Set your minimum time for eFTP in intervals.icu to 30 or 35 minutes and see what number it gives you.
But I virtually never do a consistent effort of that duration, certainly not at max effort. I’m a crit and road racer first. If I do a TT it’s a 10 miler and I’m prioritising speed (aero position) over power.
That’s kind of what I thought you’d say. Follow up question: what’s the most time in zone for a threshold workout you’ve done recently, and what was the interval structure - eg 3 × 20mins at 98% of FTP?
Send in a support ticket.
Whats duration does intervals estimate FTP off? Very rough stab at your figures doesn’t put AIFTPD far off. Say 0.90x400 = 360w. If intervals is looking at a max effort over short period it can be biased by a strong anaerobic effort and it sure sounds you are strong 
TR uses ftp to set all training zones. You would want it to be conservative so you don’t get everyone complaining about failing workouts. Just because you hit a power PR, doesn’t mean you should immediately scale up all training intensity zones.
If your 25min at 367 is a max effort, then it seems AIFTP of TR is quite accurate, as they are assuming the ftp is based around 60mins
I think the intervals default is 5 minutes. It re-estimated my eFTP the other day based off a shortish effort and I just said “Lol - nope” and went in there and set the minimum time to 20 minutes.
I’ve been riding outside and using climbs over the last block so it’s not been structured quite like that. It’s been efforts during multiple 3-4hr rides. I can say that in the last 28days (inc a rest week) I’ve done 5.5hrs at threshold using Intervals.icu measurement. If I used TR’s FTP that would likely be over 10hrs in the last 28days. I’m not sure if this is helpful though?
I exchanged messages with Amber on this a long time ago and she looked into it, but no answers came of it. I’ve not raised a support ticket since because I have other platforms estimate FTP for me
Yeah, no. 
Simple solution is to do a long form test or an open-ended interval. Get your RPE up to whatever threshold feels like and keep going.
If you have a big anaerobic contribution then a power curve extrapolated from short efforts can seriously overestimate your FTP. We’re talking 30 to 40 watts over.
Of course, all this assumes that the number and its bigness matters. Performance matters more, right?
Yeah, sorry, should have added I’d be curious to hear what TR had to say about this.
Yep, performance matters more and I just don’t have the roads for a 30-40min test. Way too many junctions or downhills as my roads are constantly rolling. TBH I’ve given up on AIFTP but still update it went I can to see if it’s improving.
I’m normally a 8-11 hr/wk rider, wanted to take it easy and so in the past 10 days I road my bike 4 hours (including 30 min tte ride) with one ride having 2x10 tempo. I was itching to go hard again and wanted to do a 30 minute tte. I know it’s not the 45 minute test, but I think it’s close enough to feel out what I could hold for 40- 45 minutes and build off of that.
The ride yesterday 30mins @ 323 watts.
The estimated FTP from various sources:
Strava : 322
Intervals.icu : 316
AI FTP : 306
I’m surprised Ai ftp is the lowest of them all. Ai ftp is normally the highest of them all. 315 seems pretty accurate to me, intervals.icu is normally pretty spot on IMO.
I rated the ride “moderate”, that’s how the overall ride felt. I didn’t associate it with any workout either.
Anyways thought I’d share this information and will see how 315 goes for the next couple weeks.
I’m not necessarily surprised by this… considering you said you’ve “wanted to take it easy” lately… AI FTPD doesn’t just look at that ONE ride when determining it’s calculation. I certainly can’t speak to how far back it looks, but have heard many times it looks at your “recent training history” when making it’s calculation… that “recent training history” is undoubtedly > 1 ride, so outside of this last effort, if many of your other rides were Z2 spins (for example)… those spins will likely all drive that calculated number lower…
Good point.
Like I said I’ll see how training goes since I start base 1 next week. I’m not afraid to lower my number if it means more consistent training.
Also I just read/learned that Joe friel recommends using the 30 minute all out power average as the number for someone’s ftp. I don’t know how I feel about that but he knows more than I do.
The next time I test myself I’ll try the kolie moore protocol again which seems most accurate, imo.
Well that would be highly problematic. If he rode at 323 watts average for 30 minutes his threshold is unlikely to be calculated at 306. I mean I guess it’s possible, but seems low for any normal ballpark measurement. What is that, 106% of AI FTP for 30 mintues? impressive.
For an ftp of 315 (based off intervals) and 30 mins at 323, that’s about 102% ftp. No way I’m setting my ftp to 323 based off Friels advice for a 30 minute test.
Intervals.icu has usually been fairly accurate if I feed it the right data.
I just wonder how much Ai ftp takes into account outside rides, even tho they say it always does. 
well, its not really “AI” its machine learning. For myself I’ve repeatedly proven over 7 years that I can reliably estimate FTP on the basis of power-to-HR at tempo/SS power. Rough estimate and then feel it out on the road when training near FTP (say 105% and below).
TR uses power and its workouts to do basically the same. It’s an estimate, like my method, and the accuracy will waver a bit depending on the data you feed it.
Let’s say your Intervals 316 estimate is correct, without knowing more.
Then I would say TR is within 3% and depending on your current training the TR estimate might be fine or you might be leaving some really minor optimizations on the table. On the flip side you would be unlikely to overreach, which is a good thing except near the end of the a block when you might want a little overreach before going into an adaptation week (to send the body a stronger adaptation signal).
Can you post an Intervals screenshot of the 30 minutes? Here is one of mine:
With default of eFTP model and eFTP minimum duration of 210-sec. Change min duration to 10 minutes and eFTP gives 263W for ftp estimate. Change min duration to 180-sec and Intervals has paused updating so I can’t tell you 
But back to the theory, here is meanmax power curve in Strava:
because its harder to see the knee of the curve in Intervals.
Point being, if you have a long enough near-max effort all these fancy algorithms are doing is finding the breaking point where the curve goes from flat-ish to trending down.
same in Intervals:
and in WKO:
I’ve got more control over graphing in WKO, so it’s a bit more obvious. Plus I added a yellow band of 95-105% manually set FTP (272 in this example, so yellow band is 258-286W).
My point being… when looking way back, its often easy to pull up an old ride in Strava (premium) and see the knee of the curve and visually estimate ftp.
Well, but the fact is you did it… you rode that power for that long. so unless ai ftp doesn’t believe you… your ftp is de facto higher than what it gave you. Just the actual current data.
That’s wrong. it’s wrong, unless you road at 105.5% of your FTP for 30 minutes. (which maybe you did). :D. My point is, it doesn’t matter if it looked back to the beginning of time. YESTERDAY you did a thing that invalidates its prediction. It should change its mind.
ftp tte can be as low as 30-35mins, so it wouldn’t be too outlandish to use 323 as ftp, you’d just begin a threshold progression at 3x10 and go from there