Objectives are the long-running transformation goals customers run through Klarity Advisor. Use these tools when the user is continuing in-flight work — not starting from scratch. See Concepts → Objectives for the underlying model.Documentation Index
Fetch the complete documentation index at: https://developers.klarity.ai/llms.txt
Use this file to discover all available pages before exploring further.
| Tool | When to use |
|---|---|
get_objective | Full objective by resource key. |
get_objective_action | One specific action. |
get_objective_finding | One specific finding. |
get_objective_note | One specific note (agent notebook, user context, or run summary). |
list_objective_actions | All actions for an objective. |
list_objective_findings | All findings for an objective. |
list_objective_notes | All notes for an objective. |
list_objective_activity | Append-only activity log for an objective. |
get_objective_context_bundle | The stitched bundle: objective + findings + actions + activity + notes + agent state. Best one-call for orientation. |
get_objective_analysis_input | Top-of-run context bundle plus recent workspace evidence — what the Advisor agent itself sees at the start of a run. |
get_objective_agent_state | The persisted agent checkpoint. Use when resuming or debugging an Advisor run. |
list_objective_items_with_active_steering | Findings or actions where the user has provided active steering feedback. |
The single best entry point
If you don’t know which tool to use yet, callget_objective_context_bundle. It returns objective + findings + actions + activity + notes + agent state in one call — enough context to decide what to drill into next.
Common chains
- Pick up where Advisor left off:
get_objective_context_bundle→ drill into the latest action or finding - Avoid duplicating analysis:
list_objective_findingsearly in any deep dive → if there’s prior work on this area, load it withget_objective_context_bundle - See what the user has shaped:
list_objective_items_with_active_steeringto find findings the user has actively steered, thenget_objective_findingfor the details - Debug or replay:
get_objective_agent_statefor the persisted checkpoint,get_objective_analysis_inputfor the snapshot the agent saw
Don’t restart cold
The most common mistake is to redo work Advisor has already done. Always checklist_objective_findings before running a fresh deep-dive on a process or value stream the customer has been working on.