CHATBOTS

Generate a Live-Agent Briefing When Onboarding Escalates to a Human

At the moment of handoff, this assembles the user's onboarding history and account context into a concise briefing note posted to the Intercom conversation so the human starts…

CategoryChatbots
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerConversation assigned to human in IntercomIntercomIntercom
  • ActionPull onboarding history and context from PostgresPostgreSQLPostgres
  • ActionSynthesize agent briefing with OpenAIOpenAI
  • ActionPost briefing as internal note in IntercomIntercomIntercom
  • OutputLog handoff event in PostgresPostgreSQLPostgres

What it does

When an onboarding conversation is handed to a human, this instantly compiles everything the agent needs: which steps the user completed, where they got stuck, what the bot already told them, and key account details. It posts that as an internal note on the Intercom conversation so the agent never starts cold.

When to use it

Use it when handoffs feel jarring because agents have to re-read the whole thread and dig through systems. A ready-made briefing cuts time-to-first-response and prevents the user from repeating themselves.

How it works

  1. 1An Intercom event for an onboarding conversation assigned to a human triggers the flow.
  2. 2The user's onboarding step history and account context are pulled from Postgres.
  3. 3OpenAI synthesizes a tight briefing: status, blocker, prior bot replies, and a suggested opening.
  4. 4The briefing is posted as an internal note on the Intercom conversation.
  5. 5The handoff event is logged in Postgres for response-time analytics.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect IntercomConversations, contacts, articles.
  2. 2
    Connect PostgresAny Postgres URL — query, write, migrate.
  3. 3
    Connect OpenAIModels, embeddings, files.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.