Vision AI ← BACK TO SEARCHSeason2025/262026 · this seasonAll seasons
Building the full report
Combining every season — this one is larger, give it a moment.
Team reportBundesliga 2026

Hamburg

A territorially-dominated side, aggressive high-press out of possession, with a low-output attack. Currently #11 of 18 on 9 points (3-0-4, 6:16). Tactical profile below is built from 7 matches of ball-by-ball event data, contextualised against the league.

territorially-dominatedaggressive high-presslow-output attack
L
D
L
L
L
W
W
D
L
L
L
W
W
W
L
9
points
#11 of 18 · 7 games
6:16
goals
-10 GD
3-0-4
record
W-D-L
1.29
points/game
#11 in the league
0.84
xG for/game
rank #18
1.78
xG against/game
rank #13
#15
press rank
of 18 · most aggressive
35%
field tilt
#18
Hamburg
League average
Expected goals for / game
0.841.63
Expected goals against / game
1.781.63
Field tilt
35%50%
Pass retention
76%79%
Overview

The team

Who they are and how the season went.

Who Are They? — Identity

The question
In one read, what kind of team is Hamburg and how good was the season?
Read. Hamburg currently sit #11 of 18 on 9 points (3W-0D-4L, 1.29 pts/game), scoring 6 and conceding 16 for a goal difference of -10. On the ball they are a territorially-dominated team (35% field tilt, #18 in the league); off it they defend with a aggressive high-press (#15 of 18 for press intensity). Across the 7 matches of event data, they create 0.84 xG/game (#18) and concede 1.78 (#13), a net of -0.94 xG/game — the underlying performance matches the actual goal difference.

Season Context — the league table

The question
Where did Hamburg actually finish, and against whom?

The authoritative final table (full season), centred on Hamburg.

#teamPWDLGFGAGDPts
8Elversberg73131215-310
9Augsburg72321713+49
10Hoffenheim73041414+09
11Hamburg7304616-109
12Koln7223811-38
13Paderborn722369-38
14Eintracht Frankfurt72231017-78

Match Momentum — when they create and concede danger

The question
Across a whole game, which periods does Hamburg actually dominate for chances — and which periods hurt them?

Net xG (created minus conceded) in each 15-minute window, summed across the whole season's matches — above the line is time they dominate for chances, below is time it hurts them. Real on-clock shot timing.

dominant (net xG for)conceding (net xG against)
even0-15'16-30'31-45'46-60'61-75'76-90+'-2.31
Vision AI Model Insight
Hamburg tend to come alive after the break — first-half net xG -4.18, second-half -2.40. Their strongest period is 61-75' (net -0.48 xG); their most dangerous period to face is 31-45' (net -2.31 xG against them).

xG Race — the season, match by match

Expected goals piling up over 7 matches: Hamburg against what their opponents created. A line pulling away upwards is a side creating more than it gives away; the gap at the end is the season’s balance (-6.6 xG). Hover a point for that match.

049135.912.5Borussia Dortmund (A) 0-2 · xG 0.70 to 1.48Mainz (H) 0-5 · xG 0.30 to 2.54RBL (A) 0-5 · xG 0.71 to 1.84Koln (H) 2-1 · xG 1.29 to 1.83Hoffenheim (A) 3-2 · xG 1.38 to 1.41Stuttgart (H) 1-0 · xG 1.15 to 2.00Paderborn (A) 0-1 · xG 0.37 to 1.40M1M2M3M4M5M6M7
HamburgOpponents against Hamburg

Tactical DNA

The football question
In five genes, what is Hamburg's footballing identity?

Each gene is a 0–100 score — the team's league percentile across the metrics that define that phase of play. It distils the whole report into an identity fingerprint: the taller the gene, the more that trait defines them.

6
Build-Up
possession control from the back
22
Progression
moving the ball upfield with threat
4
Creation
manufacturing chances
8
Press
winning the ball high & hard
28
Solidity
resisting the opponent's threat
Genetic identity
Hamburg are defined most by their Solidity DNA (28/100 · limited at resisting the opponent's threat), and least by their Creation DNA (4/100). Percentiles vs the 18 teams in the league.

