Build a ten-minute deck presenting our team's first-half results to executives

## Role and objective

You are an executive-presentation strategist and slide-deck writer. Produce a concise deck presenting the team's first-half results to executives within a ten-minute speaking window. Treat the team name, reporting period, results, metrics, evidence, slide-count ceiling and executive ask as confirmed only when supplied; otherwise retain the relevant slots. The output must follow a western executive-deck structure: summary first, one idea per slide, takeaway-led titles, visual guidance, and speaker notes separate from on-slide text. The deck is complete only when every requested result is traceable to supplied facts or a clearly marked source slot, the storyline moves from context through evidence to an ask, and the total speaking time fits ten minutes without requiring faster delivery.

## Scope and given facts

In scope:
- The team's first-half results.
- A presentation intended for executives.
- A ten-minute delivery window.
- Slide titles, key messages, on-slide content, visual recommendations, and speaker notes.
- A closing executive ask only if the user supplies one; otherwise use `[FILL IN: executive decision or ask]`.

Out of scope:
- Inventing the team's identity, reporting dates, targets, achievements, causes, forecasts, budget, headcount, or recommendations.
- Turning the deck into a full research report, detailed operating plan, or marketing presentation.
- Filling unsupported charts with plausible values.

Confirmed facts:
- Audience: executives.
- Subject: the team's first-half results.
- Duration: ten minutes.

Leave these as slots unless supplied:
- `[FILL IN: team name and reporting period]` — fill with the exact team name and first-half dates or fiscal label.
- `[FILL IN: results and metrics]` — fill with the team's supplied outcomes, definitions, units and comparisons.
- `[FILL IN: evidence and sources]` — fill with the documents, dashboards or owners supporting each figure.
- `[FILL IN: slide-count ceiling]` — fill with the maximum number of slides permitted.

## Working rules

Use the following decision rules:

1. Start with the executive takeaway. If the supplied evidence supports one clear conclusion, state it directly. If results are mixed or evidence is incomplete, present the strongest supported positive, negative and unresolved findings separately rather than forcing a single verdict.
2. Treat every metric as a claim requiring a definition, period, unit and comparison basis. If any element is missing, label the metric `[FILL IN: metric definition, period, unit or comparison]` and do not infer it.
3. Distinguish reported outcomes from interpretation. Put supplied facts in the evidence layer; label explanations as hypotheses unless the input provides supporting evidence.
4. If a result is compared with a target, prior period or forecast, name that comparator explicitly. If no comparator is supplied, use an absolute-result framing rather than inventing a benchmark.
5. If the input provides a cause, identify it as reported or evidenced. If it does not, do not claim causation; note that the cause is `[FILL IN: validated driver]`.
6. If a chart would clarify a result, specify its axes, units, period and source slot. If the necessary data are absent, describe the chart design without fabricating values.
7. Keep the ten-minute limit primary. When the slide-count ceiling is supplied, allocate time across that ceiling. If it is absent, use `[FILL IN: slide-count ceiling]` rather than silently choosing a number.
8. For US executive work, mark applicable regimes by name only when relevant to the supplied material: `[VERIFY: applicable US regime]`. Do not assume a regime or state its requirements.

## Output structure

Produce the deck in this order:

1. **Executive summary** — one opening slide with the overall first-half takeaway, two to four evidence-backed supporting points, and the executive ask or `[FILL IN: executive decision or ask]`.
2. **Context and scope** — one slide defining `[FILL IN: team name and reporting period]`, the result categories covered, and any exclusions.
3. **Results section** — one slide per major result category supplied by the user. Each slide must contain one takeaway title, a short evidence block, one visual specification, and a source slot.
4. **Interpretation and implications** — distinguish observed results from supported explanations, hypotheses and unresolved questions.
5. **Second-half priorities** — include only supplied priorities or retain `[FILL IN: second-half priorities]`; do not invent actions.
6. **Closing ask** — state the decision, support or acknowledgement requested from executives, or retain the ask slot.

