A BETTER WAY TO SHARE THE WORK
Turn experiment results into a decision, not a winner's headline
A higher number is a result. Whether it supports a change is a different question.
New to creating with an agent? The request will guide it through the task. Bring your notes; you don’t need to write HTML.
How do I explain an experiment's results with my AI agent?
Supply the experiment plan, reviewed results, validity checks, and decision criteria. Ask your agent to explain the observed effect alongside uncertainty and guardrails, distinguish planned analysis from exploration, and state the decision the evidence supports. Keep statistical work in the approved analysis workflow and review the HTML brief before sharing.
01 / SEE THE DIFFERENCE
A one-point increase that does not establish a winner
A fictional experiment with a supplied analyst review. Its numbers are illustrative, not statistical advice.
A guide-link experiment recorded 100 completions among 1,000 control users and 110 among 1,000 treatment users. Completion means opening the guide and finishing the sample task in the assigned session. Observed rates are 10% and 11%: +1 percentage point. The supplied analyst interval for the absolute difference is -1.7 to +3.7 percentage points; it includes no improvement. Assignment and logging checks passed according to the supplied review. The load-time guardrail review is pending. No rollout has been approved. Decision owner Mina must review the guardrail and uncertainty before deciding.
- Observed
- 100/1,000 versus 110/1,000 completions: 10% versus 11%, or +1 percentage point.
- Uncertainty
- Supplied analyst interval: -1.7 to +3.7 percentage points. It includes no improvement.
- Validity
- Assignment and logging checks passed according to the supplied review.
- Still missing
- The load-time guardrail review is pending.
- Decision
- Mina must review the guardrail and uncertainty. No rollout has been approved.
Open a complete fictional HTML example, with its source notes →
Create my experiment results brief02 / MAKE IT YOURSELF
Start with the evidence. Shape the page around the reader.
Establish what was tested
State the intervention, comparison, population, and planned metric. Keep the actual run and exclusions visible. A result is hard to interpret when readers cannot tell which users were assigned or what counted as success.
Check whether interpretation is ready
Bring the supplied validity review forward before a winning headline. Missing randomization, data-quality, or exposure checks should remain missing. The agent must not certify an experiment from equal-looking group counts or hide a flagged check.
Pair the observed change with uncertainty
Show the underlying values and the reviewed effect estimate in the same units. Percentage points and relative change are different quantities. Preserve the supplied interval and analyst interpretation; do not turn an interval spanning no improvement into a confident win, or uncertainty into proof of equivalence.
Explain what happens next
Review guardrails and decision criteria alongside the primary metric. Separate planned from exploratory findings and retain tradeoffs. State whether a decision is recorded, proposed, or unresolved. A static brief communicates the evidence; it must not silently launch a variant or extend an experiment.
03 / TRY THIS PROMPT
Copy this into your agent. Add your source material.
Use the conversation where you already did the work, or start one with your notes. Replace the placeholders and supply any missing context; only attach information you are allowed to share with your agent.
Get the ready-to-copy creation request for guided questions, this task, and a draft review before anything is published.
Create an experiment results brief using only authorized experiment plans, reviewed results, validity checks, and decision criteria. Ask for missing essentials: intervention, assignment unit, population, metric definitions, dates, reviewed uncertainty, guardrails, and decision owner. Show group counts and denominators. Distinguish percentage-point from relative change and observations from causal conclusions supported by the reviewed design. Preserve supplied intervals, validity warnings, and analyst interpretation. Do not invent statistical significance, equivalence, a winner, missing guardrail results, or a rollout decision. Label exploratory analyses separately from planned ones. Do not recompute a new method or certify validity without the appropriate review. Create static HTML with no scripts, forms, or live experiment controls. Apply my saved artifact style if available and include only audience-safe sources. Show the draft and unresolved questions. Do not publish or change access without separate explicit approval. Do not launch, extend, or modify the experiment.
04 / BEFORE YOU SEND
A polished page still needs your judgment.
- Can the reader identify the tested intervention, population, and primary metric?
- Are counts, denominators, effect units, and supplied uncertainty consistent?
- Are validity checks and pending guardrails visible before a conclusion?
- Are exploratory findings distinguished from planned analysis?
- Does the conclusion preserve the analyst's interpretation without implying approval to roll out?
When HTML fits
A decision pre-read that makes reviewed experiment evidence understandable to stakeholders who do not need the whole analysis notebook.
When another format fits better
Use approved experiment and statistical tools for assignment, measurement, inference, and rollout. Seek qualified analysis review where needed. The static page is not an experiment platform, calculator, or substitute for checking the study's validity.
FROM DRAFT TO A LINK
Make it clear. Make it yours. Then share it.
Keep creating and revising in the agent you already use. With a compatible connection, share/artifacts publishes the reviewed HTML so you do not have to rebuild it in another editor. Ask your agent to use your saved artifact style for headings, color, and tone; review the result before sending it.
Choose who should be able to open the page and verify the returned link. For corrections to the same deliverable, update the existing artifact without changing its link. Publish a separate artifact when the old edition needs to remain available.
These are static pages, not live apps: no scripts, forms, or automatic data refresh. Source collection and scheduling depend on your agent and its available tools, not on share/artifacts.
Make this with my agentQuestions before you start
Can the page declare the higher conversion rate a winner?
Only if the reviewed analysis and decision criteria support that conclusion. A larger observed value alone does not establish a reliable improvement, and other guardrails may still matter.
Does an interval containing zero prove no difference?
No. Preserve the supplied analyst interpretation and the uncertainty. Do not replace an inconclusive result with a claim that the variants are equivalent.
Can I include interesting subgroup results?
Yes, when authorized and accurately labeled. Say whether the analysis was planned or exploratory and retain the reviewed caveats; do not select a favorable subgroup to override the main result.