Process Intelligence

When to use

• "Analyze my pipe"
• "How can I improve this process?"
• "Is this pipe optimized?"
• "Where are the bottlenecks?"

skills/process-design/

Prerequisites

• Pipe ID or name is known (or searchable via

  search_pipes

  ).
• Read access to the pipe's cards and phase data.

Steps — investigation (Round 1)

1. Get pipe structure:
   MCP:

   get_pipe pipe_id=<id>

   Capture: phases, field count per phase, automation count.
2. Sample recent cards (last 30–50):
   MCP:

   get_cards pipe_id=<id> first=50 include_fields=true

   Look for: stale cards (no updates), cards stuck in early phases, phases with 0 cards.
3. Check automations:
   MCP:

   get_automations pipe_id=<id>

   Look for: phases with no automations (manual handoffs), repeated manual steps.
4. Check AI configuration:
   MCP:

   get_ai_agents repo_uuid=<PIPE_UUID>

   Look for: no AI agents despite manual categorization or triage patterns.

Diagnosis framework

Steps — improvement (Round 2+)

1. Identify the stalled phase and threshold (e.g., "Under Review" > 3 days).
2. Check automation events:

   get_automation_events

3. Create the automation:
   MCP:

   create_automation pipe_id=<id> name="Overdue Alert" trigger_event="card_overdue" actions='[{"type":"send_email","to":"assignee"}]'

4. Report: "Added overdue automation to 'Under Review' phase — triggers after 3 days and emails the assignee."

1. Identify a field that should only show when another field has a specific value.
2. Create the condition:
   MCP:

   create_field_condition pipe_id=<id> phase_id=<phase_id> action="show" when='{"field_id":"<f1>","value":"Yes"}' fields='["<f2>"]'

Output format per round

## Analysis — [Pipe Name]

### Findings
- [Finding 1]: [evidence from tool calls]
- [Finding 2]: ...

### Implemented this round
- [Change 1]: [tool called + result]

### Next round (if approved)
- [Opportunity]: [proposed action]

Success criteria

• Each round produces a concrete visible change (new automation, field condition, phase cleanup).
• Card throughput improves in the affected phase within the next sprint.
• No improvement causes a regression (verify with

  get_pipe

  and

  get_cards

  after each round).

Failure modes

• get_cards

  returns empty: pipe may have no cards yet — analyze structure only and recommend first card creation.

• create_automation

  fails with unknown event: use

  get_automation_events

  to list valid triggers.
• User pushes back on automation: explain what the automation does in plain language before creating.

See also

• skills/automations/

  — detailed automation creation guide.

• skills/ai-agents/

  — add conversational agents for user-facing automation.

• skills/observability/

  — check credit and execution data to quantify improvement impact.