Verified against Perplexity Pro · 2026-07-18
Turn a vague research question into a Deep Research report with a real evidence trail
A brief for Perplexity Deep Research mode that forces a stated research plan, a recency window, and an evidence table instead of a fluent-sounding single-pass answer.
The prompt
Ready to copy — highlighted parts are example details you can swap.
Run this as a Deep Research task, not a quick search. Before pulling sources, state the research plan you intend to follow — the sub-questions you will answer and the search angle for each — in two or three lines, then proceed. RESEARCH QUESTION Is on-device small-model inference actually cheaper than cloud API calls at production scale for a mid-size SaaS company in 2026? WHAT THIS IS FOR Deciding whether to migrate our support-ticket classifier off a hosted API onto local inference this quarter. SOURCE REQUIREMENTS - Prioritize: independent benchmark writeups and cost breakdowns, not vendor marketing pages - Recency window: only weight sources inside last 9 months as current. Older sources may be cited for background but must be labeled as background, not current evidence. - Do not treat one outlet's framing as the finding if other outlets or the underlying primary data disagree — surface the disagreement instead of picking a side silently. FINAL REPORT FORMAT 1. Answer at a glance — three to five sentences, no hedge that isn't backed by an actual disagreement in the sources. 2. Evidence table — one row per key finding: Finding | Source | Date | Confidence (High/Medium/Low). 3. Where the evidence is thin or contested — name the specific gap, not a generic "more research is needed." 4. Full source list in the order cited. If the question could reasonably be scoped two different ways, note the alternate scoping as an aside rather than silently picking one and hiding the ambiguity.
Customize the highlighted detailsoptional — the prompt above already works
Why this works
Perplexity Deep Research runs an iterative loop of dozens of searches and page reads, forming and revising a plan mid-run before it writes the final synthesis — asking it to state that plan up front, in the sub-questions and search angles it will chase, anchors what the planning step actually searches for instead of letting it default to whatever the first page of results converts into steps. Deep Research trades latency for exhaustiveness by design, so naming a decision context and a recency window is a budget instruction, not decoration: it tells the tool what to spend that extra time on rather than spreading equally thin coverage across an unbounded question. Forcing a Finding/Source/Date/Confidence table instead of prose also surfaces disagreement structurally — two rows with the same Finding column and different Confidence values are visibly in tension, where the same disagreement buried in a paragraph reads as one smooth, and misleadingly certain, narrative.
What you get back
Plan: (1) compare per-token cost of hosted API vs local GPU amortized cost at our volume, (2) check independent benchmarks for accuracy parity on classification tasks, (3) check operational overhead reports from teams who migrated. Answer at a glance: At sub-1M requests/month, hosted APIs remain cheaper once you include GPU idle time and maintenance; the crossover point independent benchmarks report is closer to 5-10M requests/month for a classification-sized model. Evidence table (excerpt): "Crossover near 5-8M req/mo for 7B-class models" | independent infra benchmark, June 2026 | High confidence.
Verified against
Perplexity Pro Deep Research (Sonar-based) · 2026-07-18
Changelog
- 2026-07-18 — Initial publish, verified against Perplexity Pro Deep Research mode.
Need this built into your business?
If a prompt isn't enough — what Scult builds, built and maintained for you — that's Scult's day job.
EXPLORE WHAT SCULT BUILDS