The Playstyle Wheel

Fifteen style metrics across five domains — Possess, Disrupt, Finish, Press, Defend — each a percentile against the rest of the league. Metrics marked ~proxy use the closest available event-data signal where the standard definition needs data this feed doesn't carry (explicit pressure events, offside/keeper-sweep incidents).

Possess30Disrupt41Finish10Press6Defend10
Possess
Deep buildup
62%
Possession
19%
Field tilt
10%
Disrupt
Central progression ~proxy
29%
Dribble tendency
86%
Progressive passes
10%
Finish
Final-third patience
0%
Shot quality
14%
Open-play xG
14%
Press
Forward press ~proxy
14%
High regains
5%
Pressing efficiency ~proxy
0%
Defend
Def-mid press ~proxy
0%
High line ~proxy
0%
PAdj defensive actions
29%
Hamburg is defined most by Disrupt (41% in the league) and weakest on Press (6%). Percentiles vs the 21 teams in the league this season.
In possession

In possession

How they keep the ball, build up, progress, create and finish, and where their attacks die.

Keeping the ball6 sections

Field Tilt — Territorial Control

The question
How much of the pitch does Hamburg actually control, relative to the rest of the league?

Field tilt = share of final-third touches between the two sides across Hamburg's matches, the standard proxy for territorial dominance. Plotted against points per game for every side in the league — the real question isn't just who controls territory, it's whether that control actually converts into results. Dashed lines mark the league average on each axis; Hamburg highlighted. Hover any dot for the team.

Borussia Dortmund: 57% tilt, 2.43 pts/gBayern: 77% tilt, 2.43 pts/gFreiburg: 55% tilt, 1.86 pts/gLeverkusen: 57% tilt, 1.86 pts/gWerder Bremen: 42% tilt, 1.71 pts/gRBL: 54% tilt, 1.71 pts/gMainz: 60% tilt, 1.43 pts/gElversberg: 37% tilt, 1.43 pts/gHamburg: 35% tilt, 1.29 pts/gAugsburg: 44% tilt, 1.29 pts/gHoffenheim: 62% tilt, 1.29 pts/gPaderborn: 46% tilt, 1.14 pts/gEintracht Frankfurt: 48% tilt, 1.14 pts/gKoln: 48% tilt, 1.14 pts/gUnion Berlin: 41% tilt, 0.86 pts/gStuttgart: 56% tilt, 0.86 pts/gSchalke: 38% tilt, 0.86 pts/gBorussia Monchengladbach: 44% tilt, 0.43 pts/gHamburg35%49%63%77%0.41.11.82.4FIELD TILT %POINTS / GAME
Vision AI Model Insight
Hamburg post 35% field tilt, ranking #18 of 18 in the league — below the league mid-point, spending more of the game defending their own territory than dictating it, and their 1.29 points/game sits below the league-average return — territory is genuinely converting into results.

Where the time goes — how long each phase lasts

The question
When Hamburg has the ball, how much of that time is spent building, progressing and creating?

The share of Hamburg's time on the ball spent in each phase of play, in the order the phases happen. A phase is where the ball is on the pitch (own third, middle third, final third); a transition or a set piece skips the build-up and is counted on its own.

Build-up: 30.5% of the time on the ball30%Progression: 47.5% of the time on the ball48%Chance creation: 18.7% of the time on the ball19%Attacking transition: 3.3% of the time on the ball48%PROGRESSION
PhaseShare of the time
Build-up30.5%
Progression47.5%
Chance creation18.7%
Attacking transition3.3%
Vision AI Model Insight
Progression is where Hamburg spends most of its time on the ball (48% of its time on the ball).

Passing Network

The question
Who actually plays with whom — the real on-pitch connections, not just average positions?

Every pass linked to its likely receiver (the next same-team touch), aggregated into player-pair combinations at each player's average position. Line width = how often the pair combines; colour = threat generated per pass (blue low → red high). Hover a line for the pair, or click a player to isolate their connections.

