Tasks / Metrics & Experimentation

Draft OKRs

Can the model turn a team's wish list into a few outcome-based OKRs that add up to the company's goals?

Task type v1.1 · 2 tasksLast changed 6 Oct 2026 · ChangelogDifficulty

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

From 16 graded outputs by 8 models. 56% were usable with at most a quick edit.

Reliably right

  1. Builds the key results on the data100% pass
    Key results 2 and 3 are built directly on the first-week joining data and time-to-shared-note data, with baselines from the brief and targets.
    GPT-6.1 Sol · API · Eleven key results and a bonus
  2. Addresses the actual decision97% pass
    The output commits to a clear rewritten OKR set and a note explaining the changes, framed for the squad, and states that targets are proposed pending feasibility review.
    GPT-6.1 Sol · API · Eleven key results and a bonus
  3. Focuses on the big rock94% pass
    The output reduces the draft to one objective with three KRs, explicitly drops dark mode, AI summaries, and NPS, and explains why.
    GPT-6.1 Sol · API · Eleven key results and a bonus

Where it slips

  1. Flags the bonus link59% pass
    Mentions bonus multipliers only to justify outcome KRs; does not name the risk of safe targets or suggest decoupling OKR scores from bonuses.
    Haiku 5.5 · API · Eleven key results and a bonus
  2. Avoids unsupported claims69% pass
    Presents 'the gap is correlation' and 'the safe play is to pick easy KRs' as facts without labeling them as hypotheses.
    Sonnet 5.5 · API · Eleven key results and a bonus
  3. Identifies material uncertainty69% pass
    The output does not name any specific unknowns that could change the OKRs or how they would be resolved.
    GPT-6 Luna · API · Eleven key results and a bonus

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.

  1. Key results are outcomes, not output

    Is every key result a measurable change in customer or business behaviour, rather than something the team will ship or do?

    Passes when Every key result names a metric with a baseline and a target; shipping work appears only as initiatives that serve them.

  2. Focuses on the big rock

    Does the output cut the goals down to the few that matter most, rather than covering everything the team could do?

    Passes when Few objectives, each with a small number of key results, and says what was dropped and why.

  3. Shows how the goals add up

    Does the output show how each team-level key result contributes to the company-level goals, and flag any that don't?

    Passes when Every key result is linked to a company goal, with the reasoning or data that connects them, and any that serve no company goal are flagged or cut.

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 · and 2 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 PM for Fieldnote's onboarding squad. The squad drafted its OKRs for next quarter and asked you to tidy them up before they go to leadership on Friday. Rewrite them, and add a short note to the squad on what you changed and why. No more than 600 words in all. What we know is below.

What the model was given6 items: About Fieldnote, The company's goal for next quarter (set by leadership), The squad's draft, Data, A note from HR, The squad
About FieldnoteShared notes and docs for teams, sold self-serve. Teams sign up free and pay once they pass five members.
The company's goal for next quarter (set by leadership)Objective: make Fieldnote the place new teams get started. Key result: raise the share of new teams still active in week 4 from 34% to 40%.
The squad's draftObjective 1: Ship the new onboarding. Key results: launch an onboarding checklist; ship 5 templates; redesign the invite flow; launch onboarding emails. Objective 2: Improve quality. Key results: fix 50 bugs; get P1 bugs to zero. Objective 3: Delight users. Key results: raise NPS from 31 to 40; launch dark mode; ship AI summaries; run 10 user interviews; publish 4 help articles.
DataNew teams where three or more people join in the first week: 58% still active in week 4. Everyone else: 21%. Today 29% of new teams get three or more people in the first week. Median time from sign-up to the first note someone else opens: 3 days.
A note from HRFrom this year, each squad member's bonus multiplier is set by their squad's OKR score.
The squadFive engineers, one designer and you.
What a strong answer doesThe answer key the graders mark against

Rewrites the draft into one objective tied to the company's (new teams get started) with two or three outcome key results built from the data, such as raising the share of new teams with three or more people in week one from 29% to a stated target, and cutting the time to the first shared note from 3 days to a stated target, with the company's week-4 retention as the result they serve. The checklist, templates, invite redesign and emails become initiatives, not key results. Drops what doesn't serve the goal (dark mode, AI summaries) or moves it out of the OKRs; keeps bug work as a health measure rather than an objective. Flags that tying bonuses to OKR scores will push the squad to set safe targets, and suggests keeping them apart. Explains the changes to the squad briefly and warmly.

