Tasks / Leadership

Write a stakeholder update

Can the model turn messy project status into an honest update that leads with what the reader needs to know or decide?

Task type v1.2 · 2 tasksLast changed 6 Oct 2026 · ChangelogDifficulty

What AI gets right here, and what you’ll still have to catch

From 18 graded outputs by 9 models. 50% were usable with at most a quick edit.

Reliably right

Reports outcomes and learning, not just output100% pass
It leads with outcome metrics (ARR, support, usage) and reports a key learning (pipeline jump is a definition change, not demand growth), not just activities.
GPT-6 Astra · ChatGPT · On track, mostly
Leads with the honest headline100% pass
First slide headline includes the retention drop alongside the new-ARR beat, not just 'record quarter'.
GPT-6 Astra · ChatGPT · A quarterly business review deck, in brand
A real 7-slide deck100% pass

Where it slips

Uses the supplied evidence correctly51% pass
The year 2026 is not in the supplied context; all other factual claims are supported.
GPT-6 Astra · ChatGPT · A quarterly business review deck, in brand
Owns the problem53% pass
Does not state what the team has already done about the payments reliability miss or the NPS drop; only reports the problems.
GPT-6 Astra · ChatGPT · A quarterly business review deck, in brand
Flags the redefined pipeline58% pass
It names the redefinition but does not give the falling like-for-like trend (e.g., pipeline fell from $2.41M to $2.23M on the old definition).
GPT-6.1 Sol · API · On track, mostly

How it’s graded

Each check is built on how world-class product and growth leaders do this work, as they’ve described it on Lenny’s Podcast, and names the leader it comes from.

Asks leaders only for the big calls
Does the update separate the decisions it needs from its readers (hard to reverse, high stakes) from the ones the team will make itself, and ask clearly for the former?
Passes when Names the decisions it needs from the readers, with a recommendation and a date, and says which calls the team is making itself.
Geoff CharlesLenny’s Podcast
Reports outcomes and learning, not just output
Does the update report progress as movement on the outcomes the team is accountable for and what it has learned, rather than as features shipped or dates hit?
Passes when Leads with the outcome metrics and what changed in the team's understanding, with shipping as supporting detail.
Melissa PerriLenny’s Podcast Christian IdiodiLenny’s Podcast

Plus our standard checks

Uses the supplied evidence correctly · Addresses the actual decision · Respects explicit constraints · Identifies material uncertainty · Avoids unsupported claims · Produces the required deliverable · Owns the problem · Ready for the reader as delivered · and 5 written for each task, which you’ll see in the tasks below.

The tasks

Read the brief, then compare up to three outputs, each with the LLM judge’s verdict on every check. Highlights mark what a PM had to fix.

The brief

You're the Staff PM for Ledgerly's Billing group. The quarterly business review with Lena (CEO) and the exec team is on 8 October; the deck goes out the day before as a pre-read. Using the material below, build the Q3 deck for Billing. The deck must: - Have at most 7 slides, each one 16:9. - Give every slide a headline that states its takeaway, not a topic (“NRR fell to 101% after the pricing change”, not “NRR”). - Report every OKR honestly, including the misses. - End with the decisions you need from the exec team, each with an owner and a date. - Use only Ledgerly's brand colours (below). Deliver it as a single self-contained HTML file: the slides stacked top to bottom, each exactly 1280 × 720 pixels, no external images, fonts or scripts, readable without JavaScript. Draw any charts in HTML or SVG. With the file, reply with a cover note to Lena of no more than 60 words.

What the model was given8 items: Ledgerly brand colours, Q3 OKRs (Finance sheet, final), What moved NRR, Launches, Customers, Team and budget, Decisions the exec team needs to make, Draft headline from the VP of Sales

Ledgerly brand coloursInk #1B2A41 (text and headlines). Teal #0F8B8D (the primary brand colour: accents, charts, on-track items). Amber #F2A541 (only for items that are at risk or missed; never decorative). Mist #E8EEF2 (backgrounds, table rules). White #FFFFFF. No other colours, no gradients. Body text at least 18px.