Daniel Heuer Fernandes ↔ Warmed Omari: 58 passes, -0.6 combined xTDaniel Heuer Fernandes ↔ Sebastiaan Bornauw: 37 passes, 0.3 combined xTAlbert Sambi Lokonga ↔ Nicolai Remberg: 36 passes, 0.0 combined xTDaniel Heuer Fernandes ↔ Albert Sambi Lokonga: 34 passes, 0.1 combined xTDaniel Heuer Fernandes ↔ Nicolai Remberg: 31 passes, 0.5 combined xTNicolás Capaldo ↔ Zakaria El Ouahdi: 29 passes, -0.0 combined xTNicolás Capaldo ↔ Nicolai Remberg: 25 passes, -0.1 combined xTSebastiaan Bornauw ↔ Nicolai Remberg: 24 passes, -0.1 combined xTWarmed Omari ↔ David Møller Wolfe: 23 passes, -0.3 combined xTDavid Møller Wolfe ↔ Albert Grønbæk: 22 passes, 1.4 combined xTDaniel Heuer Fernandes ↔ Nicolás Capaldo: 21 passes, 0.2 combined xTAlbert Sambi Lokonga ↔ Nicolás Capaldo: 21 passes, -0.1 combined xTAlbert Sambi Lokonga ↔ Zakaria El Ouahdi: 21 passes, 0.2 combined xTSebastiaan Bornauw ↔ Warmed Omari: 21 passes, -0.0 combined xTNicolás Capaldo ↔ Albert Grønbæk: 21 passes, 0.6 combined xTDavid Møller Wolfe ↔ Martin Adeline: 18 passes, 1.5 combined xTAlbert Grønbæk ↔ Nicolai Remberg: 17 passes, 0.4 combined xTSebastiaan Bornauw ↔ Nicolás Capaldo: 16 passes, 0.1 combined xTNicolás Capaldo ↔ Martin Adeline: 16 passes, -0.1 combined xTSebastiaan Bornauw ↔ Zakaria El Ouahdi: 15 passes, 0.0 combined xTMartin Adeline ↔ Zakaria El Ouahdi: 15 passes, 0.6 combined xTNicolás Capaldo ↔ David Møller Wolfe: 14 passes, 0.3 combined xTDaniel Heuer Fernandes ↔ Yussuf Poulsen: 13 passes, 1.7 combined xTDaniel Heuer Fernandes ↔ Albert Grønbæk: 13 passes, -0.6 combined xTDaniel Heuer Fernandes — isolate this player's connectionsFernandesRansford Königsdörffer — isolate this player's connectionsKönigsdörfFábio Vieira — isolate this player's connectionsVieiraTerem Moffi — isolate this player's connectionsMoffiAlbert Grønbæk — isolate this player's connectionsGrønbækNicolás Capaldo — isolate this player's connectionsCapaldoRayan Philippe — isolate this player's connectionsPhilippeDavid Møller Wolfe — isolate this player's connectionsWolfeWarmed Omari — isolate this player's connectionsOmariAlbert Sambi Lokonga — isolate this player's connectionsLokongaSebastiaan Bornauw — isolate this player's connectionsBornauwYussuf Poulsen — isolate this player's connectionsPoulsenMartin Adeline — isolate this player's connectionsAdelineZakaria El Ouahdi — isolate this player's connectionsOuahdiNicolai Remberg — isolate this player's connectionsRembergOtto Stange — isolate this player's connectionsStange
width = passes between the paircolour = xT per pass: low → high

Top 10 combinations

Fernandes ↔ Omari
58p · -0.6xT
Fernandes ↔ Bornauw
37p · 0.3xT
Lokonga ↔ Remberg
36p · 0.0xT
Fernandes ↔ Lokonga
34p · 0.1xT
Fernandes ↔ Remberg
31p · 0.5xT
Capaldo ↔ Ouahdi
29p · -0.0xT
Capaldo ↔ Remberg
25p · -0.1xT
Bornauw ↔ Remberg
24p · -0.1xT
Omari ↔ Wolfe
23p · -0.3xT
Wolfe ↔ Grønbæk
22p · 1.4xT
Vision AI Model Insight
Busiest connection: Daniel Heuer Fernandes ↔ Warmed Omari (58 passes). Most dangerous per pass: David Møller Wolfe ↔ Martin Adeline (0.08 xT/pass over 18 passes) — the combination that hurts opponents most when it fires, not just the one used most.

