Competitor: Whatagraph
1. Core positioning: "One platform to collect, visualize, and share marketing data" — aimed at agencies managing multiple client accounts. Positions on multi-source integration and speed.
2. Key claims: 100+ integrations; auto-scheduled reports; client-ready white-label; no developer needed; "saves 10+ hours per week."
3. Strengths: Integration breadth is credible and specific. "No developer" claim directly removes the biggest agency objection. White-label framing respects the agency relationship.
4. Gaps: No social proof with specific numbers on homepage. Doesn't address accuracy/data freshness. Pricing page buried — creates friction. No mention of what happens when a data source breaks.
5. Differentiation angle: Own data reliability and audit trail. Lead with "reports your clients trust" rather than "reports that build themselves" — shift the value from time saved to credibility earned.
Campaign: Q2 Agency Awareness — LinkedIn + Email
Dates: Apr 1 – May 31 | Goal: 200 demo requests
Key results:
- Demo requests: 218 (target: 200) ✓
- LinkedIn impressions: 1.2M (target: 800k) ✓
- Email open rate: 34% (target: 28%) ✓
- Cost per demo: $142 (target: $120) ✗
- Webinar registrations: 87 (target: 150) ✗
What drove performance: Thought-leadership posts outperformed case study posts 3:1 on engagement — consistent with Q1 data. Email series with the "reporting gap" angle had the highest CTR (6.1%) across all sends.
Underperformance: Webinar suffered from a 10-day gap between registration and event date. Drop-off rates suggest the window was too long. Cost-per-demo exceeded target because LinkedIn CPMs rose 18% in May.
Next campaign recommendations:
- Cut webinar lead-to-event window to 5–7 days
- Reallocate 20% of LinkedIn budget to email (lower CPL)
- Test one direct-benefit hook in place of thought-leadership for cold audiences
Turn a long post into a 7–9 slide carousel: one idea per slide, swipe-worthy pacing.
プロンプト 入力欄 2 件
Turn this article into a carousel of [7-9] slides for [PLATFORM — Instagram or LinkedIn].
Structure:
- Slide 1: a hook that names the payoff or the mistake (max 12 words)
- Slides 2 to N-1: ONE idea per slide, max 25 words each, no filler transitions
- Last slide: recap in 3 bullets + one CTA:
- After the slides, write the post caption (2 sentences + question)
Keep the numbers and concrete examples from the article; cut the storytelling.
Article:
出力例
Slide 1: Your onboarding email is why they never came back.
Slide 2: 63% of trial users open email #1. Only 11% open email #4. The sequence is the leak.
Slide 3: Email #1 job: one action, done in 90 seconds. Not a feature tour.
Slide 4: Subject lines with the user's goal beat product names 2:1 in our test.
Slide 5: Send #2 after the action happens, not 24 hours later. Behavior beats schedule.
Slide 6: One CTA per email. Two CTAs = half the clicks on both.
Slide 7: Recap — 90-second first win · behavior-triggered sends · one CTA. Steal our full sequence: link in comments.
Caption: We rewrote a 4-email onboarding sequence and doubled activation. The whole teardown is in the carousel. Which email in your sequence gets ghosted the hardest?
ヒントThe "max 25 words per slide" constraint is what makes output usable — without it models write paragraph slides that die in design. Tighten to 18 words for Instagram, loosen to 30 for LinkedIn.
ChatGPTGeminiClaude
Cluster a keyword list into page groups
Sort a raw keyword dump into pages — one intent per page, no cannibalization.
プロンプト 入力欄 1 件
Cluster this keyword list into page groups. One page per distinct search intent — if two keywords can be satisfied by the same page, they belong in the same cluster.
For each cluster give:
- Cluster name + the page type that wins (guide / comparison / tool page / listicle)
- Primary keyword (highest value) and supporting keywords
- One-line content angle
- Flag: any keyword that is its own intent and deserves a separate page
Also list keywords to DISCARD (zero commercial or informational value for us) with a one-word reason.
Our site: . Keywords:
[PASTE KEYWORD LIST, ONE PER LINE — VOLUME OPTIONAL]
出力例
Cluster 1 — "invoice template" (page type: free tool page)
Primary: free invoice template (9,900)
Supporting: invoice template word, invoice template pdf, simple invoice template
Angle: instant download, no email gate — every competitor gates.
Cluster 2 — "how to invoice" (page type: guide)
Primary: how to write an invoice (2,400)
Supporting: what to include in an invoice, invoice requirements freelance
Angle: first-invoice walkthrough for freelancers with a filled example.