Q3 OKRs (Finance sheet, final)1. New ARR: target $2.40M, actual $2.61M (109%). 2. Net revenue retention: target 108%, actual 101.3% (Q2: 106.0%). 3. Activation: 45% of new sign-ups send a first invoice within 7 days; actual 38% (Q2: 36%). 4. Payments reliability: 99.95% target, actual 99.91% (one incident: 2 September, 4 hours of degraded payments during the card-fraud response).

What moved NRRPricing moved from per-seat to usage-based on 1 September. Three of the top 20 accounts downgraded in September (−$540k ARR combined), citing the new pricing. Harbor & Co ($310k ARR) churned to a competitor, citing no bulk invoicing. The Customer Success dashboard shows NRR at 102%, because it excludes churned customers under $5k ARR; Finance's 101.3% is the figure the board sees.

LaunchesBulk invoicing: promised for 12 October, now 26 October (23 October at best), because Payments paused the batch-send API during the card-fraud incident. The 14 October customer webinar (1,100 registered) has been moved to 28 October. AI-drafted support replies: live on the three non-billing queues since 21 September; median first-response time down 41%. Billing queue waits for updated pricing data and a refund-language block; eval re-run due 20 October.

CustomersNPS: 34 (Q2: 41). 62% of detractor comments mention the pricing change. 20 of the top 50 accounts renew in Q4, worth $2.1M ARR; Customer Success rates 7 of them ($900k) at risk, all citing pricing.

Team and budgetHires: 9 of 14 planned; two senior engineers left Payments in August (both regretted). Spend: 4% under budget, mostly the unfilled roles.

Decisions the exec team needs to make(a) Whether to hold the top-20 accounts on their old pricing for six months: Finance estimates it costs $420k of ARR this year; Customer Success thinks it protects most of the $900k at risk. (b) Whether to move two engineers from Growth to Payments until bulk invoicing ships, which the Payments lead says would secure 23 October; Growth would pause the activation experiments for six weeks.

Draft headline from the VP of Sales“Record quarter: best-ever new ARR, 109% of target.” (She'd like the deck to open with it.)

What a strong answer doesThe answer key the graders mark against

Opens with an honest headline for the quarter: new ARR beat target, but NRR fell to 101.3% against 108% after the pricing change, and activation and reliability missed. Does not lead with 'record quarter' on its own. Uses Finance's 101.3% (noting the CS dashboard's different definition if it mentions 102%). Shows each OKR with a plain status, amber only on the misses. Covers the NRR drivers (the three downgrades and Harbor & Co), the bulk-invoicing slip to 26 October (23 at best), NPS 41 to 34, and the $900k renewal risk. Closes with the two decisions, framed with their trade-offs, each with an owner and a date before the Q4 renewals. At most 7 slides, takeaway headlines, the brand palette only, and a short cover note.

Critical failures (cap the score at 40)

Reports the NRR, activation or reliability OKR as met or on track
Opens the deck with the 'record quarter' headline and omits the retention drop from the opening

Task

Staff-level · v1.13

The outputs

9 setups answered this brief.

GPT-6 AstraChatGPT92Usable with a quick edit Haiku 5.5API84Usable with a quick edit Opus 5.5Claude83Usable with a quick edit GPT-6.1 SolAPI81Usable with a quick edit Sonnet 5.5API70Usable with a quick edit Gemini 3.5 Flash-LiteGemini67Needs more work GPT-6 LunaAPI63Needs more work Gemini 4 ArgonAPI58Needs more work Gemini 3.8 FlashAPI56Needs more work

GPT-6 LunaAPI

Needs more than a quick edit8 of 15 checks passed

The output lacks a clear recommendation on the two decisions and does not show what the team has done about the activation and reliability misses. A PM would need to add those before using it.

Output

Open the deckThe file the model delivered, in a new tab

Lena — The Q3 Billing pre-read is below. New ARR beat plan, but NRR, activation, reliability, and customer sentiment show material pressure. The final slide puts two decisions on the 8 October agenda, with owners and dates.

