For UK associations & professional bodies
Understand what your members really think.
We have a short, real conversation with thousands of your members, then turn what they say into representative, attributable evidence, whether you are answering a government consultation, mapping a skills gap, or deciding what to offer members next.
Real quotes, in members' own words, used only with their permission. A representative sample, not just the keenest to reply.
Real members, in their own words. A five-minute conversation, not a checkbox.
In their own words
"The threshold is workable for us, but the software costs and the quarterly filing are what will hurt the smaller practices."
Quoted with permission · sole practitioner
What you get
See the finished evidence, before you spend a penny.
Every consultation ends in one pack. Here is a real example, explained. This is the output, not a promise of one.
The questions
The two or three you set. Open enough for members to say what they mean, focused enough to compare across thousands.
The cohorts
Who you heard from, held to a quota so the sample is a fair spread of the whole membership, not just the loudest.
A typical response
A real member, in their own words, quoted with their permission. Every quote is one you could stand behind.
The headline
What a thousand conversations agree on, aggregated into citable findings you can lift straight into a submission.
The questions asked
Who we heard from
A typical response
"The threshold is workable for us, but the software costs and the quarterly filing are what will hurt the smaller practices."
Quoted with permission · sole practitioner, South West
What a thousand conversations say
How it works
One place to run a consultation, end to end.
01
Set your questions and your sample
Write the questions that matter and choose the cohorts you need represented: firm size, region, career stage. Set how many members you want to hear from.
02
Send one link to your members
No logins, no tokens. One shareable link, or per-channel links to attribute by newsletter or region. Optional membership check, without us keeping who answered.
03
Members have a five-minute conversation
Natural and unhurried. The agent listens and probes for the specifics a good interviewer would, so you get the reasoning, not just a rating.
04
Watch it fill, cohort by cohort
Each cohort fills and closes against its quota independently, so the link stays open for the groups slow to reply. You see the fill rate live and a plain recommendation.
05
Get an evidence pack you can submit
Themes, cohort composition against quota, a methodology note, citable lines, and a permanent public URL anyone can check, whether that is a department, your board, or your members.
Why we are different
Conversational insight, a price you can see, at your speed.
The nuance a tick-box loses
Real answers, in members' own words. Because AI does the reading, turning thousands of conversations into citable evidence is finally fast and affordable, not weeks of analysts poring over transcripts.
A price you can actually see
No demo required to find out what it costs. No opaque bands set on how badly we think you need it. The number is on this page, and it rewards depth.
Results when you decide you want them
Open a consultation, watch it fill, and the evidence is ready. Not months of fieldwork and a report that lands after the deadline has passed.
The evidence
Representative. Attributable. Verifiable.
Evidence you can stand behind, and that anyone can check. Not a black box, and not a replacement for your judgement.
Representative
Cohort quotas close each group independently, so the sample is a fair spread of the whole membership, not just the keenest to reply.
Attributable
Real quotes, in members' own words, used with each member's permission. They choose, per answer: by name, by descriptor, or not at all. Their voice, on their terms.
Verifiable
Every consultation gets a permanent public URL stating the sample, dates and method. Checkable in a way a survey PDF never is.See how every quote is checked →
Candid by design. Members speak candidly because they own the conversation and choose how they are quoted. You can be candid with whoever you answer to, government, board or members, because the evidence is real, representative and checkable.
How we keep ourselves honest
Every claim links to the words underneath it.
A report is only worth what its weakest claim is worth. So each figure carries the number of people it is drawn from, each quote is checked against what was actually said, and anything we cannot stand behind is left out rather than softened. Your submission counts as one response however many members are behind it, so its influence rests entirely on the quality of the evidence inside it.