Separate-page flag: "invoice vs receipt" — comparison intent, its own page.
Discard: "invoice meaning in hindi" (locale), "invoice 2019 crack" (junk).
ヒントGive the model your site's one-line description — clustering changes completely depending on whether you sell software, run a blog, or offer templates, and models default to generic blog clustering without it.
Stage: Evaluation
Pain points:
- 6-week ramp for new support reps
- Docs change weekly, answers go stale
Budget signal: "We have room if it pays back in a quarter."
Decision makers: [Name] (Head of Support), + IT for security sign-off
Objections / risks: Worried about setup time during peak season
Next action: Send security overview — by Fri Jun 19
[Company] is spending roughly six weeks getting each new support rep to full productivity — time that costs both salary and senior-rep attention. This proposal outlines an answer layer trained on your existing documentation that gets new reps productive in under two weeks and keeps answers accurate as your docs change. Based on your current hiring pace, the expected payback is under one quarter. The investment is [PRICE] per year, including onboarding and your team's data setup. The sections below detail the rollout plan, security review, and success metrics we'd track together in the first 90 days.
Outcome: Lost
Primary reason: We were brought in too late — they'd already shortlisted two vendors before our first call.
Contributing factors:
- Champion liked us but wasn't the budget owner.
- Our security review took 9 days; competitor turned theirs around in 2.
- We never got a meeting with the CFO.
Competitor: Won on faster procurement, not product.
Do differently: Qualify "where are you in the process?" on call one, and pre-stage the security packet.
**TL;DR** — The team approved the Q3 pricing test and pushed the mobile redesign to August. Two action items are unassigned.
**Decisions made**
- Run the pricing A/B test on the Pro plan starting July 1.
- Delay the mobile redesign to August to avoid the holiday code freeze.
**Action items**
| Task | Owner | Due date |
|---|---|---|
| Set up pricing test in billing | Priya | Jun 27 |
| Draft August launch timeline | unassigned | unassigned |
| Tell support about the price change | Marco | Jun 30 |
**Open questions**
- Who signs off on the final August date?
ヒント「所有者または日付を発明しない」ルールはこれを信頼できるようにします。 AI はそうでなければ尤もらしい-しかし間違った名前でギャップを埋めます。 Zoom/Meet トランスクリプトを最良の結果のために直接貼り付けます。
**This week**
- Shipped the onboarding email sequence; open rate at 41% vs. 29% baseline.
- Closed two enterprise pilots — Meridian Health and Solis Finance (combined ARR: $84,000).
- Reduced P1 ticket backlog from 34 to 11 by reallocating two engineers from the feature queue.
- Completed Q3 headcount plan; submitted to HR on Thursday.
**Next week**
- Priya: finalize security review for Meridian (due Thu).
- Tom: start sprint 14 with new backlog priority order.
- Me: present Q3 plan to leadership on Wednesday.
**Blockers**
- Need sign-off on the contractor extension for Tom's team by Monday — delays sprint 14 otherwise.
ヒント貼り付ける前に「配信されたオンボーディングメール」ではなく、ノートに数字を書くこと。 「オープンレート 41% vs. 29% ベースライン」はリーダーシップが覚えるものです。 AI はあなたが与えなかった指標を発明することはできません。
**Overall summary**
Priya had a strong half-year marked by two significant enterprise closes and consistent technical quality. Her communication to stakeholders improved noticeably after Q1; cross-functional friction dropped as a result.
**Strengths**
- Closed Meridian Health and Solis Finance ($84,000 combined ARR) with minimal manager involvement after the first call.
- Delivered the security review framework three days early; Legal called it "the clearest submission we've seen."
**Areas to develop**
- Tends to absorb scope quietly rather than flagging tradeoffs early — missed the sprint 12 deadline was partly caused by this. Agree on a "flag or negotiate" norm before sprint planning each cycle.
**Rating recommendation**
Exceeds expectations.
**Decision: Hire vs. Contract for Design Role**
To: [Director] | Date: Jun 17
**Context**
The onboarding project needs a designer by July 1 to hit the Aug 31 ship date. The role has been open for six weeks; the pipeline has two candidates but no offer-ready finalist.
**Options**
| Option | Pros | Cons | Cost |
|---|---|---|---|
| Extend contractor (Lena) | Available now, knows the product | 20% premium, not a long-term fix | $12,000 for 8 weeks |
| Wait for hire | Right long-term | Delays project 3–6 weeks | $0 now, risk of Q3 miss |
| Freelancer via agency | Fast, low overhead | Ramp time, no product context | $8,000–$14,000 |
**Recommendation**
Extend Lena's contract through August. She's already ramped, and missing the August date costs more than the premium.