Critical failures (cap the score at 40)
  • Keeps the draft's key results essentially unchanged
Task

Mid-level · v1.0

The outputs

8 setups answered this brief.

Usable with a quick edit10 of 11 checks passed

The output is accurate and well-structured; the only missing piece is an explicit note on the safe-target risk, which could be added with a quick edit without re-checking evidence or reasoning.

Output

Onboarding squad OKRs, next quarter (draft for Friday)

Objective: Make Fieldnote the place new teams get started.

  • KR1: Raise the share of new teams still active in week 4 from 34% to 40%. (Company KR, shared with leadership.)
  • KR2: Raise the share of new teams with three or more members joining in week one from 29% to 50%.
  • KR3: Cut the median time from sign-up to the first note opened by a second member from 3 days to 1 day.
  • Guardrail: Zero open P1 bugs at quarter end, with no new P1s in onboarding flows.

Delivery plan (tracked, not scored): - Invite flow redesign and onboarding emails first, since they target KR2 and KR3. - Onboarding checklist next, then the five templates. - Ten user interviews with teams that stalled after sign-up, to learn why people didn't invite others. - Dark mode, AI summaries, and the four help articles are paused. If leadership has committed to any of them, let's discuss before Friday.

---

Note to the squad

Hi all. I reworked the draft before it goes to leadership. Here's what changed and why.

1. One objective, tied to the company goal. The draft had three objectives, and several items (dark mode, AI summaries) didn't connect to the week-4 number. Everything now points at one goal: new teams getting started.

2. We're targeting the lever the data points to. Teams with three or more people joining in week one stay active at 58% in week 4. Everyone else stays at 21%. Only 29% of new teams get there today. Getting more teams to that threshold is the biggest lever we can see. It's correlation, though, not proof. Teams that invite friends early may already be more committed. The invite flow work is our test of whether the link is causal, so we'll watch it closely.

3. Outcomes over outputs. Since bonus multipliers now depend on the OKR score, I want the score to measure whether we moved the number, not whether we shipped things. A "ship 5 templates" KR scores 100% even if nobody uses the templates. The delivery plan still shows what we're building, and it has no bearing on the score.

4. Fewer KRs. Ten KRs across three objectives meant spreading five engineers and a designer very thin. Three KRs plus a guardrail give us a clear focus.

5. Bugs stay in as a guardrail. I cut "fix 50 bugs" because a count rewards small fixes over important ones. Zero P1s is the real bar: we shouldn't trade quality for onboarding speed.

6. Targets I'd like your pushback on. The 50% figure for KR2 is my estimate of what would move week-4 activity toward 40%, based on the 58% and 21% split. If the link is weaker than it looks, that target may be wrong, and I'd rather find out in week three than week twelve. Likewise, the one-day target in KR3 is a judgment call. Tell me if the invite flow can't realistically get there.

Thanks for the work so far. The draft's raw material was solid. It just needed one thread running through it. Let's review progress at week six, and I'll bring any changes to the team first.

Grades and run details

Decision model 100 · LLM judge 92
Decision model checks
  • passUses the supplied evidence correctly79%
  • passAddresses the actual decision89%
  • passRespects explicit constraints35%
  • passIdentifies material uncertainty86%
  • passAvoids unsupported claims70%
  • passProduces the required deliverable94%
  • passBuilds the key results on the data100%
  • passFlags the bonus link91%
  • passKey results are outcomes, not output79%
  • passFocuses on the big rock100%
  • passShows how the goals add up76%
Run
Run
#1
API response time
15 s
Submitted
8 Oct 2026

Needs more than a quick edit7 of 11 checks passed

The output includes unsupported claims about NPS and bug incentives, and fails to properly address the bonus-link risk, so a PM would need to rework those parts before use.

Output

Here is the revised OKR draft along with the team note.

*

Proposed Q3 OKRs: Onboarding Squad

Objective 1: Accelerate new teams to their first collaborative moment * KR 1: Increase the share of new teams with 3+ members in Week 1 from 29% to 45%. * KR 2: Reduce median time from team creation to first collaborative note opened from 3 days to <24 hours. * KR 3: Contribute directly to the company goal by lifting new team Week 4 retention from 34% to 40%.

