← All runbooks
gooseworks-ai / composites-inbound-lead-triage

Inbound Lead Triage

Triage inbound leads for a requested period by collecting configured lead sources, normali

agent codexmodel gpt-5.5snapshot python312-uveval programmatic9 stepsv1.0.0

Deploy Inbound Lead Triage to your jetty.io

One-click installs this runbook into a collection on your Jetty account. You can run it from the Spot dashboard, schedule it, or pipe inputs in via the API.

The shape of the run

9 steps · start to finish.

  1. 1
    Step 1

    Environment Setup

    1. Create /app/results if it does not exist.
    2. Confirm that the requested time_period is explicit enough to query each lead source.
    3. Load config/inbound-triage.json when present. If it is missing and the user did not provide raw leads, ask for source configuration before collecting leads.
    4. Confirm each configured source can be read. If a source is unavailable, record it in validation_report.json and continue with available sources only when the user approves.
    mkdir -p /app/results
    
  2. 2
    Step 2

    Configuration (Once Per Client)

    On first run, ask the user to configure their lead sources and preferences. Save to the current working directory or wherever the user prefers (e.g., `config/inbound-triage.json`).

  3. 3
    Step 3

    Collect Leads

  4. 4
    Step 4

    Classify & Rank by Urgency

  5. 5
    Step 5

    Qualify Against ICP

  6. 6
    Step 6

    Enrich with Context

  7. 7
    Step 7

    Route & Recommend Response

  8. 8
    Step 8

    Write Required Outputs

    Write `/app/results/inbound_lead_triage.md` with a prioritized action queue grouped by urgency tier. Include lead name, company, source signal, ICP fit, urgency reason, recommended owner, next action, and a response draft where appropriate.

  9. 9
    Step 9

    Iterate on Errors (max 3 rounds)

    If output generation or validation fails, perform a targeted correction and retry for max 3 rounds. Do not broaden the task beyond the failed stage.