At Trip, we’ve spent years helping clinicians around the world get trusted, evidence-based answers to their clinical questions. Now, with the success of AskTrip – our automated clinical Q&A system – we’re opening the door to a new way of delivering answers: a fully white-labelled solution that lives on your own site or intranet.
We know that many healthcare organisations want to provide instant, intelligent support to their clinicians – but don’t have the technical resources, capacity, or time to build such a system from scratch. That’s exactly where we come in.
Your Platform, Your Content, Our Technology We offer a fully tailored version of AskTrip that’s designed to seamlessly blend into your digital ecosystem. It will look and feel like your own product, aligned with your branding and tone of voice. Most importantly, you have control over the content that gets surfaced and prioritised.
By embedding your content alongside globally respected, evidence-based answers from Trip, you’re creating a hybrid knowledge hub that connects external best practice with local context and policies. That means faster answers, more confident decision-making, and improved alignment with your standards of care.
Why This Matters Healthcare professionals often struggle to find trustworthy answers quickly, especially ones that are locally relevant. With a white-labelled AskTrip solution, you’re not just offering access to high-quality evidence. You’re offering answers that carry your authority, shaped by your clinical leadership and tailored to your services.
This isn’t just a search box. It’s a clinical decision support tool, built into your environment, promoting consistency, safety, and speed.
The Benefits at a Glance
Integrated: Embedded directly into your website or intranet.
Branded: Customised with your organisation’s identity.
Contextual: Highlights your internal guidance and policies.
Intelligent: Uses AI to provide accurate, relevant clinical answers.
Efficient: Supports clinicians at the point of need—without searching through multiple systems.
A Growing Opportunity We’re already in conversations with forward-thinking organisations who see the value in offering a smart, branded Q&A service to their staff. Whether you’re a hospital trust, a health system, a professional society, or an educational body, AskTrip offers a scalable, cost-effective way to put smart answers into clinicians’ hands, without the need to develop your own tech from scratch.
AskTrip launched less than four days ago and has already handled 147 questions – well beyond our expectations. And we haven’t even promoted the service yet! That starts next week, when we’ll be emailing tens of thousands of registered Trip users.
Most common clinical areas:
Top clinical topics:
Cancer (general)
Pain management
Hypertension
Diabetes / GLP-1s
Hypothyroidism
We grouped questions by type:
Evidence level (see our explanation of how we assess this here):
High: 61%
Moderate: 20%
Good: 11%
Limited: 8%
We analysed the figures with the help of ChatGPT that supplied this nice little conclusion:
“Healthcare is full of grey areas. Clinicians are trying to make them black and white, or at least lighter grey. The questions they ask reveal more than gaps in knowledge—they show what really matters at the front line of care.
At Trip, we’re turning those questions into trustworthy answers—evidence-backed, fast, and context-aware.“
If you’ve not already tried AskTrip then give it a whirl today.
Trip introduced the freemium business model around ten years ago. It was our approach to remaining both viable and independent. The fact that we’re still here (and doing well) is some validation of our approach.
Subscriptions are available for individuals at $55 per year while institutions can subscribe, with costs dependent on both their size and organisational ‘type’ (click here for current prices).
But what do you get for the subscription? Below is an overview of the differences and as we develop new features these will mostly favour Pro subscribers:
We are absolutely delighted to announce the release of our automated clinical Q&A system – AskTrip. If you follow the blog you’ll appreciate the effort we’ve put in to create the system and we’re delighted to finally make it available to you.
What is AskTrip? AskTrip is an AI-powered clinical question-answering system built on the trusted foundation of the Trip Database. It delivers evidence-based answers to clinical questions in 30 seconds, drawing from Trip’s extensive search index to ensure the most current and relevant information.
AskTrip isn’t just smart; it’s transparent. Each answer includes links to the underlying evidence, so users can explore the sources themselves and assess their quality. Behind the system lies over 25 years of experience answering clinical questions manually – more than 10,000 Q&As – which has shaped both the structure of the answers and the types of queries the system handles best.
In short, AskTrip combines the speed and scale of AI with Trip’s proven expertise in evidence-based medicine, helping clinicians get trusted answers in seconds.
