308 - Reproducible prompts

• 301Creating reports and dashboardsHow to ask the agent for shareable work product instead of chat that scrolls away. The habits that decide whether your dashboard survives next week.
• 302Exporting dataWhen you need a spreadsheet a teammate can sort, or a data file for another system, instead of a view.
• 303Sharing your workTwo ways to share: a user share to a named teammate, or a public link anyone with the URL can open. Three controls on either: expiration, notice text, revocation.
• 304Creating collectionsBundle a dashboard, a summary, and the underlying data into one navigable briefing. Build it during the session via the agent, or by hand on the portal's Collections page.
• 305Editing what you already haveUpdate an asset in place so shared links keep working and history stays on one record. Metadata edits do not bump the version; content edits do; revert is append-only.
• 306How an asset was builtThe audit trail Plexara records at the MCP boundary: which tool calls the agent invoked, with what parameters, in the producing session. Captured at save time, readable by you or the agent.
• 308Reproducible promptsSave the starting instruction as a first-class prompt with named arguments via Manage Prompts (manage_prompt). Re-run it later with different values. Personal, persona, or global scope. What re-running does and does not guarantee.

• Stop re-typing the same starting instruction

  If you run a monthly close, a weekly pipeline review, or a quarterly board briefing, you have already typed roughly the same five-paragraph prompt into the agent a dozen times. The drift between this month and last month is real: a phrase you tightened the second time, a constraint you forgot the third time. Saving the prompt once means everyone (including future you) starts from the version that already works.

• Change the variables, not the words

  Most repeated work changes in small, named ways: a different quarter, a different region, a different customer segment. A saved prompt declares those as arguments. The agent reads the template, substitutes the values you pass, and runs the prompt with this quarter's numbers without you having to rewrite the surrounding language.

• Make the working version the team version

  When you have a prompt that produces good board-grade output, the second-most useful thing you can do (after running it) is hand it to your team in a form they can run themselves. A prompt scoped to your persona or shared globally shows up in everyone's prompt list with the same arguments and description you wrote.

name

Machine-friendly identifier. Lowercase letters, digits, hyphens, and underscores; up to 128 characters. The agent looks the prompt up by this name. Pick something stable; you'll be typing it.

display_name

Human-readable title for the same prompt. Shown in the portal's prompt list. Free-form; can include spaces and punctuation.

description

One-line summary of what the prompt does. Shows up in listings; the agent uses it to decide whether the prompt is the right one to run for a given request.

content

The template itself. Plain text with named placeholders in {curly_braces} or {{double_curly_braces}}. At run time, Plexara substitutes the argument values you pass.

arguments

The named placeholders, each with a name, a description, and a required flag. The agent uses the descriptions to know what to ask you for if a value is missing.

scope

Who can see and run the prompt: personal (you only), persona (users assigned to a matching role), or global (everyone in your Plexara). Personal is the default; the others require an admin.

owner_email

The authenticated user who created the prompt. Set by Plexara from your session, not from input. This is what gates the 'only edit your own' rule on personal prompts.

• personal

  Who sees it

  Only you (the prompt owner).

  Who can create or move into this scope

  Anyone. This is the default when you create a prompt without specifying a scope.

  Good for

  Drafts, experiments, prompts you are still tightening. The portal's create form forces personal scope; the agent path also defaults to it.

• persona

  Who sees it

  Users assigned to one of the personas listed on the prompt (the platform's role / persona system).

  Who can create or move into this scope

  Admins only. Non-admins cannot create or move a prompt into persona scope.

  Good for

  Role-based playbooks. A prompt for the finance team, a prompt for the data engineers, a prompt for the marketing analysts. Visible to the role, invisible to everyone else.

• global

  Who sees it

  Every user of this Plexara.

  Who can create or move into this scope

  Admins only.

  Good for

  Team-standard workflows that any user should be able to run: the company-wide weekly KPI prompt, the onboarding tour, the standard incident-report template.

• Agent path (Manage Prompts / manage_prompt)

  What it does

  During a session, ask the agent to save the prompt you just wrote, or to list the prompts you already have, or to update one. The tool supports create, update, delete, list, and get.

  Who can use it

  Anyone, for their own personal prompts. Admins can also set or change scope to persona or global. Non-admins cannot manage anyone else's prompts.

  What to watch

  The agent will follow your instructions about wording verbatim. If you want the template improved before saving, ask for the improvement first, then save. Once saved, the content is what the agent reads next time.

• Portal path (the Prompts page)

  What it does

  The portal has a Prompts surface that lists personal prompts and available prompts (global, persona-matching, system) and lets you create, update, and delete personal prompts. The portal's create form pins scope to personal.

  Who can use it

  Anyone with a portal account, for their own personal prompts. Admins use a separate admin surface to manage persona and global prompts.

  What to watch

  The portal is the right place to copy-edit a prompt carefully (long content, multiple arguments). The agent path is faster when you are at the keyboard already.

Before you write a single prompt of your own, Plexara registers a handful of workflow prompts automatically, conditional on which toolkits your instance has connected. They show up in your available list with category workflow. Each takes a single argument named topic (or dataset for lineage).

• explore-available-dataDiscover what data is available about a topicData catalog access
• create-interactive-dashboardDiscover data, build a visualization, and save it as a shareable assetData catalog, SQL warehouse, and the Plexara portal
• create-a-reportAnalyze data and produce a structured Markdown reportData catalog and SQL warehouse
• trace-data-lineageTrace where data comes from and what depends on itData catalog access

{
  "id": "prompt_8f3a91b2",
  "name": "quarterly-regional-sales-review",
  "display_name": "Quarterly Regional Sales Review",
  "description": "Build the standard quarterly sales review dashboard for a given quarter and year, with a year-over-year comparison cut by region.",
  "content": "Generate a sales review for Q{quarter} {year}.\n\n1. Pull regional revenue for the quarter from the warehouse\n2. Compare against Q{quarter} of the prior year\n3. Build an interactive dashboard with the year-over-year cut\n4. Save it as Q{quarter} {year} sales review - by region",
  "arguments": [
    { "name": "quarter", "description": "Quarter number, 1 through 4", "required": true },
    { "name": "year",    "description": "Four-digit year (e.g. 2026)",   "required": true }
  ],
  "category": "analysis",
  "scope": "persona",
  "personas": ["sales-analyst"],
  "owner_email": "[email protected]",
  "source": "operator",
  "enabled": true,
  "created_at": "2026-04-02T15:18:00Z",
  "updated_at": "2026-04-12T09:33:00Z"
}

• Write the prompt as a template before you save it. A prompt that has the next quarter hard-coded is going to mislead someone in three months. Replace every value that will change (dates, regions, customer IDs, periods) with a {named_argument} before you call save.

• Name the prompt for the action plus the variables. "quarterly-regional-sales-review" reads better in a list than "sales-prompt-final-v2." If the prompt takes a date or a region, the name should hint at that without including the values.

• Move from personal to persona to global deliberately, not by default. A prompt that only you run belongs in personal scope. A prompt your team runs belongs to a persona an admin sets up. A prompt the whole company runs is global and needs more wording care, because the audience is broader than the writer's head.