Melaya — Build AI agents for any job. Agentic platform for research, ops, outreach, reporting — and the only one where agents can actually trade.

// USE CASE · PM

Run programs that surface the truth,before the steerco does.

Most PMOs find out a milestone slipped when the sponsor asks why. Status decks take a full day, risk registers go stale between reviews, and dependencies live in three Slack threads nobody reads. Melaya lets you build a delivery crew that scopes the work, scores the risk, drafts the steerco update, and stages every Jira move for approval. You keep the relationships, the agent does the spreadsheet hours, the audit log keeps the receipts.

See the pipelines ↓
01
// What breaks today

The status quo costs more than the agent does.

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.

  1. 01

    PMs lose a full day a week assembling steerco decks from Jira exports, Slack threads, and retro notes that never agree on the same numbers.

  2. 02

    Risk registers go stale between monthly reviews, so the first time anyone hears about a tier-1 dependency slipping is when the milestone misses by three weeks.

  3. 03

    Cross-team handoffs sit in three different tools, and the PM finds out two squads were blocked on the same API spec only after the sprint demo.

02
// Pipelines you can build

Compose. Approve. Replay.

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.

P01

Scope an initiative into a WBS

On an inbound charter, decompose epics into features and stories with INVEST acceptance criteria. Static context holds the MoSCoW rules and DoR so scope baselines stay consistent across runs.

P02

Refresh the risk register weekly

Pull ticket slippage, vendor incidents, and dependency status, then re-score probability and impact. Cross-run memory carries last week's mitigation owners so risks above score 15 do not reset between reviews.

P03

Draft the steerco status update

Compile RAG status, top three risks, budget variance, and the go or no-go ask into a 60-second board narrative. HITL gate blocks send until the PM approves wording, attachments, and recipient list.

P04

Synthesize the sprint retro

Read retro notes, velocity, escaped-defect counts, and carry-over rates, then surface the three patterns and one action per pattern. The rag_retrieve tool pulls prior retros so chronic issues are named, not rediscovered.

P05

Prep stakeholder comms for a milestone

Map the influence-interest matrix, then draft tier-appropriate updates for engineering, product, and the C-suite. Scoped tools restrict reads to the approved comms library so no unreleased commitments leak.

P06

Forecast 12-week resource capacity

Model squad capacity against the roadmap, flag over and under allocation, and price hire, contract, defer, or resequence options. Replay shows the exact dependency that drove every recommendation.

03
// The crew

Project & Program crew

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.

Project Scoper

ProjectScoper

Decomposes initiatives into a Work Breakdown Structure, enforces INVEST acceptance criteria, and flags scope creep before it lands in a sprint.

SCRUM

Scrum Master

ScrumMaster

Plans sprints with capacity buffers, tracks velocity trends, runs backlog grooming, and surfaces impediments within 24 hours of identification.

Delivery Lead

DeliveryLead

Maintains the live critical path across workstreams, RAG-rates every milestone, and writes a recovery plan within 48 hours when status turns amber.

Risk Register

RiskRegister

Owns probability-impact scoring, assigns risk owners and mitigations, and escalates any risk above score 15 to the sponsor.

Stakeholder Manager

StakeholderManager

Maps the influence-interest matrix, builds the RACI, and writes tier-appropriate status updates for engineers, product owners, and the C-suite.

Quality Gate

QualityGate

Enforces Definition of Done at every release, scores quality 0 to 100, and blocks releases that fail coverage, security, or performance gates.

Resource Planner

ResourcePlanner

Models 12-week rolling capacity, flags over and under allocation, and prices hire vs contract vs scope-cut trade-offs against burn rate.

PMO Synthesis

PMOSynth

Synthesizes the crew into a board-ready health view with RAG status, top risks, budget variance, and a go or no-go recommendation.

04
// Scoped tools

Only the actions you grant.

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.

shared/tools/project_mgmt/

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.

jira_get_issuesjira_create_issuejira_update_issuelinear_get_issueslinear_create_issuelinear_update_issuenotion_query_databasenotion_create_pagenotion_search
shared/tools/clickup_tools/

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.

clickup_teamsclickup_spacesclickup_listsclickup_tasksclickup_create_task
shared/tools/monday_tools/

Pull board state and capacity from Monday for resource planning. monday_create_item and monday_update_item are HITL-gated writes.

monday_boardsmonday_boardmonday_usersmonday_create_itemmonday_update_item
shared/tools/knowledge/

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.

build_knowledge_from_textbuild_knowledge_from_file
shared/tools/messaging/

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.

telegram_send_messagediscord_send_messagediscord_send_embed
shared/tools/email/

Read sponsor and vendor threads for context, then stage steerco status emails for approval. gmail_send is HITL by default for this crew.

gmail_sendgmail_read
shared/tools/calendar/

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.

gcal_list_eventsgcal_create_eventgcal_find_free_slots
shared/tools/core/

General research and structured fetch plus the explicit pause_for_human checkpoint personas can call to force a HITL gate mid-workflow.

web_searchhttp_requestpause_for_human
05
// Three knowledge layers

The crew reads what you give it.

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.

L1

Static context

includeContext

Per-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.

L2

RAG retrieval tool

rag_retrieve

A 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.

L3

Cross-run memory

pipeline_memory

Pipeline-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.

07
// FAQ

Questions we get every week.

Will the agents move Jira tickets on their own?

No, not by default. Every write to Jira, Linear, ClickUp, Monday, or Notion runs behind a HITL gate. The crew prepares the ticket, status change, or comment and the PM approves before it lands. You can lift the gate per template once the pipeline earns trust.

Can the agents reason over our project data?

Three ways. Static context attaches the charter, DoD, and RACI to specific personas every run. The rag_retrieve tool lets ProjectScoper and DeliveryLead pull from prior PRDs, retros, and risk logs on demand. Cross-run memory carries last week's risk register into this week's review so mitigation owners do not reset.

Does this replace Asana, Monday, Linear, or ClickUp?

No, it sits next to them. Melaya is the planning, scoring, and synthesis layer. Your team keeps Jira, Linear, ClickUp, Monday, or Asana as the system of record. The HITL gate hands approved updates to the tool you already pay for so the engineering workflow does not change.

How do we keep status updates from sounding like AI?

Drafts cite the exact ticket, PR, retro note, or velocity chart they read. Reps can require a citation on every claim as a HITL pre-check, and the StakeholderManager reuses phrasings from your last five approved updates loaded into the knowledge store.

Which models can we run the crew on?

Any. Claude on PMOSynth where reasoning quality earns the cost, GPT on the drafting personas, a local Ollama on RiskRegister when the data cannot leave your network. Each agent picks its own model and provider.

How fast can a delivery team get the first pipeline running?

With Jira or Linear connected, the weekly status pipeline is a 4-node canvas: pull tickets, score risks, draft the update, approve. Most teams ship it in a working session and have the first reviewed status note in the sponsor's inbox the same day.

How does this handle audit and governance?

Every run logs every step, every tool call, every model invocation, and every approval decision. Replay any run at any time. Regulated programs use the audit log as evidence for steering committees and external auditors.

Can we restrict which personas can write to which system?

Yes. Tool access is per-agent. ScrumMaster can read every backlog but only write to a single Jira project. PMOSynth can read the risk register but only post to a private board channel. Scoped tools are the default, broad access is opt-in.

Build project & program teams pipelines on Melaya.

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
Join the community