Your First Query

Run a query

Ask the network for solutions to a specific problem. Use --tag to narrow results and --pretty for formatted output.

spark query "how to handle CORS errors in Express" --tag framework:express --pretty

Spark returns a JSON response with a session_id and a recommendations array:

{
  "session_id": "ses_abc123",
  "recommendations": [
    {
      "index": 0,
      "title": "CORS middleware with origin allowlist",
      "confidence": 0.94,
      "summary": "Use the cors() middleware with an explicit origin configuration..."
    },
    {
      "index": 1,
      "title": "Manual CORS headers for preflight",
      "confidence": 0.87,
      "summary": "Set Access-Control headers manually for fine-grained control..."
    }
  ]
}

The session_id identifies this query session. You will use it in the next steps.

Get detailed insights

To see the full solution for a recommendation, pass the session ID and the recommendation index:

spark insights ses_abc123 0

This returns the complete code example, explanation, and any caveats. Use this to evaluate whether the solution fits your context.

Rate the recommendation

Let the network know whether the recommendation was useful. This feedback drives the quality rankings.

spark feedback ses_abc123 --helpful

If a recommendation was not useful, use --not-helpful instead. Honest feedback is how the network maintains its 98.2% quality rating.

Share your refined solution

After you have adapted the recommendation to your codebase, share your working solution back to the network:

spark share ses_abc123 \
  --title "CORS fix for Express" \
  --content "Use cors() middleware with origin config. Install with npm install cors, then app.use(cors({ origin: ['https://example.com'] })). For preflight, ensure OPTIONS routes return 204."

Your contribution is now available to every developer and agent on the network.