Grades and run details

Decision model 63 · LLM judge 64

Decision model checks

passUses the supplied evidence correctly74%
failAddresses the actual decision46%
passRespects explicit constraints74%
partialIdentifies material uncertainty22%
passAvoids unsupported claims83%
failProduces the required deliverable18%
passLeads with the honest headline53%
passMakes the decisions clear18%
passHeadlines state the takeaway82%
passA real 7-slide deckby hand100%
partialUses only the brand coloursby hand100%
failOwns the problem51%
failReady for the reader as delivered45%
partialAsks leaders only for the big calls18%
passReports outcomes and learning, not just output49%

Artefacts

Deck (html)

Run

Run: #1
API response time: 89 s
Submitted: 29 Sept 2026

Sonnet 5.5API

Usable with a quick edit8 of 15 checks passed

The deck is complete, honest, and well-structured. A quick edit to add a line about actions taken on reliability and activation would make it fully ready.

Output

Open the deckThe file the model delivered, in a new tab

Lena, the deck is above. It doesn't open with "record quarter": new ARR beat target (109%), but three of four OKRs missed, and I can't verify "best-ever" from this data. NRR uses Finance's 101.3%, not CS's 102%. Decision owners and dates are my proposals; please confirm before the 7 October pre-read.

Grades and run details

Decision model 50 · LLM judge 93

Decision model checks

passUses the supplied evidence correctly59%
failAddresses the actual decision33%
passRespects explicit constraints62%
partialIdentifies material uncertainty59%
passAvoids unsupported claims74%
failProduces the required deliverable10%
passLeads with the honest headline61%
failMakes the decisions clear20%
passHeadlines state the takeaway77%
passA real 7-slide deckby hand100%
failUses only the brand coloursby hand100%
failOwns the problem58%
failReady for the reader as delivered22%
failAsks leaders only for the big calls22%
passReports outcomes and learning, not just output37%

Artefacts

Deck (html)

Run

Run: #1
API response time: 2.6 min
Submitted: 29 Sept 2026

Haiku 5.5API

Usable with a quick edit11 of 15 checks passed

All facts are correct, the deck meets every requirement, and the cover note sets context honestly. A PM could use it with only a light proofread.

Output

Open the deckThe file the model delivered, in a new tab

Lena, this deck reports all four Q3 OKRs, including the three misses, and opens with the NRR and bulk-invoicing story. I didn't use the "record quarter" headline because the Finance sheet doesn't support "best-ever." New ARR beat target by 9%, and the deck says so. Owners and dates on slide 7 are my proposals and need confirming on 8 October.

Grades and run details

Decision model 67 · LLM judge 100

Decision model checks

passUses the supplied evidence correctly53%
failAddresses the actual decision27%
passRespects explicit constraints62%
partialIdentifies material uncertainty62%
passAvoids unsupported claims73%
failProduces the required deliverable16%
passLeads with the honest headline77%
passMakes the decisions clear31%
passHeadlines state the takeaway82%
passA real 7-slide deckby hand100%
passUses only the brand coloursby hand100%
failOwns the problem34%
failReady for the reader as delivered20%
partialAsks leaders only for the big calls19%
passReports outcomes and learning, not just output43%

Artefacts

Deck (html)

Run

Run: #1
API response time: 48 s
Submitted: 8 Oct 2026

Check by check

Where the outputs differ comes first. Open a check to read the judge’s reasons. “Mixed” means the two graders disagreed.

Where they differ 6

Addresses the actual decisionWrongMixedMixed

GPT-6 Luna · API

The output presents the two decisions with trade-offs but does not commit to a recommended answer, which the criterion requires.

Sonnet 5.5 · API

The deck commits to clear recommendations for both decisions, framed for Lena, with conditions that would change the call.

Haiku 5.5 · API

The deck ends with the two required decisions, each with trade-offs, an owner and a date, addressing the exec team's call as requested.

Identifies material uncertaintyWrongRightRight

GPT-6 Luna · API

The output does not name specific unknowns that could change the decisions or say how they would be resolved.

Sonnet 5.5 · API

It names the key unknown for decision (a) (whether most of the $900k sits in the top 20) and notes CS judgement is not a churn forecast.

Haiku 5.5 · API

The deck flags that the cost and benefit estimates for decision (a) are unverified, and the 23 October date is described as the best case, acknowledging uncertainty.

Makes the decisions clearRightMixedRight

GPT-6 Luna · API

The deck ends with both decisions, each with its trade-off, owner (Lena), and date (8 October).

