Skip to main content

Troubleshooting

Common issues, what they mean, and how to fix them.

12 min read

When something isn't working, this is the page to check first. Symptoms are listed by where you'd notice them — start with the section that matches what you're seeing.

First, don't panic. Most issues are configuration, not bugs. The platform is designed so you can't break anything important — pause the deployment, fix the issue, resume. Even an ugly issue rarely costs you more than the cost of a few wasted test calls.

If you can't find your issue here: Email support@hirefinn.ai with the deployment ID, the call ID (if applicable), and a description of what you expected vs. what happened. Include screenshots if visual.


Test calls

"My test call never came through."

Likely causeWhat to check
Phone number format wrongInclude country code. US: +15551234567. India: +919876543210. The platform shows a "tested format: …" preview before triggering.
Trial credit exhaustedSettings → Plan and billing → Usage. New accounts get $25 credit.
Number on global suppression listSettings → Compliance → Do Not Call List → search for your number.
Carrier rejectionSome carriers (especially international) block calls from new numbers. Try a different from-number.
Spam blocker on your phoneApple/Google spam filters sometimes silently block. Try from a different from-number.

"Test call came through but the Finn was silent / weird."

Likely causeWhat to check
Welcome message set to defined but field is emptyEdit Finn → Welcome Message → ensure there's text in the field or switch to dynamic
Voice not properly assignedEdit Finn → Voice → re-select. Some voices require a region match.
LLM service misconfigured (advanced)Edit Finn → AI Service Configuration → reset to default
Microphone permission issue on Finn sideRefresh, try again. Persistent: contact support.

Building / editing a Finn

"I can't save my Finn — Save button is grayed out."

Likely causeWhat to check
Required field emptyLook for red labels — usually Name, Voice, or Language.
Validation error in workflowIf using Workflow tab, check for nodes with red borders.
Browser session expiredRefresh, log back in, try again. Your edits autosave drafts.

"My Finn isn't following the script I wrote."

Likely causeWhat to fix
Identity field too vagueBe specific. "You are Maya, a friendly receptionist" beats "You are an AI assistant."
Guardrails buried under too many other instructionsMove critical guardrails to their own dedicated field (Style & Guardrails).
Conflicting instructions across fieldsAudit Identity + Style + Welcome + Workflow for contradictions.
Knowledge base contains contradictory infoOpen the Knowledge tab in Data Extractor Sidebar for a sample call to see what was retrieved. Remove contradictions from KB.
Free-form when you need structureIf you have a strict required-order flow, use Workflows instead.

"The Finn is too chatty / not chatty enough."

SymptomFix
Too talkyAdd to Response Guidelines: "Keep responses under two sentences unless asked for more detail."
Too briefAdd to Response Guidelines: "Give complete answers with examples when relevant."
Interrupting the callerTune Settings → Call Settings → Interruption Sensitivity (lower = more patient)
Long awkward silencesTune max_idle_duration lower (e.g. 5s instead of 10s)

"My Finn keeps asking the same question twice."

Likely causeFix
The caller's answer didn't match the expected formatSoften the Ask node's parser, or rephrase the question
LLM didn't capture the answer to memoryAdd to Response Guidelines: "Once a question is answered, do not ask it again."
Workflow loop bugOpen the workflow → check for an edge that loops back to the Ask node

Knowledge Base

"Finn isn't answering questions I know are in the documents."

Likely causeWhat to check
Documents not indexed yetKnowledge Base tab → check status. Should say Indexed. Click Re-index Now if stuck.
Document is image-only PDFScanned PDFs aren't OCR'd. Convert to text first (e.g. with Adobe or an online OCR tool).
Document too long, retrieval misses relevant sectionSplit the document into smaller focused files.
Question phrasing doesn't match document phrasingOpen Data Extractor Sidebar → Knowledge tab for a sample call → see what was retrieved. If wrong snippets came back, KB needs more semantic coverage.
File over 25 MB size limitCompress or split.

"Finn is giving outdated answers."

