Traces

DriftWise records traces of every LLM call made during plan analysis, drift narratives, and noise fix generation. Traces help you understand how the AI reached its conclusions and debug unexpected results.

Viewing Traces

List traces for a scan

curl "https://app.driftwise.ai/api/v2/orgs/$ORG_ID/scans/<scan_id>/traces" \
  -H "x-api-key: $DRIFTWISE_API_KEY"

Returns a summary list:

[
  {
    "id": "trc-a1b2c3d4e5f6...",
    "kind": "narrative",
    "model": "claude-sonnet-4-6",
    "input_tokens": 4200,
    "output_tokens": 850,
    "latency_ms": 2340,
    "cached": true,
    "fallback": false,
    "created_at": "2026-04-10T15:30:00Z"
  }
]

Get a specific trace

curl "https://app.driftwise.ai/api/v2/orgs/$ORG_ID/traces/trc-a1b2c3d4e5f6..." \
  -H "x-api-key: $DRIFTWISE_API_KEY"

Trace Fields

Field	Description
id	Trace ID (trc- prefix + 24 hex chars)
kind	Operation type — see Trace Kinds below
model	LLM model used
input_tokens	Token count for the input prompt
output_tokens	Token count for the response
latency_ms	End-to-end LLM call time in milliseconds
cached	Whether the prompt cache was hit
fallback	Whether fallback (non-LLM) generation was used
error	Error message if the LLM call failed
inputs	The data sent to the LLM (plan JSON, resource state, etc.)
parsed	Structured output extracted from the LLM response

Admin vs. Regular View

Traces contain sensitive data (full prompts and raw LLM responses). Access is tiered:

Field	Regular user	Platform admin
ID, kind, model, tokens, latency	Yes	Yes
Inputs and parsed output	Yes	Yes
System prompt	-	Yes
User prompt	-	Yes
Raw LLM response	-	Yes

Regular users see enough to understand what data was analyzed and what the LLM concluded. Admins see the full prompts for debugging prompt engineering and injection issues.

Trace Kinds

Kind	When generated
narrative	Plain-English narrative for plan analysis
drift-narrative	Narrative for cloud drift vs. Terraform state
classify	Risk classification for a single change
plan-noise-fix	AI-generated fix for a noisy plan pattern
iac-gen	Terraform code generated from live resources

Retention

Traces are automatically purged 30 days after creation. Download traces you need to retain beyond that window.

Use Cases

• Debugging unexpected risk scores — check what data the LLM received and how it reasoned
• Monitoring LLM costs — track token usage across scans
• Prompt cache efficiency — the cached flag shows when prompt caching saved tokens
• Fallback detection — when fallback: true, the LLM was unavailable and a deterministic fallback was used instead