learn-ai-project-management-with-phoebe / PM session 6 of 10
Learn AI + Project Management with Phoebe · PM track · Session 6 of 10

The status report: from fluent and empty to steerco-ready

Week 9 of Northwind. The ingest slipped 14 days, a vendor has gone quiet, and you have forty Slack messages, a ticket export and two half-written notes. Tonight you build the report that carries that week honestly - and you watch, live, what each thing you supply is worth. The simulator scores the report as you feed it: 24 out of 100 with nothing, 100 with everything.

🟡 PM track PMs · TPMs · delivery leads Live simulator on this page 45 min
0-3 · Welcome 3-15 · Why reports fail 15-42 · The simulator + your own week 42-45 · Q&A
Part 0

Where we are

You have a workspace (b1), a charter (b2), a milestone architecture (b3), a dependency map (b4) and a live risk register (b5). Northwind is now nine weeks in and M3 - raw ingest signed off - has slipped from 10 August to 24 August. This is the week the reporting either earns trust or quietly loses it. Status reporting is also the single most common first use of AI in delivery teams, which makes it the most common place to go fluently, confidently wrong.

Live - presented in session Self-study - read after class ★ Try it now prompt Official sources covered
★ What you walk out with today A six-check rubric that separates a report a steerco can act on from one it can only nod at, first-hand experience of what each check is worth (the simulator scores it), your own week run through the same rubric, and a reusable report prompt that refuses to write "good progress".
Part 1 · covers the reporting canon + the AI failure mode

Why the AI-drafted status report fails 6 min live

Ask any model to "write a weekly status report" from a pile of programme noise and you get something readable, well-structured, and useless. Not because it is stupid - because you asked it to compress ambiguity, and compression without a rule produces the average of everything. "Amber. Good progress, some blockers." Nobody can act on that, and worse, nobody can argue with it.

SIX PARTS, IN THIS ORDER 1 · Status, by the rule amber means what we agreed 2 · What changed since last week, with numbers 3 · Actions one owner, one date, each 4 · Decisions taken what, when, by whom 5 · Evidence ticket ids and real numbers 6 · The ask the decision you need, by when Drop any one and the report degrades in a specific way: no rule and the colour is a mood, no delta and a 14-day slip reads like a stable plan, no ask and it is a broadcast. A report a sponsor cannot challenge is not a safe report. It is an unfalsifiable one.
🔍 Click to zoom - the six parts, and the specific failure each missing part causes
LiveThe four fluent failures3 min

Every weak AI status report fails in one of four recognisable ways. Learn to spot them and you can review a draft in thirty seconds.

  • The mood ring. A RAG colour with no rule behind it. Two readers disagree about whether the programme is in trouble, so nobody acts.
  • The flat photograph. A picture of this week with no comparison to last week. A 14-day slip and a stable plan look identical.
  • The orphan actions. "Follow up on the data-quality issue." Owned by nobody, dated never, and it will appear again next week, reworded.
  • The unfalsifiable claim. "Quality is looking reasonable." No ticket, no number, nothing to challenge - and nothing to trust.
Real world

Amber for eleven weeks. A programme reported amber for eleven consecutive weeks with no agreed definition of amber. Every week the steerco nodded. In week twelve it went red and the sponsor asked why nobody had flagged it - and the honest answer was that everybody had, in a colour nobody had defined. The report was not lying. It just could not carry information.

Self-studyAgreeing the RAG rule before you need it2 min read

Write the rule at kickoff, when nothing is on fire and nobody is defending anything. A workable default:

The colour is a rule, not a mood: Northwind's RAG test This week's gate forecast and open critical risk on time slipping blocked GREEN Every live gate on time, no critical risk open AMBER Gate forecasts 2+ weeks late, credible recovery plan RED Unrecoverable without a steerco: scope, money, or date Agree the rule at kickoff - restating it in every report ends the what-does-amber-mean debate.
🔍 Click to zoom - the colour is a rule, not a mood
ColourMeans
GreenEvery live gate forecasts on or before its date, no critical risk open above the agreed threshold
AmberA gate forecasts 2 or more weeks late, and there is a credible recovery plan attached
RedA gate is unrecoverable without a decision from the steerco: scope, money, or the date moves

Then restate the rule inside every report. It costs one line and removes the entire "what does amber mean here" conversation - which is the conversation that eats the first ten minutes of a steerco that should be spent deciding something.