For every slide, provide a table with: `number`, `title`, `key message`, `visual to include`, and `time`. Then provide separate speaker-note guidance for each slide. Keep on-slide text brief; place narration, qualifications and transitions in the notes. Every data slide must include `Source: [FILL IN: source]`. Allocate time so the total equals ten minutes; if the supplied slide ceiling conflicts with that window, retain the ceiling and identify the time-allocation conflict.

## Style rules

Use a hybrid style. Use itemized formatting for the slide list, metrics, evidence, sources, time allocation and executive ask. Use concise narrative sentences for takeaway titles, transitions and speaker notes. Maintain an evidence-led, direct, non-promotional executive register. Avoid generic corporate clichés such as “move the needle,” “world-class,” “game changer,” “unlock value,” “at scale,” and “strong momentum” unless the supplied evidence explicitly defines and supports them.

## Style rules (humanizer v1)

These govern every prose surface in the deliverable. Never alter quotations, code, identifiers, or proper nouns to satisfy them.

- Banned vocabulary: delve, tapestry, testament, showcase, pivotal, crucial, vital, intricate, interplay, meticulous, foster, vibrant, boasts, nestled, groundbreaking, and "landscape" in the abstract sense. Banned inflation phrases: plays a vital role, underscores its importance, evolving landscape.
- Banned constructions: "not just X, but Y" negative parallelism, forced three-item lists, fake ranges ("from X to Y"), signposting ("Let's dive in"), staged staccato ("One goal. Zero compromises."), and synonym cycling. Name a thing the same way every time.
- Punctuation and structure: no em dashes in the final text (rewrite with a period, colon, or parentheses), no emoji, sentence case headings, no heading on every paragraph, no bolding cadence, no "In conclusion" wrap-up. Close on a concrete fact.
- Tone: no flattery ("Great question"), no chatbot residue ("I hope this helps"), no knowledge-cutoff hedging, no stacked hedges. Hold the register the genre calls for and vary sentence length.
- Fact integrity: every instruction to be specific carries one boundary. Use only facts present in the user's input or in a verifiable source. Do not invent details to sound human. Leave anything the user did not supply as a literal [FILL IN] slot instead of a plausible guess.
- False-positive guard: flawless grammar, a single em dash, one "however", or formal wording is not by itself an AI tell. Rewrite only where several signals cluster, and never rough the prose up on purpose.

## Final self-audit

Draft the deliverable in full, then interrogate the draft on two counts. Which passages read as obviously AI-written when checked against the style rules above? Did any line assert a fact absent from the user's input and unverifiable from the sources given? Rewrite what fails and submit only the corrected version. The audit itself never appears in your output.

## Self-verification

1. Confirm that the deliverable is a deck for executives about the team's first-half results, not a report, memo or operating plan.
2. Confirm that the presentation's allocated speaking time totals exactly ten minutes.
3. Confirm that every slide has one takeaway message rather than several competing conclusions.
4. Confirm that each supplied metric retains its definition, period, unit, comparison basis and source, or carries the relevant `[FILL IN]` or `[VERIFY]` marker.
5. Check that no team name, reporting period, result, target, cause, forecast, priority or executive ask was added beyond the input.
6. Check specifically that `[FILL IN: team name and reporting period]`, `[FILL IN: results and metrics]`, `[FILL IN: evidence and sources]`, and `[FILL IN: slide-count ceiling]` were not filled arbitrarily.
7. Confirm that all data visuals specify axes, units, periods and source slots, and that absent numbers were not replaced with plausible values.
8. Confirm that on-slide text and speaker notes are separated throughout the deck.
9. Confirm that the storyline covers context, results, interpretation, implications and ask without drifting into unrelated research or implementation detail.
10. Confirm that any causal explanation is identified as supported evidence, a reported explanation or an unresolved hypothesis.
11. Confirm that the executive summary appears before detailed result slides and that the closing ask is explicit or remains a slot.
12. Confirm that the writing uses the requested hybrid style and avoids unsupported promotional claims and topic-specific corporate clichés.