A platform lead, AI architect, or transformation owner asks where to focus next. This is the “spin up multiple agents to scan the entire process tree” use case — agents should fan out in parallel across the hierarchy.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.
Example prompts
- “Find the highest-leverage automation opportunities in our P2P value stream.”
- “Where in our close cycle should we focus next?”
- “Scan our org for duplicate invoice processing across geographies.”
End-to-end recipe
Confirm the workspace
Call
list_accessible_workspaces and switch if needed.Build the work queue
Call
get_process_hierarchy_tree — the whole tree, or filtered to the value stream of interest. The leaves become your work queue.Fan out in parallel across leaves
For each leaf:
get_process_details— current version, steps, dependencies. Note step count, manual vs system steps, exception count.list_process_observations— exception volume per process.
Hunt high-leverage patterns in the graph
Call
search_knowledge_graph for patterns: “manual approval”, “duplicate entry”, “data re-keying”, “exception handling”, “swivel-chair workflow”. Then explore_graph_neighbors on each pattern entity to see which processes and systems touch it.Check workspace metadata
Call
get_attribute_configurations to look for “automation status”, “system of record”, “control level”, or similar attributes that help rank candidates.Avoid duplicating prior Advisor work
Call
list_objective_findings. If Advisor has already analyzed this area, call get_objective_context_bundle to load prior thinking and build on it. If not, surface a fresh candidate set.Confirm each top candidate
For each top candidate:
get_process_observations— confirm the deviation or manual pattern with concrete evidence.get_downstream_dependencies— first cut at blast radius.
Synthesize a ranked candidate set
Process IDs, observation counts, dependency depth, similarity to known patterns, evidence trail.
Cross-check vendor tooling (optional)
Call
research_web on the highest-ranked candidates to see if there’s published vendor or framework guidance worth pulling in.What to surface in the brief
- A ranked list of candidate processes
- For each: observation count, dependency depth, pattern signal
- Citable process IDs and observation timestamps
- Gaps where the workspace doesn’t have enough evidence yet