Part 2 · the live simulator

Watch the report climb: 24 to 100 ★ 12 min · everyone plays

Below is Northwind week 9, fed to a model with everything switched off. Read the report first - it is fluent and it is worthless. Then turn on one lever at a time and watch two things: the score, and the specific failure that disappears. Turn on the scorecard to see which of five real programme weeks come out steerco-ready with your current setup.

Turn on one lever at a time - watch the score climb RAG rule 17 pts Owners + dates 17 pts Decision log 14 pts Evidence 13 pts The ask 9 pts The delta 6 pts Points follow the simulator's own order: the RAG rule and named owners matter most.
🔍 Click to zoom - the RAG rule and named owners are worth the same, and worth the most
How to play it in session Go one lever at a time, in this order: the RAG rule (17 points - the biggest single jump), owners and dates (17), the decision log (14), evidence (13), the ask (9), the delta (6). After each, read only the paragraph that changed. Then flip to the scorecard: with only the RAG rule and owners on, exactly one of the five weeks passes - the quiet one. The slip week needs the delta, the blocked week needs the ask, the steerco week needs decisions plus evidence. The lesson is not "do everything" - it is that the week tells you what it needs.
LiveWhat each lever actually is, on your desk4 min
  • The RAG rule - one line in your house rules and one line restated in every report. Agreed once at kickoff.
  • Owner and date per action - comes from your owner list (b1) and your RACI. If the model cannot find an owner, it must write "TBC - ask [role]", never "the team".
  • The decision log - a running list with ids: D-14, 31 Jul, sponsor, what was decided, what it cost. Session b7 builds it from meeting transcripts.
  • Evidence - ticket ids, dates, and the actual metric. This is the lever that makes the report challengeable, which is what makes it trustworthy.
  • The ask - the decision you need, the options, the cost of each, and the date after which it stops being available.
  • The delta - forecast dates, open criticals, and one throughput number, this week against last week.
The honesty rail The report prose in the simulator is a scripted teaching simulation - a real model words it differently every time. The rubric is real, and so is the rule underneath it: the dates came from the team, the model only drafted, and a named human signs it before it goes out.
Demo 1 of 2

Run your own last week through the rubric ★ 8 min · everyone builds

Open the last status report you actually sent - not a good one, the real most recent one. Score it against the same six checks. Most people land between 40 and 60 the first time, and the missing points are always the same two.

Check 1 - is the status colour defined by a written rule that appears in the report? If the rule lives only in your head, score zero.

Check 2 - can a reader see what changed since last week, with at least one number?

Check 3 - does every action carry exactly one named owner and one date?

Check 4 - are the week's decisions recorded with who took them and when?

Check 5 - can every claim be traced to a ticket, a metric, or a document?

Check 6 - is there a clear ask, with a deadline and the cost of not deciding?

Total your score out of six. Whatever you scored, fix the single cheapest gap this week rather than all of them. Usually it is the RAG rule, which takes one meeting.

Real world

Four out of six, and the two missing were the expensive ones. A senior PM scored her own reports and found she was strong on actions, decisions, evidence and the delta - and had never once written the ask or defined amber. Nine months of reports, and not one had told the sponsor what decision she needed. She had been escalating in the corridor instead, which worked until the sponsor changed. Two lines fixed it permanently.

Demo 2 of 2

The report prompt that refuses to write "good progress" ★ 10 min · build your own

Now encode the rubric so you never grade by hand again. This prompt lives in your workspace; in b9 it becomes a skill that runs every Thursday against your real tools.