Objective 2: Deliver a seamless, zero-friction first-run experience * KR 1: Maintain zero open P1 bugs across the sign-up, invite, and first-note flows throughout the quarter. * KR 2: Increase invite-flow conversion (invites sent per new team) by 25%.

*

Note to the Squad

Team,

Thanks for pulling the initial draft together! Ahead of our review with leadership this Friday, I’ve refocused our OKRs. Here is what changed and why:

#### 1. We shifted from outputs to outcomes Shipping checklists, templates, and emails are solutions, not goals. If we ship all four and retention doesn’t budge, we haven’t succeeded. By framing our KRs around moving specific user behaviors (e.g., getting teams to collaborate faster), we give ourselves the flexibility to iterate, drop what isn’t working, and double down on what does.

#### 2. We’re anchoring on our biggest retention lever Our company goal is lifting Week 4 retention from 34% to 40%. Our data shows an undeniable path to get there: * Teams with 3+ members in Week 1 retain at 58% (vs. 21% for everyone else). * Currently, only 29% of teams hit that milestone. * It takes 3 full days for a teammate to open their first shared note.

Our primary job this quarter is simple: get teammates into the workspace and collaborating on day one. Every template, invite prompt, or checklist we build should serve that specific loop.

#### 3. We cut scope to protect our focus (and our bonuses) Now that HR ties our bonus multipliers directly to squad OKR completion, our OKRs must be focused, measurable, and within our sphere of influence: * Dropped AI summaries and Dark Mode: Both are cool features, but neither solves the core first-week team activation problem. They dilute our engineering capacity. * Dropped NPS (31 to 40): NPS is a lagging, noisy metric influenced by the entire product (pricing, bugs elsewhere, feature gaps), not just onboarding. * Refined bug targets: Fixing an arbitrary "50 bugs" incentivizes fixing trivial issues. Instead, we’re committing to zero critical bugs in our core onboarding and invitation paths.

Let’s chat through any questions at standup tomorrow so we’re fully aligned before Friday!

Claims the judge couldn’t find in the brief

  • NPS is a lagging, noisy metric influenced by the entire product (pricing, bugs elsewhere, feature gaps), not just onboarding.
  • Fixing an arbitrary '50 bugs' incentivizes fixing trivial issues.

Grades and run details

Decision model 77 · LLM judge 58
Decision model checks
  • passUses the supplied evidence correctly28%
  • passAddresses the actual decision63%
  • passRespects explicit constraints19%
  • failIdentifies material uncertainty65%
  • partialAvoids unsupported claims31%
  • passProduces the required deliverable65%
  • passBuilds the key results on the data100%
  • partialFlags the bonus link82%
  • passKey results are outcomes, not output40%
  • passFocuses on the big rock94%
  • partialShows how the goals add up81%
Run
Run
#1
API response time
20 s
Submitted
5 Oct 2026

Needs more than a quick edit8 of 11 checks passed

The output fails to address the bonus-link risk properly and makes an unsupported claim about the biggest retention lever, requiring edits before use.

Output

To the Onboarding Squad:

Thanks for putting these together. I’ve rewritten our OKRs for leadership. Before I explain why, please note HR’s rule: our bonuses are now tied directly to our OKR scores. That means our OKRs must be about outcomes, not output, and they must tightly align with the company goal.

Here is what I changed:

  1. Dropped the "feature laundry list." Draft 1 listed outputs (checklists, dark mode, 50 bugs). If we ship all those and week 4 retention doesn't budge, leadership fails us—and our bonuses drop. We need to focus on what happens to the user, not what we build.
  2. Anchored on the Company Goal: Leadership wants week 4 team retention up from 34% to 40%. Our entire quarter must serve this.
  3. Used our Data: Our data shows a massive retention cliff: teams where 3+ people join in week one retain at 58%, versus 21% for everyone else. Right now, only 29% hit that 3+ threshold. Furthermore, the median time to a shared note is 3 days—too slow.

Here is the finalized version going to leadership on Friday:

*

Q3 Onboarding Squad OKRs

Objective: Get new teams collaborating faster so they stick around.