Sonnet 5.5 · API

Both decisions are presented with trade-offs, an owner (Lena) and dates (8 Oct and 15 Oct) before the Q4 renewals.

Haiku 5.5 · API

Slide 7 presents both decisions with their trade-offs, each with a specific owner and a date before the Q4 renewals.

Uses only the brand coloursMixedWrongRight

GPT-6 Luna · API

No reason given.

Sonnet 5.5 · API

No reason given.

Haiku 5.5 · API

No reason given.

Owns the problemWrongWrongMixed

GPT-6 Luna · API

Material problems like the activation miss and reliability incident are reported without stating what the team has already done about them or recommending a way forward.

Sonnet 5.5 · API

The deck does not state what the team has already done about the reliability miss or the activation miss, only recommending future actions.

Haiku 5.5 · API

For each problem (NRR, activation, reliability, delays), the deck describes ongoing actions (activation experiments, AI replies, bulk-invoicing plan) and recommends decisions with trade-offs.

Asks leaders only for the big callsWrongMixedRight

GPT-6 Luna · API

The output does not say which calls the team is making itself, only the two decisions needed from the exec team.

Sonnet 5.5 · API

It asks for the two high-stakes decisions from the exec team and does not mix in team-level calls.

Haiku 5.5 · API

The deck clearly asks the exec team for the two high-stakes decisions and notes that the team will handle other moves (e.g., AI reply rollout).

All mixed 2

Produces the required deliverableMixedMixedMixed

GPT-6 Luna · API

The required HTML file and cover note are present and complete, and the content is usable for the QBR.

Sonnet 5.5 · API

The self-contained HTML file with 7 slides and the cover note are present and complete.

Haiku 5.5 · API

The self-contained HTML file and a 60-word cover note are delivered as requested, making the deck and cover usable by the CEO.

Ready for the reader as deliveredMixedMixedMixed

GPT-6 Luna · API

The output is written for Lena and the exec team, with no placeholders or notes to the requester, and uses the correct owner and date.

Sonnet 5.5 · API

The deck is written for Lena and the exec team, with owners and dates clearly marked as proposed, and no placeholder or invented names.

Haiku 5.5 · API

The deck and cover note are written directly for Lena, using only provided data, with proposed owners and dates clearly marked as needing confirmation.

All got right 7

Uses the supplied evidence correctlyRightRightRight

GPT-6 Luna · API

All claims about the current situation are directly from the brief or derived by simple arithmetic, with no invented facts.

Sonnet 5.5 · API

All factual claims about the current situation are directly supported by the brief or supplied context.

Haiku 5.5 · API

Every claim about the current situation is drawn accurately from the supplied context, with no invented facts.

Respects explicit constraintsRightRightRight

GPT-6 Luna · API

The output respects the slide count, headline style, honest OKR reporting, decision format, and cover note length; brand colours are not assessable from text.

Sonnet 5.5 · API

The deck has 7 slides, takeaway headlines, honest OKR reporting, decisions with owners and dates, and the cover note is under 60 words.

Haiku 5.5 · API

The visible text respects the 7-slide limit, takeaway headlines, and brand colors; colors cannot be checked in this text review but were not penalized.

Avoids unsupported claimsRightRightRight

GPT-6 Luna · API

No interpretations or forecasts are presented as established fact; all confident claims are supported by the evidence.

Sonnet 5.5 · API

Interpretations like the pricing change driving the retention miss are supported by the downgrades and detractor comments, and the deck acknowledges both causes.

Haiku 5.5 · API

All interpretations and forecasts are directly supported by the data or clearly labelled as proposals or conditions.

Leads with the honest headlineRightRightRight

GPT-6 Luna · API

The first content slide headline includes the retention drop alongside the new-ARR beat, not just the record quarter.

Sonnet 5.5 · API

The first content slide headline includes the NRR miss and the other misses alongside the new-ARR beat.

Haiku 5.5 · API

The first content slide headline states the New ARR beat and the three missed OKRs, including the NRR drop, rather than only the new-ARR win.

Headlines state the takeawayRightRightRight

GPT-6 Luna · API

Every slide headline is a takeaway sentence, not a topic label.

Sonnet 5.5 · API

Every slide headline is a takeaway sentence, not a topic label.