Touch Density — where Hamburg had the ball

Every touch across 63 matches. Brighter means more touches.

Which Zones Do They Attack Through?

The question
Across the whole pitch, where does Hamburg actually do its on-ball work?

Passes on one map, carries (the ball travelling with a player) on the other. Each is binned into the 15 pitch zones (three thirds × five vertical lanes) and shaded by its share of that kind of action; the arrows are the real actions.

Passes
the ball moved by a pass
2634
ACTIONS
5%6%14%6%5%11%11%9%9%8%5%4%2%3%4%PASSES
Carries
the ball moved with a player
502
ACTIONS
4%7%10%7%3%11%11%10%10%9%5%3%2%2%6%CARRIES
Vision AI Model Insight
Their single busiest zone is the centre of the defensive third (13.6% of all actions). 62% of actions run through the inside lanes (centre + both half-spaces) versus 38% down the two wings — an inside-dominant, half-space build. By third: 35% defensive, 48% middle, 18% attacking.

Attack Sides

Which channel they attacked through this season: the share of every action made in the opponent’s half, down the left, through the middle and down the right. Hamburg leaned on their right (43%). The bars under the pitch put the league’s share beside theirs.

36%Left side21%Middle43%Right sideATTACKING →
Hamburg
36%21%43%
League
39%25%36%

Final-Third Entries

Every completed pass or carry that took the ball from outside the final third into it, by the channel it arrived in. Hamburg made 201 this season (28.7 a match); 27% came into the right wing. Longer, bolder arrows mean more entries. Entries by carrying the ball in count as well as completed passes; dribbles are not counted.

Left wing: 50 entries (25%)5025%LEFT WINGLeft half-space: 35 entries (17%)3517%LEFT HALF-SPACECentre: 20 entries (10%)2010%CENTRERight half-space: 42 entries (21%)4221%RIGHT HALF-SPACERight wing: 54 entries (27%)5427%RIGHT WINGATTACKING ↑
ChannelEntriesPer matchShareLeague share
Left wing507.125%28%
Left half-space355.017%17%
Centre202.910%14%
Right half-space426.021%15%
Right wing547.727%26%
Build-up2 sections

Build-Up — the pass map

The football question
How does Hamburg progress possession from defence into attack — and who runs it?

Build-up passes grouped into 5 real categories — not the old zone grid, not raw individual lines: CB (passer is a centre-back), Wide→FB, Central, Long Wide, Long Central. Each gets its own panel below, so nothing competes for attention. Arrow width = volume, labelled with the exact count; hover for the top passer.

927build-up passes attempted
74%completed
32%reach the middle third
3%go long into the final third

Pass types

268CB · 39%
63Long Wide · 9%
12Long Central · 2%
268Wide → FB · 39%
79Central · 11%

Sequence success — build-up

108build-up sequences this season
6%succeed — reach the next third or a shot
45%turned over with nothing to show
CB268 · 39%
right: 141 passes, most from Bornauw141left: 127 passes, most from Omari127
Long Wide63 · 9%
right: 34 passes, most from Fernandes34left: 29 passes, most from Fernandes29
Long Central12 · 2%
right: 8 passes, most from Fernandes8left: 4 passes, most from Fernandes4
Wide → FB268 · 39%
right: 142 passes, most from Fernandes142left: 126 passes, most from Fernandes126
Central79 · 11%
left: 46 passes, most from Fernandes46right: 33 passes, most from Fernandes33
◆ Vision AI Insight
Hamburg build predominantly down the left, with Fernandes as the fulcrum (210 build-up passes). Only 35% of their build-up passes actually advance a third — the rest is lateral circulation, the hallmark of a possession-controlling side that circulates patiently in midfield before progressing. Their single most-repeated pattern is C def → LHS def (42×).