Likely causeFix
Old version of document still in KBKnowledge Base → delete old file, upload new one
Website import has stale cached contentKnowledge Base → Website Imports → [URL] → Re-crawl Now
Cached query result (rare)Click Re-index Now to force refresh

Deployments

"I clicked Launch but no calls are going out."

Likely causeWhat to check
Outside calling-hour windowDeployments only dial during the configured calling-hour window in caller's local time. If you launch at 8 AM PT with 9-6 calling hours, first call won't go out until 9 AM.
Audience emptyOpen the audience and confirm it has rows. Sync issues can leave it empty.
All numbers suppressedSettings → Compliance → Do Not Call List. If you accidentally suppressed your test list, remove them.
From-number not registeredUS numbers without caller ID registration fail silently. Check Settings → Phone numbers → [Number] → Registration Status.
Spend cap hitLive Deployments → health panel will show "Cap reached." Raise cap or wait for next period.
Deployment pausedLive Deployments → click deployment → check status.

"Calls are going out but everyone hangs up immediately."

Likely causeFix
Caller ID showing "SPAM LIKELY"Register caller ID. Without registration, US carriers label your calls as spam and answer rates collapse.
Welcome message sounds like spamTighten the opening. "Hi, this is [name] calling from [recognizable company name] about [reason they'd expect a call]." The "about" matters — generic openings get hung up on.
Calling at bad hoursVerify calling-hour window is being applied.
List is cold (no prior relationship)This isn't a Finn problem — it's a list problem. Cold lists always have low pickup-and-stay rates.

"Deployment is paused but I don't know why."

Live Deployments → click deployment → scroll to Pause Reason. Common reasons:

ReasonWhat it means
Spend cap reachedConfigured per-deployment cap was hit. Raise it or close the deployment.
Audience exhaustedAll contacts called (with retries). Either complete the deployment or add more contacts.
Buffer drainedDispatcher ran out of work momentarily. Usually self-recovers within a minute.
Manual pauseYou or a teammate hit Pause. Check the audit log.
Carrier outageTelephony provider issue. Resumes when their outage ends.
Plan limit hitYou've used your plan's monthly call allotment. Upgrade or wait for next cycle.

Analytics

"Analytics shows zero calls but I know calls happened."

Likely causeFix
Looking at wrong deploymentCheck the deployment dropdown — easy to land on a different one
Cache staleClick Refresh (button shows up when "Cached" badge is visible)
Calls were under 5 secondsSome metrics filter out very-short calls (treated as no-answer). Look at the full call log.

"Post-call analysis fields are blank."

Likely causeFix
Fields added after the deployment startedPost-call analysis only runs on calls that completed after the field was added. New calls will be populated.
Field question is too vagueReword. "Did the caller express interest?" is better than "Interest level?"
Transcript is too shortIf a call lasted 5 seconds, there's nothing to extract from.
LLM extraction errorRare. Check the call's Extraction Status in the sidebar.

"Sentiment seems wrong on calls."

Sentiment analysis isn't perfect. It's a useful indicator, not a verdict. If consistently misclassifying, add a custom post-call field with a more specific question (e.g. "Did the caller seem satisfied with the resolution?") and use that instead.


Phone numbers

"I bought a number but can't use it."

Likely causeWhat to check
Compliance verification pendingSome countries (India, France, Germany) require KYC. Settings → Phone numbers → [Number] → Compliance Status.
Caller ID not registered (US)Outbound calls fail with "carrier rejected" until registered.
SIP trunk misconfigured (BYO)Settings → Telephony Account → test trunk. Common: codec mismatch, wrong credentials.
Number not assigned to a Finn (inbound)Settings → Phone numbers → [Number] → Default Inbound Finn → assign one.

"Outbound calls fail with 'carrier rejected.'"

CauseFix
Caller ID not registered (US/Canada)Settings → Phone numbers → [Number] → Caller ID Registration
Destination country requires sender verificationKYC under Settings → Phone numbers → Compliance
From-number capability doesn't include voiceBuy a voice-capable number; SMS-only numbers can't make calls
Carrier is filtering known-bad sendersTry a different from-number; old numbers sometimes get blacklisted by carriers

Integrations

"CRM sync isn't pulling in new contacts."

