it needs as it goes.

Outputs

    How the recipe runs

    Blu follows the steps in order and shows you each one before anything goes live.

    1. 01Catch every inbound messageCreate a workflow 'AI inbox triage' triggered when a new inbound conversation arrives in any tracked channel (email, web chat, contact form, social DM via webhook). Goal: every message reaches the right human within 5 minutes with appropriate context attached, replacing the manual ops triage.
    2. 02Work out what they wantThis step builds a workflow. Configure AI step that classifies the inbound message into one of: sales-inquiry (interested in buying), support-question (existing customer issue), billing-question (payment/account), partnership (BD/integration), spam/non-actionable, or escalation-required (legal threat, security, abuse). Output: intent_label + confidence + extracted entities (mentioned products, mentioned competitors, urgency signals). Use the result of "Catch every inbound message".
    3. 03Send it to the right teamThis step builds a workflow. Configure multi-split routing into branches: sales-inquiry to AE task + sales-inbox; support-question to support queue (linked customer); billing-question to finance queue; partnership to BD task; spam to archive silently; escalation-required to on-call alert. Each branch gets the full message context attached. Use the result of "Catch every inbound message", "Work out what they want".
    4. 04Match them to an accountThis step builds a workflow. On the sales-inquiry branch: try to match sender's email/domain to an existing Account or Lead. If match, surface their history (prior touches, opened deals, account tier). If no match, create lead with auto-enrichment trigger. Use the result of "Catch every inbound message", "Send it to the right team".
    5. 05Draft the first replyThis step builds a workflow. Configure AI write step on the sales branch: draft a personalized initial reply acknowledging the inquiry, referencing any past interactions if matched, offering specific next steps (book a demo / talk to specialist / send pricing). Saved as draft on the AE task; AE reviews, edits if needed, sends. Reply-SLA target: 5 minutes from inbound. Use the result of "Catch every inbound message", "Match them to an account".
    6. 06Give the AE the whole pictureThis step builds a workflow. Create AE task with: original message, AI classification + confidence, matched account/lead context, AI-drafted reply ready-to-send. Assign by territory or round-robin. Priority: HIGH for known accounts, MEDIUM for unknown. SLA: 5-minute first response. Use the result of "Catch every inbound message", "Match them to an account", "Draft the first reply".
    7. 07Queue the support questionsThis step builds a workflow. On the support-question branch: route to support queue with customer context (account tier, recent product usage, recent tickets). If customer is on a paid plan, flag as priority; if free-tier, route to FAQ-first response template. Use the result of "Catch every inbound message", "Send it to the right team".
    8. 08Ask a human when unsureThis step builds a workflow. Configure Slack step that fires when AI classification confidence is below 60% OR when the message is escalation-required type. Posts to #ops-triage channel with the message and AI's best guess at routing, asking for human review. Don't let edge cases fall through. Use the result of "Catch every inbound message", "Work out what they want".
    9. 09Publish and audit the callsThis step builds a workflow. Validate and publish. Monitor: classification accuracy (sample 5% of messages weekly, human-rates whether the AI got it right: target: 90%+), first-response SLA, mis-routed-message rate. Tune the AI prompts when accuracy dips. Use the result of "Catch every inbound message", "Give the AE the whole picture", "Queue the support questions", "Ask a human when unsure".

    Install Intempt and run it

    1. 1

      Sign up

      Create a free Intempt workspace.

    2. 2

      Connect your data

      Add the sources this recipe reads from.

    3. 3

      Ask Blu

      Type /ai-inbox-triage-agent-workflow in Blu once this recipe is live there.

    4. 4

      Review and approve

      Blu builds each step and waits for your OK before anything goes live.

    Related recipes

    Intempt TechnologiesDiscovery call qualification fieldsGenerates an AI summary for Discovery calls from meeting data using the qualification framework in the summary recipe.View recipe Intempt TechnologiesPost demo nurtureKeeps a demo warm for 90 days with a playbook, a case study, an ROI calculator and a customer story, and pulls the AE in early if they bite.View recipe Intempt TechnologiesReturn rate by categoryShows which product categories get returned most, and which ones have got worse since last quarter.View recipe

    More recipes by Intempt Technologies

    Discovery call qualification fieldsGenerates an AI summary for Discovery calls from meeting data using the qualification framework in the summary recipe.View recipe Post demo nurtureKeeps a demo warm for 90 days with a playbook, a case study, an ROI calculator and a customer story, and pulls the AE in early if they bite.View recipe Product swap in a sceneReplaces the product in a shot you already have with a different one, keeping the scene, lighting and shadow the same.View recipe

    Got a play worth sharing?

    Publish it to the Intempt Collective Marketplace and earn when other teams run it.

    Submit a recipe