**What we need from you**
Approval to extend Lena at the current rate through Aug 31. I need this by Monday to give her enough notice.
ヒントあなたの推奨を明示的に述べます。 「オプション B」は推奨ではありません。 「I は X を推奨します、Y のため」を言うことはあなたを強制します。決定メーカーが迅速に移動するために必要なものは正確です。 すべてをヘッジするメモは行動を取得しないメモです。
**Overall status: Yellow** — on track for the sprint goal but one blocker needs resolution by tomorrow to stay there.
**Progress**
- Diego merged the API rate-limit fix; staging verified clean.
- Priya completed sections 1–2 of the Meridian security questionnaire.
- Tom finished the doc rewrites for onboarding steps 3 and 4.
**Blockers**
| Blocker | Owner | By when |
|---|---|---|
| Legal hasn't reviewed the data agreement; Priya can't complete section 5 | [Manager] to escalate | Jun 18 EOD |
**Watch items**
- QA environment has been flaky — if it goes down again it delays Diego's next PR review.
Overall fit: Possible — strong on the technical side, light on the team leadership the spec asks for.
Matches:
- 6 years in data engineering, all in fintech (spec asks 4+).
- Hands-on with dbt and Snowflake, which the spec names explicitly.
- Led a pipeline migration project end-to-end.
Gaps:
- No evidence of managing other engineers — spec requires leading a team of 3+.
- No mention of vendor negotiation or tooling budget ownership.
- ML pipeline experience listed but no specifics; could be shallow.
Question to ask: "The role manages two junior engineers from day one — have you had direct reports before, and what did that look like?"
Candidate: Maya Chen | Role: Head of Growth | Interviewer: J. Park
Headline: Strong strategic thinker, but gave thin answers when pushed on execution specifics.
Strengths:
- Articulated a full-funnel growth model unprompted — showed systems thinking.
- Comfortable with ambiguity; described building a team from scratch at her last role.
Concerns:
- When asked about a campaign that underperformed, pivoted to what the team learned without owning her own call that was wrong.
- No specific CAC or payback period numbers cited in any example.
Standout moment: Her reframe of retention as a growth lever landed well — clear, original, and grounded.
Recommendation: Hold — ask a second interviewer to pressure-test the execution gap before advancing.
| Criterion | Candidate A (Sara) | Candidate B (Tom) | Candidate C (Lea) |
|---|---|---|---|
| Technical depth | High | Medium | High |
| Leadership exp. | 3 direct reports | None | 6 direct reports |
| Domain fit | Strong (SaaS) | Moderate | Weak (retail only) |
| Communication | Clear, concise | Strong, verbose | Clear |
| Culture signals | Collaborative | Independent | Collaborative |
Case for Sara: Built and scaled a 3-person team in a similar product org. Strong on ambiguity; interview showed she works well without a playbook.
Case for Tom: Highest technical ceiling in the group. Would need to grow into the leadership scope, but the raw thinking is there.
Case for Lea: Most leadership experience by volume, though in a different industry. Strong communicator; the domain gap is the real question.
Key tradeoffs: Do you need someone who can lead today, or someone you can develop? How much does the industry gap matter given your onboarding capacity?
Q1: What two crops did the Dust Bowl destroy most severely in Oklahoma between 1934 and 1936?
Type: Recall
Sample answer: Wheat and cotton were the two crops most severely destroyed during the Dust Bowl years described in the passage.
Q2: Why did many families leave even when they owned their land outright?
Type: Inference
Sample answer: Even landowners left because dust storms made farming impossible for years at a stretch, meaning owning the land didn't protect them from losing their income and food supply.
Q3: The author argues that the Dust Bowl was partly caused by farming practices. Do you think knowing that changes how we should respond to today's droughts? Explain using the text.
Type: Synthesis
Sample answer: Varies — accept any response that connects the passage's evidence about over-plowing to a current policy or personal action.
Why Bees Are Disappearing — and Why It Matters
Bees are dying at a faster rate than ever before. Scientists call this "colony collapse disorder" — when the worker bees in a hive suddenly vanish, leaving the queen bee alone with no one to feed her.
No one knows exactly why it keeps happening. But researchers think three things are working together: pesticides (chemicals sprayed on crops to kill insects), a tiny parasite called the Varroa mite that feeds on bee bodies, and the loss of wildflower fields where bees find food.