Likely causeFix
Sync schedule too infrequentSettings → Integrations → [CRM] → set to every 15 min or hourly
CRM token expiredRe-authorize the integration
Filter excludes new contactsOpen the audience's CRM filter and verify the criteria
CRM API rate-limitedWait and retry. Heavy syncs can trigger CRM-side limits.

"My webhook isn't receiving events."

Likely causeWhat to check
URL unreachable from internetUse a public URL, not localhost. For local testing, use a tunnel (ngrok, Cloudflare Tunnel).
Returning non-2xx responseThe platform expects 200-299. 3xx/4xx/5xx triggers retry.
Endpoint timing outMust respond within 10s. For long-running logic, accept the webhook quickly and process asynchronously.
HMAC signature mismatchVerify your signing implementation matches our spec — see Integrations → Webhooks.

"Calendar bookings aren't appearing in my calendar."

Likely causeFix
Wrong calendar selectedSettings → Integrations → Calendar → check selected calendar
Permissions revoked in calendar providerRe-authorize the integration
Booking went to a calendar you don't viewMany people have multiple calendars; the booking is somewhere. Check "all calendars" view.
Calendar event title misleadingBookings default to "Appointment via FinnAI" — search by that

Billing

"My invoice is higher than expected."

Settings → Plan and billing → Usage → Anomaly Flags. Look for line items >2x your trailing 30-day average. Common causes:

  • A Finn ran on a hostile audience and got into long stuck calls (set limit_call_duration).
  • A deployment was launched without a spend cap and dialed a much bigger list than intended.
  • Premium voice or premium model was enabled (Settings → Plan).
  • A new country was added — international telephony rates can be 10-50x US rates.

"I want a refund for a wasted deployment."

Email billing@hirefinn.ai with the deployment ID and an explanation. Bug-related issues are typically refunded. User-configuration mistakes typically aren't, but reach out anyway — case-by-case.


Account & access

"I can't log in."

Likely causeWhat to try
Forgot passwordClick "Forgot password" on the login page
Account locked after too many failed attemptsWait 15 minutes, then try again
Email not confirmedCheck spam folder for confirmation email
Team account but you weren't invitedAsk your admin to invite you via Settings → Team
SSO not workingIf your org uses SSO, you must log in via the SSO link, not email/password

"I lost access to my account / lost 2FA device."

Email support@hirefinn.ai with proof of account ownership (billing email, last 4 of payment method, etc). We'll help you recover access.


Performance / quality

"Latency is too high — Finn takes too long to respond."

Target: <800ms between end-of-user-speech and start-of-Finn-response.

CauseFix
Premium voice selectedSwitch to a standard voice (-100-200ms)
Far-away regionSet account region during signup to closest to your callers
Network issues at carrierUsually transient — wait a few minutes
Complex workflow with deep nestingSimplify; collapse sub-flows
Large knowledge base + slow retrievalSettings → Knowledge → re-index, or reduce KB size

"Finn sounds robotic / not human enough."

CauseFix
Standard voice tierTry a premium voice
Language mismatchConfirm voice's primary language matches what you're speaking
Response Guidelines too restrictive"Keep responses under one sentence" makes it feel terse. Loosen.
Workflow forcing rigid scriptSwitch to free-form, or use Say nodes more sparingly

When all else fails

  1. Pause the deployment — stops dialing, no more cost incurred.
  2. Look at a recent failed call — open the Data Extractor Sidebar for full context.
  3. Search this troubleshooting page with Ctrl+F for keywords from your error.
  4. Email supportsupport@hirefinn.ai with deployment ID, call ID, and your description.
  5. Use the chat-bubble Finn — bottom-right corner — it's trained on these docs and can usually resolve issues instantly.
  6. For Enterprise customers — your dedicated CSM is in your Slack channel.

Next

  • FAQ → — questions that aren't quite troubleshooting.
  • Compliance → — things that fail because of legal/regulatory issues.
  • Glossary → — definitions for any term you don't recognize.

Was this page helpful?

Still stuck or have feedback?

Email support@hirefinn.ai or use the chat bubble in the bottom-right corner — it's a Finn that knows the Academy cold.