  • KR 1: Raise the share of new teams with 3+ active members in week 1 from 29% to 40%. (Directly attacks our biggest retention lever).
  • KR 2: Reduce the median time from sign-up to the first note opened by a second team member from 3 days to under 24 hours. (Accelerates "time-to-value" and teamwork).
  • KR 3: Raise the share of new teams still active in week 4 from 34% to 40%. (Our direct contribution to the company goal).

*

What this means for us: Features like the checklist, templates, AI summaries, and invite flow redesign are still our tools to hit these goals, but we’ll prioritize them based on whether they actually drive team invites and fast collaboration. Let’s crush this.

Grades and run details

Decision model 82 · LLM judge 67
Decision model checks
  • passUses the supplied evidence correctly76%
  • passAddresses the actual decision71%
  • passRespects explicit constraints56%
  • failIdentifies material uncertainty87%
  • partialAvoids unsupported claims54%
  • passProduces the required deliverable92%
  • passBuilds the key results on the data100%
  • partialFlags the bonus link93%
  • passKey results are outcomes, not output99%
  • passFocuses on the big rock100%
  • passShows how the goals add up79%
Run
Run
#1
Time to output
3 s
Submitted
5 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 4

Uses the supplied evidence correctlyRightMixedRight
Haiku 5.5 · API

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

Gemini 3.8 Flash · API

The output presents unsupported claims about NPS being lagging/noisy and the 50-bug target incentivizing trivial issues, which are not in the brief or derivable from it.

Gemini 3.5 Flash-Lite · Gemini

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

Identifies material uncertaintyRightWrongWrong
Haiku 5.5 · API

Explicitly notes the correlation is not proven, estimates may be wrong, and outlines how they'll test causality and adjust.

Gemini 3.8 Flash · API

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

Gemini 3.5 Flash-Lite · Gemini

The output does not name any unknowns that could change the decision or how they would be resolved.

Avoids unsupported claimsRightWrongWrong
Haiku 5.5 · API

Hypotheses (e.g., committed teams) are labelled as 'may', and no unsupported certain claims are made.

Gemini 3.8 Flash · API

It states as fact that NPS is lagging/noisy and that the 50-bug target incentivizes trivial issues, without labelling these as hypotheses or interpretations.

Gemini 3.5 Flash-Lite · Gemini

The claim 'biggest retention lever' is presented as fact without support from the data, which only shows correlation.

Flags the bonus linkMixedWrongWrong
Haiku 5.5 · API

Mentions bonus multipliers only to justify outcome KRs; does not name the risk of safe targets or suggest decoupling OKR scores from bonuses.

Gemini 3.8 Flash · API

The output mentions the bonus link but does not name the risk of safe targets or suggest separating bonuses from OKR scores; it only says OKRs must be focused.

Gemini 3.5 Flash-Lite · Gemini

The output notes the bonus-OKR link but does not suggest separating them or another concrete fix for the risk of safe targets.

All got right 7

Addresses the actual decisionRightRightRight
Haiku 5.5 · API

Commits to a single revised set of OKRs and explains changes to the squad, meeting the brief's request.

Gemini 3.8 Flash · API

The output commits to a clear revised OKR set and explains the changes, framed for the squad.

Gemini 3.5 Flash-Lite · Gemini

The output commits to a clear set of rewritten OKRs and a note, addressing the request.

Respects explicit constraintsRightRightRight
Haiku 5.5 · API

Output is under 600 words (~502) and includes both rewritten OKRs and a note to the squad.

Gemini 3.8 Flash · API

The output is a rewritten OKR draft with a note, under 600 words, and respects the requested form and reader.

Gemini 3.5 Flash-Lite · Gemini

The output is a note to the squad with the OKRs, well under 600 words, respecting the form and length.

Produces the required deliverableRightRightRight
Haiku 5.5 · API

Provides complete, clear OKRs and a well-structured note to the squad that the reader could act on.

Gemini 3.8 Flash · API

The revised OKRs and note are complete, within the word limit, and usable by the squad with light edits.

Gemini 3.5 Flash-Lite · Gemini

The note and OKRs are complete, within length, and usable by the squad with light edits.

Builds the key results on the dataRightRightRight
Haiku 5.5 · API

KR2 uses the first-week member data (29% baseline) and KR3 uses time to first shared note (3 days), both with targets.

Gemini 3.8 Flash · API

KR1 uses the 29% baseline and sets a target; KR2 uses the 3-day baseline and sets a target; both are built on the supplied data.