This matters to you. About one-third of everything you eat — from apples to almonds to the seeds in your bread — needs bees to grow. Fewer bees means less food, and higher prices at the grocery store.
Assignment: Persuasive essay on school lunch policy (Grade 7, 100 points, 4 criteria)
Claim & Argument (30 pts)
Excellent (30): States a clear, specific position in the opening paragraph and maintains it throughout without contradiction.
Proficient (22): Position is clear but shifts slightly or is restated with inconsistent wording.
Developing (14): A position is implied but never explicitly stated.
Beginning (6): No clear position identifiable.
Evidence (30 pts)
Excellent (30): Cites at least 3 pieces of specific evidence (data, examples, or quotes); each is explained and tied to the claim.
Proficient (22): Cites 2–3 pieces of evidence; explanation of connection to claim is sometimes missing.
Developing (14): Evidence present but vague ("studies show...") or unconnected to the argument.
Beginning (6): No evidence, or evidence contradicts the claim.
[Criteria 3–4 continue in same format...]
学年の先生が通知表のコメントを書くのをお手伝いしています。以下の各生徒について、次の条件を満たしたコメントを書いてください:
- 50~75語
- 具体的(スキル、行動、または例を挙げること。一般的な表現は避ける)
- 全体的にポジティブなトーンで、改善点は前向きに表現する
- 三人称(「彼女は / 彼は / 彼らは」)で書く
- 専門用語と学年コードを使用しない
生徒ノート(1行ずつ、「---」で区切る):
[PASTE STUDENT NOTES IN FORMAT: Name | Strengths | Growth area | Any specific detail]
各生徒について1つのコメントを同じ順序で作成してください。
出力例
Amara J.
Amaraは今学期、読者として大きく成長しました。現在、20分間の読書ブロック中ずっと独立して本を読み、彼女が継続的な努力で身につけた習慣として、彼女の挑戦を助ける本を選んでいます。執筆では、彼女は自分の考えを支持するための具体的な詳細情報を追加する能力を発展させており、継続的な練習により、彼女は読書で示しているのと同じ自信を彼女の下書きに持ってくるでしょう。
---
Felix O.
Felixは数学に本当の好奇心をもたらし、12までのすべての掛け算の事実をマスターしました。これは大きなマイルストーンです。彼は授業の議論に熱心に参加し、しばしば復習中に自分の仕事の誤りを見つけます。彼の次の焦点は、多桁の問題で彼のステップを明確に示すことなので、彼の強力な思考は読者に見えます。
Paste the assignment, get a 4-level rubric with observable criteria — no vague "shows understanding".
プロンプト 入力欄 4 件
Create a grading rubric for this assignment.
Class: . Assignment: .
Requirements:
- 4 performance levels: Exceeds / Meets / Approaching / Beginning, with point values out of
- 4–6 criteria rows drawn from what the assignment actually asks (not generic "effort")
- Every cell describes OBSERVABLE work ("cites two primary sources" not "shows good research skills") so two graders would score the same paper the same way
- Language students in can read themselves
- End with a 2-sentence student-facing summary of what an A looks like
Format as a table.
出力例
Criterion: Thesis & claim (8 pts)
- Exceeds (8): Arguable thesis in first paragraph; every body paragraph advances it.
- Meets (6): Clear thesis; most paragraphs connect to it.
- Approaching (4): Topic stated but claim is a fact, not an argument.
- Beginning (2): No identifiable thesis.
Criterion: Evidence (8 pts)
- Exceeds (8): Two+ primary sources cited and explained; quotes under 2 lines each.
- Meets (6): Two sources cited; explanation present but thin in one spot.
[...]
What an A looks like: You take a position someone could disagree with, and every paragraph gives a piece of evidence for it — then explains the evidence instead of letting quotes speak for themselves.
ヒントThe "two graders score it the same" constraint is what forces observable language — without it every model drifts into "demonstrates strong understanding" cells that cause grade disputes.
本文を貼り付けたうえで、ほしい出力の形を指定してください。箇条書き、1 段落の TL;DR、構造化された表などです。形式と読み手を指定するだけで、「これを要約して」と頼むより格段に使える要約が返ってきます。非常に長い文書であれば、コンテキストウィンドウの大きい Claude のほうが一度に扱える分量は多くなります。
ChatGPT は研究論文を正確に要約できますか?
要旨と主要セクションについてはよく機能します。研究論文向けのプロンプトを使うと、主張・手法・結果・限界の順で返ってきます。ただし AI は細部を言い違えることがあるため、引用する箇所は必ず原論文と照らし合わせて確認してください。