Access is via links at the top of the main Trip site and from the search results page:
Landing page
The landing page for AskTrip looks like this:
At the bottom you’ll see the most recent questions and above Ask a clinical question you’ll see four options:
Ask a question
Past questions
Search questions
‘AskTrip’ explained
Past questions
This allows you to browse questions and you can filter these by clinical area (e.g. cardiology, oncology), question type (e.g. diagnosis, management) and quality of evidence (moderate to high).
In our past Q&A systems (such as ATTRACT) users said they enjoyed looking at questions other health professionals had asked, and that was for two main reasons:
They felt good if they knew the answer.
They didn’t know what they didn’t know.
We can’t help feeling that this curiosity will still be there and that browsing questions will be a great feature of the site.
Search questions
Enter your search terms and there are options to filter the results by question type and quality of evidence.
‘AskTrip’ Explained
This is a bit of background about the site and also a high-level explanation of how the system works.
Show original question – in the beta we noted that people would ask poorly formed questions, so our system tidies them up. Clicking on the link allows you to see the original question
The foot of the answer looks like this:
References
Report an issue – given the nature of the site it’s important to allow users to report a question they believe is sub-optimal.
Handy extras worth knowing
Free vs. Pro access – Free users of Trip will have three free questions per month while Pro users will have unrestricted access.
Road-map & feedback – We have ambitious development plans (e.g. multilingual, specific Q&A monthly emails, question trajectories) but if you’d like to see extra features then please let us know via suggestions@tripdatabase.com
Mobile optimisation – the site is optimised for mobile devices so – using your phone or tablet’s web browser – navigate to AskTrip!
Adding AskTrip to your website – We’re already in discussions with third-party organisations about embedding AskTrip directly into their websites and intranets. These tailored versions match the host’s look and feel, and can feature local clinical guidance, policy content, or risk advice – integrated alongside trusted, evidence-based answers. It’s your voice, delivered at the point of care.
In conclusion
We built AskTrip to put high-quality evidence in your hands within seconds. Whether you’re a long-time Trip user or completely new, we’d love you to take AskTrip for a spin, push its limits, and tell us where it shines – or where it can do better (use feedback@tripdatabase.com). Your real-world questions are what will make the system smarter over time. Give it a try today and let us know what you think—together we can turn good evidence into great care, faster than ever.
Finally….
There are a number of people that deserve thanks in getting this over the line:
Beta testers – A small group of users asked over 500 clinical questions during the beta phase. Their persistence and repeated use gave us confidence that AskTrip was solving a real problem. Their thoughtful feedback played a major role in shaping and improving the system. We’re hugely grateful.
Abrar – one of our developers, while not involved in the main AskTrip work was instrumental it getting it live.
AD – our designer, he designed and developed the ‘front end’ of the site – he’s done a fabulous job.
Phil – Phil has been part of Trip for over 20 years as our lead developer. While Abrar now handles most of the day-to-day development, Phil continues to play a vital role in shaping Trip’s direction. For AskTrip, he took on the vast bulk of the coding – and it’s fair to say this feels like his finest contribution yet. The quality, care, and scale of his work have been immense. Like a fine wine, he just keeps getting better. I couldn’t be more grateful.
When answering clinical questions, it’s not enough to simply provide an answer – it’s essential to communicate how strong the supporting evidence is. Because our Q&A system is automated, we’ve developed a pragmatic yet transparent way of scoring the strength of evidence behind each answer.
How We Classify Evidence At the core of our approach is how we classify the references used to generate an answer. For simplicity, we’ve grouped the sources into four categories:
Essential – The highest quality sources, such as NICE, AHRQ, guidelines; especially when they are up to date.
Desirable – Other high-quality secondary evidence (e.g. systematic reviews) and key primary research studies.
Other – The rest of the content in Trip e.g. peer-reviewed journal articles, eTextbooks.
AI – Content that is generated primarily through the large language model (LLM), used when evidence is sparse or missing.
The Scoring System Each answer is scored based on the proportion of higher-quality evidence (Essential and Desirable) it includes:
High – 75% or more of the references are Essential or Desirable
Good – 55–74% are Essential or Desirable
Moderate – Below 55% Essential/Desirable
Limited – 50% or more of the answer is generated by the AI (i.e. minimal reference support)
A Nuanced Interpretation This system produces some interesting situations. For example, an answer may score High if it’s based entirely on high-quality sources – even if those sources all agree that the evidence is limited or conflicting. In other words, a High score reflects the confidence in the evidence base used to construct the answer, not necessarily that the answer is definitive or conclusive.
