This guide is designed to help you:
- Write effective queries (“prompts”);
- Interpret responses critically;
- Use AI within a compliant and ethical framework.
💬 Have a question? Contact us here.
Ask your Medical AI Expert a question
1. Principles of responsible use
1.1 Confidentiality and data protection
- PulseLife's technology filters out individual-level information entered by mistake that the system could otherwise capture.
- You remain responsible for:
- Never providing any data into PulseLife that could identify an individual (name, date of birth, patient record number, address, etc.)
- Providing only the clinical information necessary to answer the question asked
- The AI Medical Chatbot runs on independently certified, GDPR-aligned infrastructure
1.2 Clinical responsibility
PulseLife's AI Expert provides a view of the current state of medical evidence; it is not a decision-making device. Clinical responsibility remains entirely with the healthcare professional.
2. Understanding the “medical prompt”
2.1 Definition
A prompt is how you phrase your request to the AI system: the more precise your instruction, the more relevant the response.
2.2 Structure of an effective prompt
A good prompt follows this logic: Clinical Context + Question OR Objective + Constraints
Clinical context (where relevant): provide the clinical information needed to answer the question in context (sex, age, medical history, observations, symptoms, etc.)
- “pregnant woman”
- “history of myocardial infarction; moderate renal impairment”
Question OR expected objective: write a precise question OR clarify your objective (relating to the context, if one is given)
- “… what are the possible oral anticoagulation strategies”
- “… does the literature recommend gestational diabetes screening”
Additional instructions (where relevant):
- “… according to the latest RCOG guidance”
- “… according to the latest NICE guidelines”
- “… show the benefits/risks”
Further examples:
Clinical context + Question + Constraints:
- 64-year-old patient, exertional dyspnoea, lower-limb oedema, elevated BNP, echocardiogram showing LVEF of 35%. What is the current treatment strategy according to NICE guidance?
Clinical context + Question:
- 28-year-old man, sleep disturbance, anxiety, occasional dark thoughts. What criteria help distinguish major depression from an anxiety disorder?
Simple question:
- What are the contraindications for methylphenidate (e.g. Ritalin)?
- What investigations are indicated when endometriosis is suspected?
- What are the indications for active surveillance in prostate cancer?
2.3 Where to start
- Start with a subject you know well; build your confidence and test the tool's limits.
- Try a complex question you're confident in.
32-year-old woman presenting with severe dysmenorrhoea and chronic pelvic pain resistant to NSAIDs. Regular cycle, but pain worsens premenstrually; deep dyspareunia. On examination: tenderness in the posterior fornix, tender nodules on the uterosacral ligament. Pelvic ultrasound shows a 3 cm left ovarian endometrioma, suggestive of endometriosis. How can the diagnosis of endometriosis be confirmed?
2.4 Common mistakes
- No question or objective: “64-year-old patient, exertional dyspnoea, lower-limb oedema, elevated BNP, echocardiogram showing LVEF of 35%”
- A question or objective that's too vague: “What treatment for breast cancer?”, “Explain diabetes”
- Too much irrelevant information: “56-year-old patient, diabetic on metformin for 5 years, works as a teacher, persistent cough for 5 days with no fever: what breast cancer screening is recommended?”
- Several questions at once: asking one question at a time gets you a precise answer to each of your queries
3. Best practice by type of need
3.1 Exploring clinical options
Aim: explore the evidence
Sample prompt:
“For an adult patient with BRAF-positive metastatic melanoma, what are the first-line options according to the latest phase III studies?”
Tips:
- Set out the clinical context clearly (age, symptoms, comorbidities, stage, etc.)
- Frame the question clearly in relation to that clinical context
3.2 Literature review or scientific update
Aim: access a clear, well-sourced summary
Sample prompt:
“Summarise the main international recommendations (2023–2025) on the management of type 2 diabetes, citing sources.”
Tips:
- Set out clearly what you're looking for
- Be specific about your instructions (which guidelines, which date range, etc.)
4. Compared examples: “poor” vs “good” prompt
Objective | Poor prompt | Good prompt |
Therapeutic options | “What's the treatment for diabetes?" | “In a 65-year-old patient with poorly controlled type 2 diabetes on metformin, no renal impairment, what are the current recommendations for second-line treatment according to NICE guidance (NG28)?" |
Literature review | "What's new on lung cancer?" | “Cite the main recommendations published since 2023 on metastatic NSCLC with KRAS mutation and summarise their findings in 5 points." |
5. Verification and clinical judgement
5.1 Assessing the reliability of a response
Ask yourself these three questions every time:
- Is the response clearly based on one or more legible reference(s)?
- Are the references appropriate (region, source, date)?
- Is the reasoning consistent with current clinical practice and my own experience?
5.2 Rephrasing to improve quality
If the response is incomplete or too general:
- Add context (“in the case of moderate renal impairment…”)
- Add instructions (“base this only on international guidelines”)
- Rephrase if needed, clarifying the question or objective “as if you were speaking to a colleague”
6. Security, compliance and PulseLife best practice
6.1 Secure environment
PulseLife operates on infrastructure that is:
- Independently certified to HDS, the French national standard for secure health-data hosting;
- Protected under GDPR-aligned safeguards;
6.2 Limitation of liability
Suggestions produced by the AI system do not constitute a prescription or a recommendation. The healthcare professional remains solely responsible for the final decision and its outcome.
6.3 Training and supervision
Users must be trained in the critical reading of AI-generated responses. They must always supervise the tool.
7. Conclusion: AI as a partner in clinical reasoning
Artificial intelligence replaces neither the knowledge, the intuition, nor the responsibility of the healthcare professional.
Used rigorously, it becomes a partner in clinical reasoning: it structures your thinking and speeds up access to knowledge.
Prompting well means caring well: phrase your queries with precision and check the answers with judgement.
❓ Have a question?
Contact us here.
PulseLife – Trusted medical intelligence
Secure. Human. Clinical.