Skip to content

Metric · Definition · Studies

Failed Intent Rate (FIR)

The share of questions a website fails to answer. Analytics shows what visitors did. FIR measures what they wanted and didn't get.

Studies

2026 · Switzerland, Germany, Austria · presented at MeasureCamp ZurichDACH e-commerce 2026: can an AI agent answer your shoppers?20 online shops, ten shopper questions. Results published on 21 November 2026 at 18:00 CET.
2027 · DACH, Italy, UK, UAE · in preparationThe 2027 Failed Intent IndexThe DACH sample again for a year-on-year comparison, plus three new markets. To take part or get the results first, write to [email protected].

Definition

A visitor arrives with a question: are returns free, do you ship to Austria, do you have this in XL. If the site gives no usable answer, that intent has failed. FIR is the share of those questions that fail:

Standard analytics can't see this. GA4 records that a session ended, not that the visitor was looking for a returns policy that was buried in a PDF. Two sessions that look the same in a dashboard can fail for completely different reasons, and each reason has its own fix.

I defined the metric in May 2026 in Failed Intent Rate: the KPI your GA4 dashboard is missing, on the blog of AskVio, the website assistant I build, and presented it publicly for the first time at MeasureCamp Los Angeles on 30 May 2026. That post measures FIR on live traffic. For the 2026 DACH study I needed a version that works from outside, on any site, without an assistant installed. That gives two variants of the same idea.

Two variants: live FIR and audit FIR

Live FIRAudit FIR
What it measuresHow often real visitors asked for something and did not get itHow often a site cannot answer a fixed set of common questions
Where questions come fromReal visitors, in their own words, through an on-site assistantA fixed list, the same for every site (10 in the 2026 DACH study)
A question fails whenThe answer has low confidence, or a product request matches nothing in the catalogThe public pages hold no specific, usable answer
Formula(low-confidence answers + zero-catalog-match queries) ÷ all queriesquestions not answered ÷ questions asked
ComponentsContent FIR and Catalog FIR, tracked separatelyOne number per site; catalog gaps are out of scope
What you needAn assistant on the site that logs questions and answersNothing on the site; an outside crawler reads public pages
Comparable across sites?No: each site gets different questionsYes: same questions, same crawler, same scoring
Best forFinding what to fix first on your own site, week by weekBenchmarks, studies, and checking a site before an assistant goes live

The two numbers are not interchangeable. Live FIR depends on what a site's own visitors happen to ask, so a 12% live FIR and a 12% audit FIR say different things. When FIR is reported, it should say which variant it is.

They work well together. Audit FIR asks: can a site answer the basics a shopper needs, before any visitor shows up? Live FIR asks: once visitors arrive, what do they actually ask that the site can't answer? A site can score well on the first and still fail on the second, for example because shoppers keep asking for a size or product it doesn't sell.

Where to go next

Disclosure

I build AskVio, which reports live FIR to the shops that use it. Audit FIR needs no AskVio and no assistant of any kind, and a shop's audit result does not depend on using one. The scoring tool, fir-audit, will be open source from 20 November 2026.