Paste the prompt below into your programme workspace, with your context pack loaded.

Feed it a genuinely messy week - raw notes, exported tickets, unedited threads. Do not tidy the input first; tidying it is the job you are trying to move.

Read the "gaps" block it returns before the report itself. That block is the model telling you what your week is actually missing - usually an owner or a real number.

Fill the gaps from the team, not from the model. Then re-run and send.

★ Try it now - the weekly status report promptDraft this week's exec status report from the material below, using the pack in this workspace. RULES - a draft that breaks any of these is rejected: 1) Status colour must follow our written RAG rule, and restate the rule in one line. 2) Show the delta: forecast gate dates, open criticals, and one throughput number, this week vs last week's report in the pack. 3) Every action: exactly one named owner and one date. If unknown, write "TBC - ask [role]". Never "the team". 4) List decisions taken with id, date and who took them. If none, say "none this week". 5) Every claim carries a ticket id, a metric, or the document it came from. No adjectives about progress - numbers or nothing. 6) End with "What I need from you": the decision, the options with costs, and the date after which it is no longer available. Then, BEFORE the report, output a GAPS block: everything above you could not fill from the material, and exactly who I should ask. Do not fill a gap by inference. Length: one page. Match the format of the most recent report in the pack. MATERIAL: [paste the week - notes, tickets, threads, unedited]
The version that produces the mood ringHere are my notes from this week. Please write a professional weekly status update for senior stakeholders, summarizing progress, highlights and any blockers.
Why the GAPS block matters more than the report A model asked to summarize will always produce something - that is the whole failure mode. Forcing it to declare what it could not source turns a smoothing machine into a checklist that audits your week. Most PMs find the same gap twice a month: an action with no real owner. That was always true; the report just used to hide it.
Homework

Try it yourself - this week ◐ 30-45 min total

Source material

Official sources covered

Taught from the delivery reporting canon, PMI's AI guidance on oversight, and the Northwind case carried from the PMO course. This session covers:

PMBOK Guide 7 - measurement and stakeholder performance domainsPart 1 · what a report is for and who it serves
PMI - AI in project management: status reporting as first adoptionPart 0-1 · why this is the highest-risk first use
PMI - Standard for AI in Portfolio, Program and Project Management (2026)Part 2 · human oversight with real intervention, not a rubber stamp
learn-tech-project-pmo-with-phoebe - tracker and RAG statusPart 1 · the by-hand version of this artifact
Check yourself

Three questions before you go 🎯 ◐ 90 seconds

1 · In the simulator, which single lever is worth the most points - and why?

The RAG rule and owners tie at 17 points, and the rule is the floor: an undefined amber is the PM's mood, so two readers disagree about whether the programme is in trouble and nobody acts.

2 · Your draft says data quality is "looking reasonable". What is wrong with it?

A claim nobody can check is not a safe claim. The evidence lever exists to make the report challengeable; 96.4% against a 99% gate is a fact, "reasonable" is a feeling with a suit on.

3 · The GAPS block says an action has no owner. What do you do?

The gap is the finding. An inferred owner is an invented commitment, and "the team" is how an action survives untouched for a month. Fill gaps from people, never by inference.

PM session 6 cheat sheet · pin this

The six checksrule-based status · delta · owner+date · decisions · evidence · the ask.
The mood ringa RAG colour with no written rule. Fix it once at kickoff, restate it every report.
The flat photographno week-on-week comparison, so a 14-day slip reads like a stable plan.
Orphan actions"the team will follow up" survives untouched for months. One name, one date.
Unfalsifiable claims"looking reasonable" cannot be challenged, so it cannot be trusted. Numbers or nothing.
The askdecision needed, options with costs, and the date it expires. No ask = a broadcast.
The GAPS blockmake the draft declare what it could not source. The gaps are your real findings.
The railthe model drafts, the dates come from the team, a named human signs it.