01 / The familiar format
You could share this as a wiki page.
A fictional wiki entry with the same underlying facts. Read it here, then compare how the HTML version presents the information.
Team wiki · Fictional example
Birch Reports — what to investigate next
Question and scope
Snapshot September 7, 2026. Owner: Ash. Question: what should we investigate to make reports easier to use? This covers selected sources A and B only, not an exhaustive search or systematic review.
Source A — First-time interpretation
A: in a September 2 session, three of five first-time volunteers asked what a label meant while interpreting a synthetic sample report. This small convenience group is not representative of all users. Timing, completion and satisfaction were not measured in the supplied record.
Source B — Finding saved work
B: five of eight selected support notes from September 1–5 mention difficulty finding a saved report. These concern existing-work retrieval, not first-time interpretation. Selection was not random, and note counts are not unique-user counts.
Interpretation
Overlap in participants or events is unknown. Tasks, methods and audiences differ; combining counts would not establish a population rate. Ash proposes separate investigation of newcomer terminology and existing-user retrieval. This is a proposed direction, not a proven redesign or universal main problem.
Decision and privacy
No redesign, staffing or research date is approved. The product team decides in its research planning process. No participant identities, verbatim quotes or private links are supplied.
02 / The HTML version
Same information. See what needs your attention.
This is the complete static HTML example, not a screenshot. Scroll inside the preview to read it all. It has no live data, scripts, forms, or external resources.
Inspect the complete HTML source
This is the authored source for the example. The preview above passes through our HTML sanitizer before rendering in an isolated frame.
<!doctype html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1"><title>Birch Reports · Research synthesis</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 two-source synthesis / September 7, 2026 / Owner Ash</p><h1>Two moments of confusion. Two questions to test.</h1><p class="intro">What should Birch Reports investigate next? The supplied evidence points to different tasks—not one proven universal problem.</p></header><section class="lead"><h2>Proposed direction, not an approved redesign</h2><p>Investigate terminology with newcomers and report retrieval with existing users separately. No staffing or research date is approved.</p></section><section><h2>Keep each finding beside its context</h2><div class="grid"><article class="card"><p class="label">Source A / September 2</p><h3>Interpreting a first report</h3><p>Three of five first-time volunteers asked what a report label meant while using a synthetic sample.</p><p class="note">Small convenience group; not representative. No timing, completion-rate or satisfaction measure supplied.</p></article><article class="card"><p class="label">Source B / September 1–5</p><h3>Finding saved work</h3><p>Five of eight selected support notes from existing users mention finding a saved report.</p><p class="note">Selected notes, not random sampling or unique-user counts. Different task from Source A.</p></article></div></section><section class="warning"><h2>Do not combine these into a rate.</h2><p>Methods, audiences and tasks differ. Participant or event overlap is unknown. Adding the counts would not establish how common either problem is across the customer population.</p></section><section><h2>What this synthesis leaves open</h2><p>Whether clearer terminology or changed retrieval would help needs further investigation. The product team must decide the next research step in its existing planning process.</p><p class="note">Sources A and B are the entire supplied set. This is not a systematic review. No participant identities or private source links are included.</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>
Make the next one about your work.
- Take the task to your agent. We provide a request with the goal, example, and checks. Copy it into the conversation where your context lives.
- Supply only what is missing. Use material your agent is authorized to access. Don’t substitute the example’s invented facts for your own.
- Review a draft before sharing. Check facts, readability, and sensitive information. Publishing and choosing who can open it are separate, explicit decisions.
Make this with my agentNo publishing connection is needed for an initial local draft. Your agent needs to be able to create an HTML file; preview and connection support vary by client.