Debug Logs
Salesforce debug logs, explained by AI
Pull the org’s captured debug logs, read them in a viewer that makes the noise scannable, then select up to five related logs and have the AI correlate them — pinpointing exceptions, the slowest SOQL and DML, and governor-limit consumption.
Debug logs
Read Salesforce debug logs (ApexLog) captured for this org, then analyze them with AI. Logs are only recorded while a trace flag is active in Setup → Debug Logs; this app is read-only.
Analyze logs together
3/5 selectedTick up to 5 logs below, then add an optional question for AI.
Question for AI (optional)
| Operation | Status | Started | |
|---|---|---|---|
| /services/apexrest/credit Alex Rivera | SystemLimitException | 4m ago | |
| /services/apexrest/credit Alex Rivera | SystemLimitException | 9m ago | |
| /services/apexrest/credit Alex Rivera | SystemLimitException | 16m ago | |
| QueueableHandler.execute Alex Rivera | Success | 38m ago | |
| /aura Alex Rivera | Success | 41m ago | |
| CreditReviewController.save Priya Nair | Success | 1h ago | |
| Interaction Recalculation Priya Nair | Success | 2h ago |
| 1 | 64.0 APEX_CODE,FINEST;APEX_PROFILING,INFO;DB,INFO;SYSTEM,DEBUG |
| 2 | 09:41:12.4 (4218976)|EXECUTION_STARTED |
| 3 | 09:41:12.4 (4231044)|CODE_UNIT_STARTED|[EXTERNAL]|CreditCheckRestResource.doPost |
| 4 | 09:41:12.5 (98442310)|SOQL_EXECUTE_BEGIN|[38]|Aggregations:0|SELECT Id, Stage__c, Opportunity__c FROM Credit_Assessment__c WHERE Opportunity__c IN :ids |
| 5 | 09:41:12.5 (99551208)|SOQL_EXECUTE_END|[38]|Rows:200 |
| 6 | 09:41:12.6 (612884001)|SOQL_EXECUTE_BEGIN|[142]|Aggregations:0|SELECT Id FROM Assessment_Rule__c WHERE Assessment__c = :row.Id |
| 7 | 09:41:12.6 (613990774)|SOQL_EXECUTE_END|[142]|Rows:1 |
| 8 | ... line 142 runs once per row — 99 more times |
| 9 | 09:41:13.0 (1004221199)|LIMIT_USAGE_FOR_NS|(default)| |
| 10 | Number of SOQL queries: 100 out of 100 |
| 11 | Number of query rows: 401 out of 50000 |
| 12 | Number of DML statements: 0 out of 150 |
| 13 | 09:41:13.0 (1004556001)|FATAL_ERROR|System.LimitException: Too many SOQL queries: 101 |
| 14 | 09:41:13.0 (1004556240)|Class.CreditCheckRestResource.assess: line 142, column 1 |
| 15 | 09:41:13.0 (1004601883)|EXECUTION_FINISHED |
What you can do
- The recent-log list with operation, user, status, duration, size, and time
- A raw-body viewer that makes a wall of log output scannable
- Select up to five related logs and analyse them together as one investigation
- The AI reads each log through its own tools: no copying and pasting into a chat box
- Exceptions pinpointed, the slowest SOQL and DML surfaced, governor-limit usage explained
- Ask follow-up questions in the same conversation, with your full org context available
- Log bodies are stored once pulled, so re-reading costs no API calls
How it works
Turn on a trace flag
Logs only exist while a trace flag is active. Set one in Setup → Debug Logs for the user you are chasing, then reproduce the behaviour.
Pull and read
The log list appears with operation, status, and duration. Open any one to read it properly.
Analyse together
Tick up to five related logs, add a question, and let the AI correlate the evidence across all of them.
Why it's different
Ask questions about the log
Pasting a debug log into a chat window fails on the first big one — logs are enormous and the interesting part is rarely at the top. Here the AI reads each selected log through its own tools, correlates several from the same investigation, and has your schema, automation, and Apex source available while it reasons. You get the explanation, not a truncation.
Try asking
- “Why did this transaction hit the SOQL query limit?”
- “What threw the exception in this log, and what called it?”
- “These three logs are the same user retrying — what is failing?”
- “Which part of this transaction is actually slow?”
- Hand a log to the AI instead of reading 40,000 lines yourself
Debug Logs — questions
Works even better with
Read next
- Why Salesforce deployments fail — and how to read the errors
Metadata API errors are famously unhelpful. A field-by-field guide to the failures that actually recur, and what each one is really telling you.
Put Debug Logs to work on your org
Every AI feature on your own provider key, from A$19.95 per user per month.
- 14-day free trial
- No credit card required
- Cancel any time