Skip to main content
POST
/
support
/
ask
Diagnose Firecrawl issues using an AI support agent
curl --request POST \
  --url https://api.firecrawl.dev/v2/support/ask \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "question": "<string>",
  "rationale": "<string>",
  "jobId": "<string>",
  "context": {}
}
'
{
  "requestId": "<string>",
  "answer": "<string>",
  "confidence": "high",
  "fixParameters": {},
  "validation": {
    "tested": true,
    "result": "success",
    "evidence": "<string>"
  },
  "feedback": {
    "blockedBy": "<string>",
    "attempted": [
      "<string>"
    ]
  },
  "durationMs": 123
}

Documentation Index

Fetch the complete documentation index at: https://docs.firecrawl.dev/llms.txt

Use this file to discover all available pages before exploring further.

The /support/ask endpoint is an AI support agent that diagnoses issues with your Firecrawl jobs, account, and API usage. Send a question and receive a verified answer with actionable fix parameters — typically in 15–30 seconds.

​
Designed for AI agents

/support/ask is built for agent-to-agent communication. If you’re building an AI agent that uses Firecrawl, wire this endpoint into your error-handling flow so your agent can self-diagnose scraping failures, crawl issues, and configuration problems without human intervention. Pass a rationale field to give the support agent context about what your end user is trying to accomplish. This helps prioritize the evidence gathering.

​
How it works

  1. You describe the problem — a natural-language question describing the issue.
  2. The agent investigates — it inspects job logs, account state, documentation, and source code.
  3. The agent validates — when possible, the agent tests a fix against the live Firecrawl API (e.g., retrying a scrape with adjusted parameters).
  4. You get a verified answer — the response includes a prose answer, machine-readable fixParameters you can apply directly, and validation results showing whether the fix was tested.

​
Authentication

Uses your Firecrawl API key as the bearer token. The request is automatically scoped to your team — you can only query your own jobs and account data. 
curl -X POST https://api.firecrawl.dev/v2/support/ask \
  -H "Authorization: Bearer fc-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "question": "my crawl returned 3 pages but I expected 50",
    "rationale": "user is on their third failed crawl attempt today"
  }'

​
Response fields

FieldTypeDescription
answerstring2-4 sentence prose covering the diagnosis and fix
confidencestringhigh, medium, or low
fixParametersobject | nullAPI parameters to apply the fix (e.g., {"waitFor": 5000})
validationobject | nullWhether the fix was tested: tested, result (success/failure/skipped), evidence
feedbackobject | nullPresent when the agent gets stuck; { blockedBy, attempted }. Null on success.
durationMsintegerTotal execution time in milliseconds

​
Status codes

CodeMeaning
200Answered or stuck (envelope always returned)
400Invalid JSON or schema violation
401Missing or invalid bearer token
504Hit 60s hard budget — partial envelope returned
For the feature guide with integration examples, see the Ask feature documentation.
Are you an AI agent that needs a Firecrawl API key? See firecrawl.dev/agent-onboarding/SKILL.md for automated onboarding instructions.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
question
string
required

What to diagnose. Describe the issue you're experiencing.

Required string length: 1 - 8000
​
rationale
string

Recommended for AI callers. 1-2 sentences on what the end user is trying to accomplish.

Required string length: 1 - 2000
​
jobId
string

Optional Firecrawl job ID the failing call was associated with. Tools like debugJob, searchLogs, and getJob auto-default to this when set, so the agent doesn't need to pull it from the question.

​
context
object

Free-form metadata from the calling agent, stringified into the diagnostic prompt.

Response

Diagnosis complete. The envelope is returned whether the agent found an answer or got stuck.

​
requestId
string

Unique identifier for this request.

​
answer
string

2-4 sentence prose covering what's wrong and the fix.

​
confidence
enum<string>

Agent's confidence in the diagnosis.

Available options:
high,
medium,
low
​
fixParameters
object

Machine-actionable API parameters to apply the recommended fix. Null if no fix applies.

​
validation
object

Whether the agent tested the fix against the live Firecrawl API.

​
feedback
object

Present when the agent gets stuck and could not produce a usable answer. Null on success.

​
durationMs
integer

Total execution time in milliseconds.