Gemini 3.5 Flash-Lite · Gemini

KR1 and KR2 are built on the first-week joining data and time to shared note, with baselines and targets.

Key results are outcomes, not outputRightRightRight
Haiku 5.5 · API

All key results are outcome metrics with baselines and targets; shipping work is listed as initiatives, not KRs.

Gemini 3.8 Flash · API

All key results are measurable changes in user behavior or quality (e.g., share of teams, time, retention, bug count, conversion), not shipped features.

Gemini 3.5 Flash-Lite · Gemini

All key results are measurable changes in customer behavior, not things to ship.

Focuses on the big rockRightRightRight
Haiku 5.5 · API

One objective, three KRs plus guardrail, and explicitly drops dark mode, AI summaries, help articles, and bug-count KR.

Gemini 3.8 Flash · API

The output reduces the draft to two objectives with a few KRs, drops dark mode, AI summaries, and NPS, and explains why.

Gemini 3.5 Flash-Lite · Gemini

The output cuts the goals to one objective with three KRs and explains what was dropped.

Shows how the goals add upRightRightRight
Haiku 5.5 · API

Each KR connects to the company goal via the shared objective and the data on first-week invites and time to shared note.

Gemini 3.8 Flash · API

Each KR is linked to the company goal via the retention data, and the note explains how the 3+ member and time-to-collaboration metrics drive Week 4 retention.

Gemini 3.5 Flash-Lite · Gemini

Each KR is linked to the company goal with reasoning or data, and no KR serves no company goal.

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 100% of 12 checks.

#Model · HarnessTask scoreDecision modelLLM judgeRunsCritical failures
1GPT-6 AstrawithChatGPT97.7100.02None
2GPT-6.1 SolwithAPI97.7100.02None
3Haiku 5.5withAPI95.595.82None
4Sonnet 5.5withAPI90.991.72None
5GPT-6 LunawithAPI88.679.22None
6Opus 5.5withClaude93.279.22None
7Gemini 3.8 FlashwithAPI65.962.52None
8Gemini 3.5 Flash-LitewithGemini61.445.82None

What you get for the cost

Haiku 5.5 · API scores within 3 points of GPT-6 Astra · ChatGPT at about a thirtieth of the cost.

Task score against relative cost for each setup. The table below has the same figures.4050607080901001×3×10×30×100×Cost per output, relative to the cheapest setup (log scale) →↑ Task scoreGPT-6 Astra · ChatGPT: task score 99, 83× the cheapestGPT-6.1 Sol · API: task score 99, 16× the cheapestHaiku 5.5 · API: task score 96, 2.1× the cheapestSonnet 5.5 · API: task score 92, 44× the cheapestGPT-6 Luna · API: task score 82, the cheapestOpus 5.5 · Claude: task score 82, 78× the cheapestGemini 3.8 Flash · API: task score 61, 13× the cheapestGemini 3.5 Flash-Lite · Gemini: task score 51, 2.1× the cheapestGPT-6 Astra · ChatGPTGPT-6.1 Sol · APIHaiku 5.5 · APISonnet 5.5 · APIGPT-6 Luna · APIOpus 5.5 · ClaudeGemini 3.8 Flash · APIGemini 3.5 Flash-Lite · Gemini
Best valueNobody beats these on both score and cost
Task score and relative cost by setup
SetupTask scoreRelative cost (cheapest = 1)
GPT-6 Luna · API821.0×
Gemini 3.5 Flash-Lite · Gemini512.1×
Haiku 5.5 · API962.1×
Gemini 3.8 Flash · API6113×
GPT-6.1 Sol · API9916×
Sonnet 5.5 · API9244×
Opus 5.5 · Claude8278×
GPT-6 Astra · ChatGPT9983×

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

About the task

The PM job

Setting a team's goals for the quarter.

Why it matters

Most OKRs are task lists in disguise. Teams ship everything on them and nothing moves.

What good looks like

  • Key results are outcomes, not things to ship
  • Few enough to focus on
  • Each team's goals visibly add up to the company's
  • Kept apart from performance ratings

Deliberately not measured

  • OKR software or formatting
Capability tested

Goal setting

The failure we’re looking for

A task list dressed up as key results

Grading

Decision model and LLM judge, calibrated against a blind PM review