Three pains every sales and BD team hits weekly. Each one is what your reps actually complain about, not what a feature page would call them.
Breaking a new initiative into a work breakdown structure eats a full day before anyone touches a ticket.
Cross-team dependencies get tracked in someone's head until a milestone slips without warning.
The risk register goes stale between board meetings, so surprises land at the worst possible time.
Every pipeline below is a shape you wire on the canvas using the crew and tools further down. Not a feature we ship for you, a pattern you configure.
ProjectScoper decomposes the initiative into a WBS from the brief and any reference docs you feed it, and DeliveryLead maps the result against existing cross-team dependencies before the first ticket gets filed.
RiskRegister pulls live issue state from Jira and Linear to score probability and impact, and DeliveryLead checks each risk against the critical path, so the register reflects reality instead of last quarter's snapshot.
StakeholderManager maps every stakeholder's influence and interest, drafts the update, and PMOSynth folds it into the broader project narrative before gmail_send delivers it and gcal_create_event books the review.
ScrumMaster tracks backlog grooming and velocity across the sprint, and QualityGate enforces acceptance criteria and DoD/DoR compliance on each ticket before it's marked done.
ResourcePlanner models current and projected capacity straight from your Monday.com and ClickUp boards, while DeliveryLead checks the forecast against delivery milestones.
useCases.list.project-management.workflows.5.body
Real personas from the project_management crew. Each ships with a tuned system prompt and a default tool allowlist. Swap models per persona on the canvas.
Decomposes initiatives into a Work Breakdown Structure, enforces INVEST acceptance criteria, and flags scope creep before it lands in a sprint.
Plans sprints with capacity buffers, tracks velocity trends, runs backlog grooming, and surfaces impediments within 24 hours of identification.
Maintains the live critical path across workstreams, RAG-rates every milestone, and writes a recovery plan within 48 hours when status turns amber.
Owns probability-impact scoring, assigns risk owners and mitigations, and escalates any risk above score 15 to the sponsor.
Maps the influence-interest matrix, builds the RACI, and writes tier-appropriate status updates for engineers, product owners, and the C-suite.
Enforces Definition of Done at every release, scores quality 0 to 100, and blocks releases that fail coverage, security, or performance gates.
Models 12-week rolling capacity, flags over and under allocation, and prices hire vs contract vs scope-cut trade-offs against burn rate.
Synthesizes the crew into a board-ready health view with RAG status, top risks, budget variance, and a go or no-go recommendation.
Every tool below is a real shared tool from the Melaya bundle. Allowlist per agent; HITL-gate the writes; revoke any of them in one click.
Read tickets, epics, and project pages from Jira, Linear, and Notion so the crew works against live data. Every create and update call runs behind a HITL gate by default.
Reach into ClickUp spaces and lists for teams running delivery there. clickup_create_task is HITL-gated so no task lands without a PM nod.
Pull board state and capacity from Monday for resource planning. monday_create_item and monday_update_item are HITL-gated writes.
Build the per-workflow knowledge store from charters, PRDs, retro notes, and prior steerco decks. Feeds the rag_retrieve tool and static context across all three knowledge layers.
Post the Monday risk digest or sprint health card to the delivery channel. Every send is logged in the same audit trail as Jira writes and is HITL-gated by default.
Read sponsor and vendor threads for context, then stage steerco status emails for approval. gmail_send is HITL by default for this crew.
Read squad calendars for true capacity and schedule retro or steerco slots that respect everyone's leave. gcal_create_event runs behind a HITL gate.
General research and structured fetch plus the explicit pause_for_human checkpoint personas can call to force a HITL gate mid-workflow.
Every pipeline ships with three layers of knowledge access. Mix and match per agent on the canvas. No shared vector space with another tenant, no surprise reads, no opaque retrieval.
includeContextPer-pipeline documents appended to specific agents' input on every run. The ICP brief, playbook, pricing sheet, or won-deal email corpus. Whatever needs to be there before the agent thinks. You pick which personas get which docs.
rag_retrieveA scoped tool granted per-agent. When the agent decides it needs more depth, it queries the workflow's vector store on demand. Same knowledge base as Static context, accessed only when the model asks for it.
pipeline_memoryPipeline-level state that carries from one run to the next. Yesterday's research is in scope for today's follow-up. The crew remembers what it already prospected, what got approved, what was sent. The audit log is the second-order knowledge base.
Sandbox tier is free with no card. Join the waitlist and we will email you the moment a slot opens.
← Back to every use case