---
title: PM Intelligence Advisor
---

# PM Intelligence Advisor

An advisory intelligence layer for the AI Project Manager. It reasons across all
your project management boards and surfaces strategic insights, completion
predictions, policy recommendations, and answers to plain-English questions
about your projects.

## What it is

The PM Advisor turns the raw cross-board data (the PM Cross-Board Intelligence
snapshots) into advice a human can act on. It has six parts:

- **Strategic insights** -- it detects cross-board patterns (resource
  conflicts, cascading delays, effort drift, seasonal risk, cross-department
  coordination) and lists them ranked by severity, each with a plain-language
  description and the reasoning behind it.
- **Strategic coaching** -- for the highest-severity insights it derives a
  concrete recommended action ("review and reassign overdue items across
  boards", "investigate the shared upstream dependency", etc.).
- **Prediction narratives** -- for a board it runs a Monte Carlo simulation over
  the board's recent completion velocity to estimate when the remaining work
  will finish (p50 / p85 / p95), with a confidence label and a deadline warning
  when the estimate slips past a due date. A what-if mode re-runs the estimate
  with added/removed items or a velocity change.
- **Policy recommendations** -- it watches how often you approve or deny an
  automation and recommends promoting a trusted action to automatic, or pulling
  a too-eager one back to propose-only.
- **Quick question** -- a box where you type a plain-English question about your
  projects and get an answer grounded in the current board data, with a
  confidence score and suggested follow-up questions.
- **Handoff enrichment** -- enriches shift handoffs with cross-board context
  via the `PM_ADVISOR_HANDOFF_ENRICHED` IPC handler (`enrichHandoff()`).

## Where to find it

The panel appears in the sidebar as **PM Advisor** when the feature is enabled.
It shows:

- **Insights list** -- the current strategic insights, each with a severity
  chip (High / Medium / Low). Empty until the advisor has reasoned over your
  boards.
- **Ask the advisor** -- a quick-question box at the bottom. Type a question,
  press Ask, and the advisor answers with its confidence and a few follow-up
  prompts.

A refresh button reloads the insights and the advisor's status.

The feature is registered as `pm-intelligence-advisor` in `UNRELEASED_FEATURES`
(status: `shipped`), with setting key `pmIntelligenceAdvisorEnabled`. Enable it
in **Settings -> Lab** or set `AMC_SHOW_PM_INTELLIGENCE_ADVISOR=1`. It is
non-spawnable -- the panel renders its own UI and hosts no Claude session.

## How it behaves

The quick-question box first tries a deterministic, template-based answer
grounded in the board snapshots (no AI cost). Depending on your PM AI comfort
setting, a low-confidence template answer may be escalated to an LLM. A daily
per-feature cap bounds the number of LLM calls, and a low-comfort setting keeps
answers template-only.

That cap is **$5/day**, and it is not specific to the advisor: `$5` is the shared
default ceiling for Mission Control's LLM features — the sprint retrospective uses
the same one — set when you have not chosen your own. Individual PM features may
pin a lower cap of their own where their calls are cheaper or run unattended, so
`$5` is the default you get, not a promise that every PM AI feature may spend that
much. The cap resets each day.

### Settings

- **PM Intelligence Advisor enabled** -- master toggle for the advisor panel and
  its background reasoning. Defaults to off until the feature ships.

The advisor also reads the PM AI comfort setting to decide when a question may
be escalated to an LLM.

## For agents

The panel's obligations are pinned in
`pm-intelligence-advisor-contract.md` under `.claude/memory/contracts/`, which is
where to look before changing the panel, the escalation path, or the settings it reads.

## Related

The advisor is one of the tools that dock in Mission Control's main panel, so
[mission-control.md](mission-control.md) is the parent page. Its insights and prediction
narratives are built on the snapshot layer described in
[pm-cross-board-intelligence.md](pm-cross-board-intelligence.md), and the underlying Monte
Carlo completion forecasting is covered in detail by
[pm-predictive-analytics.md](pm-predictive-analytics.md). The other panel that reasons over
the same boards operationally is [pm-operations-engine.md](pm-operations-engine.md), and the
full list of library pages is in [INDEX.md](INDEX.md).