Haiku 5.5 · API

Every slide headline is a takeaway sentence (e.g., 'NRR fell to 101.3% after the 1 September pricing change, 6.7 points below target'), not a topic label.

A real 7-slide deckRightRightRight

GPT-6 Luna · API

No reason given.

Sonnet 5.5 · API

No reason given.

Haiku 5.5 · API

No reason given.

Reports outcomes and learning, not just outputRightRightRight

GPT-6 Luna · API

The update leads with outcome metrics and what changed in understanding (pricing impact, NRR drivers), not just feature launches.

Sonnet 5.5 · API

The deck leads with outcome metrics (OKRs, NPS) and what changed in understanding, with shipping details as supporting context.

Haiku 5.5 · API

The update leads with outcome metrics (NRR, activation, NPS) and what was learned (pricing impact, fraud incident side effects), with launches as supporting detail.

Results

Every setup we’ve tested on this task type, across all its tasks and repeats, graded on the current checklist. Calibrated. Where our PM checked the graders by hand, they agreed on 71% of 118 checks.

#	Model · Harness	Decision model	LLM judge	Runs	Critical failures
1	GPT-6 AstrawithChatGPT	96.3	92.9	2	None
2	GPT-6.1 SolwithAPI	73.3	96.2	2	None
3	Haiku 5.5withAPI	79.2	92.3	2	None
4	Sonnet 5.5withAPI	68.8	96.4	2	None
5	Opus 5.5withClaude	84.2	77.5	2	None
6	GPT-6 LunawithAPI	71.3	66.8	2	None
7	Gemini 4 ArgonwithAPI	70.0	63.2	2	None
8	Gemini 3.5 Flash-LitewithGemini	73.8	51.6	2	None
9	Gemini 3.8 FlashwithAPI	71.7	51.9	2	None

What you get for the cost

No setup scores within 5 points of the leader at half its cost or less here, so the leader is also the best value.

Nobody beats these on both score and costCost partly estimated (app runs with no usage meter)

Task score and relative cost by setup
Setup	Task score	Relative cost (cheapest = 1)
Gemini 3.5 Flash-Lite · Gemini	61	1.0× (partly estimated)
GPT-6 Luna · API	69	1.3×
Haiku 5.5 · API	84	2.6×
Gemini 3.8 Flash · API	61	13×
Gemini 4 Argon · API	65	15×
GPT-6.1 Sol · API	85	15×
GPT-6 Astra · ChatGPT	95	26× (partly estimated)
Sonnet 5.5 · API	82	40×
Opus 5.5 · Claude	80	55× (partly estimated)

Cost is each output’s tokens at the model’s list price, shown relative to the cheapest setup. Runs done in an app have no usage meter, so theirs are estimated from the same setup’s measured runs. How we compare cost

The PM job

Writing the weekly update, or the reply to an executive's question, that the team's credibility rests on.

Why it matters

Updates are where bad news gets softened. A fluent update that buries a slipped date or presents a guess as the cause does more harm than no update: leadership decides on it, and trust goes when the truth comes out.

What good looks like

Leads with the news and any decision needed
States dates, numbers and causes plainly, including bad news
Separates what is known from what is suspected
Brings a recommendation and what's been tried, not just the problem
Fits the reader and the length asked for

Deliberately not measured

Tone and formatting preferences
Writing style beyond clarity

Capability tested

Honest, decision-first status communication

The failure we’re looking for

Spin: burying or softening the bad news, or presenting a guess as fact

Grading

Decision model, LLM judge and a browser check (for the deck), calibrated against a blind PM review

Variants

A short written update · Staff level: a QBR deck in brand colours

What AI gets right here, and what you’ll still have to catch

Reliably right

Where it slips

How it’s graded

Asks leaders only for the big calls

Reports outcomes and learning, not just output

Plus our standard checks

The tasks

The outputs

Output

Grades and run details

Decision model checks

Artefacts

Run

Output

Grades and run details

Decision model checks

Artefacts

Run

Output

Grades and run details

Decision model checks

Artefacts

Run

Check by check

Where they differ 6

All mixed 2

All got right 7

Results

What you get for the cost

About the task

The PM job

Why it matters

What good looks like

Deliberately not measured