We believe this approach strikes a useful balance between automation and transparency. It allows users to quickly gauge how much trust they can place in the evidence behind each answer, while also recognising the complexity and occasional uncertainty inherent in clinical decision-making.
98% of the core Q&A work is complete and now we’re mainly testing and correcting minor issuess…
The main AskTrip page will look like this:
While an answer page looks like this:
Lots to see here:
References are now looking lovely – in the beta this was the biggest bugbear of testers!
Clinical areas – to help users browse Q&As of interest
Clinical type – it should actually be ‘Question type’, these include causes, treatment, complication etc, a way of classifying Q&As to help browsing but also act as a timeline of a condition – one for a future project
Quality of evidence – how strong was the evidence in answering the question. Useful for users but also one for a future project
Show original question – we noticed, from the beta, that users didn’t always form perfect questions e.g. no initial capital letter, no question mark, odd spacing. Our system corrects that – for display – but the original question is available to be seen
Related questions – not the best examples, due to the lack of Q&As in this version of the site and ignore the numbers after each title, that’s for our testing. But this is showing users questions that are closely related to this particular question
Report an issue – if a particular answer concerns someone, they can easily report it to us to be checked by our medical team
Since the beta we’ve added a whole bunch of new features, many behind the scenes, so we’re delighted that the answers still come back in less than 30 seconds.
Release date – definitely by the end of the month, maybe as early as the end of next week!
The testing of the automated Q&A system is ongoing and yesterday I thought we’d hit a major problem – a poor answer!
A quick historical detour: around 15–20 years ago, while running the NLH Q&A Service for the NHS in England, the wonderful Muir Gray (who funded the service) was keen to identify frequently asked questions. One that consistently came up was: “What is the optimal frequency of vitamin B12 injections in pernicious anaemia?”
Fast forward to today. I tested that same question on our current Q&A system – and the results were underwhelming. Thankfully, thanks to Rocio, we had a full testing trace, letting me follow every step in the process. This led me to the NICE guideline Vitamin B12 deficiency in over 16s: diagnosis and management, which states: “In this guideline, we do not use the term ‘pernicious anaemia’ to describe autoimmune gastritis.”
Curious, I emailed Chris (our medical director) to ask whether “pernicious anaemia” is now considered outdated. His reply? “Pernicious anaemia is old hat – only old fogies like us still use that term!”
So, back to the Q&A system, I did two things:
Re-asked the question using autoimmune gastritis instead of pernicious anaemia = great answer..
Updated our synonym mappings to treat both terms as equivalent in search.
What started as a concern about system performance turned into a valuable reminder of how medical language evolves – and that I’m getting old 🙂
As part of the Q&A system we are minded that including patient identifiable information (PII) is a big no-no! So, as part of the initial question processing we have a ‘guardrail’ system to handle this eventuality!
Test Q (completely made up) : My patient (Mrs Jane Smith DOB 17/12/1856) has persistent vulvovaginal candidiasis not improving with prolonged fluconazole treatment. What investigations should I undertake and can you suggest some treatments?
Our system reported:
The question as written is problematic due to a violation of criterion (2): it includes patient identifiable information.
Issue (2): Inclusion of Patient Identifiable Information Name: “Mrs Jane Smith”
Date of Birth: “DOB 17/12/1856”
These are direct identifiers and must not be included in a clinical query, even in professional contexts where confidentiality is expected.
Corrected Version (with Identifiable Information Removed): Q: A postmenopausal woman has persistent vulvovaginal candidiasis that has not improved with prolonged fluconazole treatment. What investigations should I undertake and can you suggest alternative treatments?
The question processing stage is really interesting. As well as guardrail (stripping out PII, profanities etc) it’s correcting spelling, grammar, formatting. It’s assigning question type and clinical area(s). There’s a lot of activity before the search has even started.
We’re getting close…. The system was great before and it’s getting much much better!
Trip Database Blog 
Recent Comments