You review the facts and access. Nothing is published without your approval.
The method behind the workshop pre-readAsk your agent to distinguish evidence from proposals and make the participant’s preparation clear.
What should go in a workshop pre-read?
Lead with the question the workshop needs to explore, then provide only the evidence and preparation participants need. Your agent can organize authorized notes into a short HTML pre-read that separates facts, proposals and open choices. Keep the actual discussion and decision record in their established workflows.
What to give your agent
The workshop purpose, intended participants and decision authority if there is one.
Essential background evidence with dates and limits.
Open options, constraints and questions; distinguish them from decisions already made.
The requested preparation, proposed agenda and confirmed logistics if available.
State the question participants will work on
A workshop to explore options is different from a meeting authorized to choose one. Say which it is. Keep a missing decision owner or uncertain mandate visible instead of writing an agenda that assumes approval.
Give everyone the same essential evidence
Select the few facts needed for the discussion and show their limits. Separate supplied observations from interpretations. Keep deeper optional reading below the essentials so preparation is not a demand to reconstruct the whole project.
Ask for useful preparation
Request a concrete contribution such as one question or a constraint from the participant's role. Do not quietly turn preparation into a vote or a commitment. Include supplied reading-time guidance only if it is realistic and verified, not an invented promise.
Make the live session easier to start
Create static HTML with the question, background, options and preparation task. Review access and logistics. Record discussion outputs after the session separately; the pre-read remains context, not evidence that everyone agreed.
Create a workshop pre-read from my authorized purpose, evidence, open options and preparation requirements. Ask for missing essentials. State whether the session explores, recommends or decides. Separate facts, interpretations and proposals; do not invent agreement, votes, effort estimates, logistics or decision authority. Lead with the discussion question and one concrete preparation task. Keep optional background separate. Use static HTML with no scripts or forms and my saved style if available. The page does not collect responses or attendance. Show the draft and unresolved questions; keep decisions in the existing workflow. Do not publish or change access without separate explicit approval.
Check before you shareAccuracy, clarity, and permission
Is the session's actual authority clear?
Is essential reading separate from optional background?
Can participants identify the specific preparation task?
Are open options and missing evidence still visibly open?
When HTML fits
A short shared context page people can read before or at the start of a discussion.
When another format fits better
Use meeting, collaboration or polling tools for live participation. The page does not capture attendance, votes or approval, and is not the post-meeting decision record.
What we started withThe same facts, as an email
Fictional project email
Juniper Support — preparation for choosing a help-center pilot
Team,
For our September 7, 2026 pre-read snapshot, the workshop can recommend a pilot to explore, not authorize publishing or full rollout. No option is approved. The meeting date, location and duration are still unspecified.
Our evidence is six selected support notes mentioning navigation confusion and three mentioning outdated examples. These are selected observations, not representative prevalence or unique-customer counts. Raw private notes are excluded. Option A tests a topic index; option B revises two help examples. Both lack effort estimates and confirmed resources, and we have no measured or predicted percentage improvement.
Please bring one unanswered question and one constraint from your role. That is not a vote or promise of capacity. My proposed agenda is to review evidence, compare the options and record gaps preventing a confident recommendation; no time allocations are set.
Lee will make any later decision in the project workflow after reviewing our recommendation and gaps. No decision date is supplied. This is common context only, not attendance collection, voting or a decision record. Actual outcomes need a separate reviewed record.
Sam, facilitator
Inspect the HTMLOne self-contained file
The example is sanitized and isolated from this site. No scripts, forms, or live data.
