SYS OPERATIONAL Log in Get started
Start here Overview Quickstart Chat
Context Adding context Policies Precedents Memory Entities Playbooks Templates Sources Context freshness Best practices
Decisions Request structure Response structure API reference Authentication Request object Response object Context via API Webhooks Audit logs
Integrations Overview Slack Gmail Linear Proactive queue
Advanced settings Confidence & escalation Policies & safety Risk levels Assistant attribution Confidence Autopsy Context-Building Notifications Judgement Coaching Decision Simulation Judgment Benchmarking Profiles Judgment Profiles Delegation Chains
Support & reference FAQs Debugging decisions Why something escalated Improving confidence Security & privacy Changelog LLMs.txt

Debugging decisions

If a decision doesn't match your expectations, start with the audit log.

Review:

  • The original request and context
  • The confidence score
  • The reason provided
  • Which policies, precedents, and entities were applied

Most unexpected outcomes are caused by missing or ambiguous context, not incorrect logic.

There are no results for that search on this page, however, if you press the enter key then our entire documentation will be searched and you will receive the results. If you need assistance, please contact us.