You are helping me build a custom AI Intelligence Dashboard. This dashboard will be my personal market intelligence system for tracking developments in my industry.
Before building anything, interview me one question at a time. Wait for my answer before moving to the next.
- What industry or domain do you want to track? (Examples: AI/ML, fintech, healthcare, climate tech, cybersecurity, SaaS, consumer tech, biotech.)
- What sources should the dashboard scan? Name specific publications, blogs, newsletters, GitHub repos, lab changelogs, YouTube channels, or any other sources you trust. List as many as you want.
- What qualifies as a development worth including? What criteria should a story meet to make the dashboard? (Examples: must name a specific product or mechanism, must trace to a primary source, must be from the past 7 days, must affect practitioners not just researchers.)
- What should be explicitly excluded? What types of stories waste your time? (Examples: crypto, repackaged press releases, rumor-based reporting, saturated stories with no new angle, region-specific stories outside your market.)
- What signal categories do you want? (Examples: Breakthrough, Deployment, Funding, Policy, Acquisition, Open Source, Regulation. Pick 4-6 that match your industry.)
- Who is this dashboard for — just you, or does a team read it? What's their expertise level? What do they need to act on versus just be aware of?
- How often do you want this refreshed? (Daily, every 3 days, weekly.) And what time of day do you want it ready?
Once I have answered all seven, generate a complete Perplexity Computer prompt using this structure:
CONTEXT:
I run [my role/company description from answer 1].
Scan this [time period]'s developments across [sources from answer 2].
Read full pages, not snippets. Cross-reference findings and flag where sources disagree.
Before executing, propose a task plan with estimated credit cost per phase.
Do not begin work until I confirm the plan.
OBJECTIVE:
Build an interactive intelligence dashboard, deployed as a live rendered app, with:
- Card grid: headline, 2-sentence summary, signal tag [categories from answer 5], source URL
- Click any card to expand: full briefing, relevance to [user's domain], practitioner take, media coverage grid, and a dated timeline of events leading to this development
- Top strip: Signal vs. Noise — 5 most consequential developments with a one-line verdict each
- Bottom panel: 3 open questions the research raises
STYLE:
Dark mode. High information density.
Single self-contained HTML file, CSS and JS inline.
TONE:
Concrete and evidence-based. No hype.
Flag weak evidence with ⚠️.
Disqualify: [exclusions from answer 4].
AUDIENCE:
[Audience description from answer 6].
A development qualifies only if:
[Qualification criteria from answer 3]
- Traces to a named source — no unattributed claims