<!doctype html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1"><title>Juniper Support · Workshop pre-read</title><style>
*{box-sizing:border-box}html{color-scheme:light}body{margin:0;background:#f5f8fc;color:#182e46;font:17px/1.65 system-ui,sans-serif}main{max-width:1000px;margin:auto;padding:clamp(20px,5vw,64px)}h1,h2,h3,p{margin:0 0 18px}h1{font:500 clamp(32px,5vw,58px)/1.14 Georgia,serif;letter-spacing:-.025em;overflow-wrap:anywhere}h2{font:500 29px/1.3 Georgia,serif;overflow-wrap:anywhere}h3{font-size:19px;line-height:1.4}.label{font:700 12px/1.6 system-ui,sans-serif;letter-spacing:.08em;text-transform:uppercase}.intro{font-size:20px}.lead{background:#23486b;color:white;padding:24px;margin:28px 0}.lead p:last-child{margin:0}.grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(min(100%,230px),1fr));gap:20px;margin:24px 0}.card{background:white;border:1px solid #bbc5c4;padding:24px}.metric{font:500 38px/1.2 Georgia,serif;display:block;margin-bottom:12px}section{margin:36px 0}ul,ol{padding-left:22px}li{margin-bottom:12px}.note{font-size:14px}.warning{border-left:5px solid #956118;padding-left:20px}a{color:inherit;text-underline-offset:4px}a:focus-visible,summary:focus-visible{outline:3px solid #956118;outline-offset:4px}table{width:100%;border-collapse:collapse;table-layout:fixed;font-size:15px}th,td{text-align:left;vertical-align:top;border-bottom:1px solid #bbc5c4;padding:12px 8px;overflow-wrap:anywhere}caption{text-align:left;font-weight:700;padding:12px 0}pre,code{white-space:pre-wrap;overflow-wrap:anywhere}footer{border-top:1px solid #bbc5c4;padding-top:24px;margin-top:40px;font-size:14px}@media(max-width:480px){th,td{padding:10px 4px;font-size:14px}}@media print{body{background:white}.card,.lead{break-inside:avoid}h2,h3{break-after:avoid}}
</style></head><body><main><header><p class="label">Fictional pre-read / September 7, 2026 / Facilitator Sam</p><h1>Which help-center pilot should we explore?</h1><p class="intro">Recommend a next investigation—not permission to publish or roll out a change. Lee decides later in the existing project workflow.</p></header><section class="lead"><h2>Bring one question and one constraint.</h2><p>Choose an unanswered question and a constraint from your role. Preparation is not a vote or a promise of capacity.</p></section><section><h2>The evidence everyone starts with</h2><div class="grid"><article class="card"><h3>Navigation confusion</h3><p>Six selected support notes mention difficulty navigating.</p></article><article class="card"><h3>Outdated examples</h3><p>Three selected support notes mention outdated examples.</p></article></div><p class="note">Selected observations—not representative prevalence or unique customer counts. Private raw notes are not reproduced.</p></section><section><h2>Two open options</h2><ul><li>Test a topic index.</li><li>Revise two help examples.</li></ul><p>Effort estimates and resource availability are missing for both. No measured improvement or percentage impact is supplied. Neither option is approved.</p></section><section><h2>Sam’s proposed discussion order</h2><ol><li>Review the evidence.</li><li>Compare the options.</li><li>Record gaps that prevent a confident recommendation.</li></ol><p class="note">Meeting logistics and time allocations are not supplied.</p></section><section><h2>What happens after discussion</h2><p>Review the recommendation and gaps before Lee makes any later decision. Create a separate record of the actual workshop outcome. This pre-read collects no attendance, answers or decisions.</p></section><footer>Fictional worked example by share/artifacts. Names, dates, figures and records are invented for demonstration. Static snapshot; no live data or automatic updates.</footer></main></body></html>
The original worked scenarioThe source scenario, step by step
Choose what to learn before choosing a pilot
Fictional help-center workshop; no option has been approved.
The original notes
The workshop will recommend which help-center pilot to explore, not authorize publishing. Six selected support notes mention navigation confusion. Three selected notes mention outdated examples; counts are not prevalence. Options: test a topic index or revise two examples. Effort estimates are missing. Ask participants to bring one unanswered question and one constraint from their role. Facilitator Sam proposes reviewing evidence, comparing options and recording gaps. Lee decides later in the project workflow.
Purpose
Recommend a help-center pilot to explore; do not authorize publishing.
Evidence
Six selected navigation notes and three outdated-example notes; neither count measures prevalence.
Choices
Test a topic index or revise two examples. Effort estimates are missing.
Prepare
Bring one unanswered question and one role-specific constraint. Sam facilitates; Lee decides later in the project workflow.
Preparation supports a real discussion without manufacturing a decision in advance.
Questions, adaptations & sourcesGo deeper when you need to
Should the pre-read contain a recommendation?
It can, if that is part of the supplied context. Label it as a recommendation and give alternatives and material limits room to be considered.
What if participants do not read beforehand?
Plan reading time in the session if the facilitator chooses that approach. Do not claim the page verifies reading or attendance.
Can I use it as the final decision record?
Create a separately reviewed record from the actual discussion. A pre-read cannot establish what participants later agreed.