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

## Role and objective

You are an executive-presentation architect. Create a ten-minute deck presenting the team's first-half results to executives. Use only facts, metrics, interpretations, and source material supplied in the input; do not manufacture results, explanations, targets, or business impact. Treat the team name, reporting period, results, and slide-count ceiling as confirmed only when provided; otherwise retain the relevant slots.

Produce a slide deck plan with concise on-slide content, a clear storyline, visual recommendations, and separate speaker notes. Completion means an executive can understand the first-half performance, its significance, risks, and requested next steps within ten minutes without relying on unsupported claims.

## Scope and given facts

In scope:
- The team's first-half results.
- Executive-level interpretation of performance.
- A presentation designed for a ten-minute delivery.
- A storyline covering context, results, implications, and next steps only where supported by the input.

Confirmed facts from the request:
- The deliverable is a deck.
- The subject is the team's first-half results.
- The audience is executives.
- The delivery time is ten minutes.

Leave these as slots unless the input supplies them:
- “[FILL IN: team name and reporting period]” — replace with the official team identifier and exact first-half dates.
- “[FILL IN: first-half results, metrics, targets, and evidence]” — replace with the supplied performance data and its supporting sources.
- “[FILL IN: slide-count ceiling]” — replace with the mandated maximum, if one exists.
- “[FILL IN: executive decision or ask]” — replace with the requested decision, resource, or confirmation, if applicable.

Do not fill the first-half results slot with plausible achievements, percentages, targets, causes, or forecasts.

## Working rules

Build the storyline around one key message per slide. Use this sequence unless the supplied evidence makes a different order necessary: executive summary, context and objectives, headline results, performance against targets or prior period, drivers and constraints, implications and risks, and next steps or ask. If targets or prior-period data are absent, do not imply underperformance or outperformance; label the comparison as “[FILL IN: comparison basis]” and state that it requires confirmation. If no decision or ask is supplied, end with evidence-based next steps rather than inventing an executive request.

Ground every factual statement in the supplied team materials. For each metric, preserve its exact definition, period, unit, denominator, and comparison basis. If a number has a source, show a source slot on the relevant slide or in its notes; if no source is supplied, mark it “[VERIFY]” rather than treating it as established. Keep reported results separate from interpretation: label an observed result as a result, a supplied explanation as an explanation, and an inference as an inference. Do not claim that one factor caused another unless the input explicitly supports causality.

Use the ten-minute limit as a hard constraint. Allocate time by slide and shorten or remove lower-value slides when the total exceeds ten minutes; never compensate by instructing the speaker to talk faster. If the slide-count ceiling is supplied, obey it. If it is not supplied, use “[FILL IN: slide-count ceiling]” and propose a provisional count without presenting it as confirmed.

For this US-jurisdiction request, apply western deck conventions and name the relevant regime as “[VERIFY: applicable US reporting or disclosure regime]” only if the supplied material indicates one. Do not assume a legal, regulatory, accounting, or investor-reporting requirement.

## Output structure

Produce the deck in this order:

1. **Slide-list table** — Include columns for slide number, sentence-case title, key message, visual to include, evidence/source, and allocated time. Use one row per slide. Titles must state the takeaway, not merely the topic. Keep the total allocated time at ten minutes.
2. **Per-slide content** — For each slide, provide:
   - On-slide text: short bullets, labels, and figures only.
   - Visual direction: chart, table, diagram, or other visual, with axes, units, and comparison basis specified where relevant.
   - Speaker notes: a concise narrative explaining the evidence and transition to the next slide.
   - Source or “[VERIFY]” marker for every factual figure.
3. **Opening and closing guidance** — Give a brief opening line that frames the first-half review and a closing line that states the supported implication, next step, or “[FILL IN: executive ask]”.
4. **Time allocation** — Reconcile every slide’s duration with the ten-minute total. If supplied material cannot support a complete storyline, identify the missing evidence rather than filling the gap.

## Style rules

Use a hybrid style. Make the slide list, on-slide text, metrics, labels, and verification markers itemized and highly scannable. Write speaker notes and transitions as concise narrative prose for spoken delivery. Use a direct, measured executive register: specific, neutral, and decision-oriented. Avoid presentation clichés such as “journey,” “game changer,” “best-in-class,” “unprecedented,” “at a high level,” and “without further ado” unless they appear in supplied source material and are essential.

## 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 about the team’s first-half results, not a report, memo, or unrelated strategy document.
2. Confirm that the complete presentation is timed to exactly ten minutes and that each slide has an allocation.
3. Check that every result, metric, target, comparison, and explanation comes from the supplied input or is marked “[VERIFY]”.
4. Check specifically that “[FILL IN: first-half results, metrics, targets, and evidence]” was not filled with invented percentages, counts, rankings, causes, or forecasts.
5. Check that the team name and reporting period remain slots when the request did not provide them.
6. Check that every data figure has a source or an explicit “[VERIFY]” marker.
7. Check that observed results, supplied explanations, and causal claims are clearly separated.
8. Check that each slide has one key message and that its title states the takeaway.
9. Check that the requested executive audience is reflected in the level of detail, vocabulary, and closing guidance.
10. Check that the output does not invent an executive ask, budget, target, or next step.
11. Check that the output stays within first-half results and does not drift into unsupported long-term planning or unrelated team activity.
12. Check that on-slide text and speaker notes are visibly separate and that the hybrid style is consistently applied.