What we will never say
The refusals are the more useful half. Every line in this column is something a competitor could tell you, and we will not.
| We will never say | Because | We say instead |
|---|---|---|
| "68% of members think X" | It confuses how often something was raised with how many people believe it. Silence on a theme is not disagreement. | "Raised in an estimated 68% of responses (95% CI 64 to 72%, n=88)" |
| "Representative of the membership" | Participation is self-selecting. Government's own consultation analyses state this plainly about their own data. | The achieved sample set against your membership profile, and a statement of who is missing |
| A margin of error | There is no valid inferential basis from a self-selected sample to a whole membership. | Confidence intervals on the sample proportion only, described as such |
| "Significantly more likely" between cohorts | Themes are model-assigned labels carrying measurement error a significance test does not model. On a self-selected sample a p-value is theatre. | Non-overlapping 95% intervals, described as a gap worth examining, never as a tested result |
| A sentiment score, such as "7.2" | Spurious precision on a constructed scale. | Sentiment direction per theme, evidenced with quotes |
| NPS, satisfaction scales, derived importance | These need complete structured data on scaled items. Conversational data is missing by design. | Add a short structured module, or decline the work |
| "Worth £Xm to the sector" | No valid basis for projecting to a population. | A clearly labelled illustrative scenario with its assumptions on the face of it |
The governing line. We quantify how often something was raised within the sample we achieved, and never infer to your whole membership. That is the same position UK government takes when it counts themes in free-text consultation responses.
How a member's words reach a page
Six gates. A quote that fails any one of them does not appear, and the default at every stage is silence.
The member says it
A conversation of roughly five minutes, stored as their actual words and not only as a paraphrase, so the source of every later claim still exists to be checked.
The machine proposes a quote, and the code checks it
Every candidate quote is matched against the transcript and discarded if it is not verifiably there. Paraphrases, inventions, tidied grammar and sentences stitched together from different points in the conversation are all rejected.
Contact details are removed, and the removal is logged
Emails and phone numbers are stripped, and we record that we did it. Deliberately narrow, because this is not anonymisation. The member decides that themselves at the next step.
The member sees exactly what would be published
Their own words and the description that would sit beside them, because context identifies a firm as surely as a name does. In a 400-member body, "a regional contractor in the North West with about 50 staff" names someone.
They choose how far it goes
Not quoted, quoted anonymously, quoted with a description such as firm size and region, or quoted by name. You set the ceiling, the member chooses within it, and the ceiling is enforced on our server rather than in their browser.
They can take it back, including after publication
Withdrawal is first class. A withdrawn quote disappears from the next generation of the report. Consent given is not consent locked.
The line is in the database, not the policy. A response carries no name, email or user reference, ever. Identity lives in a separate table holding no reference to any response or consultation. The only path from an answer to a person runs through an explicit permission grant, and a database constraint physically refuses to attach an identity to an anonymous one.
What we have measured, and what we have not
Three independent passes over a real 88-response consultation.
What these numbers are not. They measure whether the analysis is stable and what it refuses. They do not measure whether the themes are right, because that needs a human-coded comparison on the same data and we do not have one yet. Until we do, we report consistency and refusals, and we do not claim accuracy. That is the honest answer, and it is the reason a person reviews the theme set before anything is published.
What it costs
A price you can see, that rewards depth.
A campaign fee, then a price per conversation that falls as you talk to more members. Size it below.
That is a ceiling, not a bill. You agree a maximum, and we invoice for the conversations that actually happen. If fewer members respond than you hoped, you pay for fewer. Every agency in this market invoices for the fieldwork whether it lands or not, because its moderator days and recruitment are committed before anyone replies. Ours are not, so we carry that risk instead of charging you for it.
No demo required to see the price. It is published here, not negotiated behind a call, and never set on how badly we think you need it. If you reach your maximum and want to keep going, the agreement extends.
Try it yourself, on your own questions.
Set up a consultation of your own and put it in front of real members. Give us your website address and we draft your profile from it, so you are writing questions within a few minutes rather than filling in forms.
Your first 20 conversations are funded. No card, no sales call.
When you go to your whole membership, it works differently on purpose: we agree a price and a maximum, a person reads your questions and cohort design, and a short test round runs before anything reaches your members. An association gets one chance to mail its membership.