← All runbooks
soultrace-ai / soultrace

SoulTrace Personality Assessment

Take an adaptive personality assessment through the SoulTrace API. The agent guides the user through 24 questions on a 1–7 Likert scale, sending all accumulated answers with every request (the API is stateless and replays Bayesian inference on each call). At completion, the user

agent claude-codemodel claude-sonnet-4-6snapshot python312-uveval programmatic6 stepsv1.0.0

Deploy SoulTrace Personality Assessment 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.

Deploy on jetty.io →View source
The shape of the run

6 steps · start to finish.

  1. 1
    Step 1

    Environment Setup

    ▶
    pip install requests
mkdir -p /app/results

# Verify API reachability
curl -s -X POST https://soultrace.app/api/agent \
  -H "Content-Type: application/json" \
  -d '{"answers": []}' | python3 -m json.tool

    If the API returns a non-200 response or connection times out, check the SoulTrace status and wait for the rate limit to reset (100 req/hour per IP).

  2. 2
    Step 2

    Start the Assessment

    ▶

    Send an empty answers array to receive the first question:

  3. 3
    Step 3

    Collect All 24 Answers (max 3 rounds of retries per question)

    ▶

    Present each question to the user on a 1–7 Likert scale and re-POST all accumulated answers after each response. The API selects the next optimal question via Bayesian inference on each call.

  4. 4
    Step 4

    Process and Save Results

    ▶

    When `status == "complete"`, persist the full API response and display the archetype:

  5. 5
    Step 5

    Iterate on Errors (max 3 rounds)

    ▶

    If any step fails:

  6. 6
    Step 6

    Write Executive Summary

    ▶

    import pathlib, json, datetime