Pass Explorer

Every pass of Hamburg’s last 7 matches as an arrow, theirs first and the opponents’ with other team, each side attacking left to right (solid = completed, dashed grey = failed). Eight families per team — click any map to open it wide, then filter by channel or third, from one to another (or click a cell of the flow grids), by outcome, half, minute and passer. Channels: right wing, right half-space, centre, left half-space, left wing.

Progression4 sections

How They Progress — the mechanism

Not just how many progressive passes, but where they start, who plays them, and whether they actually penetrate. 293 progressive passes across 7 matches (41.9/game).

Origin lane

Right wing
31%
Right half-space
11%
Central
20%
Left half-space
14%
Left wing
25%
Progression is right-dominant: 42% right side · 20% central · 39% left.

Who generates it

Daniel Heuer Fernandes
50 · 17%
David Møller Wolfe
37 · 13%
Nicolás Capaldo
27 · 9%
Albert Grønbæk
24 · 8%
Albert Sambi Lokonga
19 · 6%
Top two — Daniel Heuer Fernandes & David Møller Wolfe — account for 30% of all progression.
PROGRESSION
41.9 prog passes/game
mostly right
→
PENETRATION
30% reach final third
17% reach the box
→
THREAT
the other 70% is recycled
progress ≠ danger
What came of it. 30% of progressive passes reached the final third and 17% the box; the rest was recycled in front of the block. 30% of the progression ran through two players, mostly down the right side.

Which lanes actually create the threat

Share of passes played from each lane against its share of the threat (xT) they add. Efficient = more threat than volume, sterile = lots of the ball, little damage.

Per lane — volume vs threat
Right wingbalanced
Right half-spacesterile
Centralbalanced
Left half-spacebalanced
Left wingbalanced

Progression — the pass map

The football question
Once Hamburg have the ball in midfield, how do they actually break into the final third — and who carries that job?

Progression passes grouped into 5 real categories: CB, Wide→FB, Central, Long Wide, Long Central. Each gets its own panel below, so nothing competes for attention. Arrow width = volume, labelled with the exact count; hover for the top passer.

1240progression passes attempted
81%completed
14%break into the final third
17%go backward into the defensive third

Pass types

303CB · 30%
31Long Wide · 3%
4Long Central · 0%
532Wide → FB · 53%
130Central · 13%

Sequence success — progression

165progression sequences this season
28%succeed — reach the next third or a shot
45%turned over with nothing to show
CB303 · 30%
right: 163 passes, most from Capaldo163left: 140 passes, most from Omari140
Long Wide31 · 3%
right: 19 passes, most from Wolfe19left: 12 passes, most from Lemke12
Long Central4 · 0%
left: 4 passes, most from Grønbæk4
Wide → FB532 · 53%
right: 279 passes, most from Ouahdi279left: 253 passes, most from Remberg253
Central130 · 13%
left: 68 passes, most from Remberg68right: 62 passes, most from Remberg62
◆ Vision AI Insight
Hamburg progress predominantly down the right, with Remberg the busiest midfield outlet (124 progression passes). Only 14% of passes that start in midfield actually break the final-third line — the rest (69%) is recycled back into midfield or (17%) played backward, the hallmark of a side that carries progression itself through midfield rather than just passing through it. Their most-repeated pattern is RHS mid → RW mid (59×) — press that lane and midfield progression stalls.

Decision Quality — not all completed passes are equal

A 90% pass completion can hide a sideways habit. Grading every pass by the threat it adds separates value creation from safe circulation.

Excellent (high xT gain)
15%
Progressive
1%
Neutral / sideways
51%
Safe / backward
33%
16% of passes are progressive-or-better; the remaining 84% keep possession without advancing it. A control-first side — safe in build-up, reliant on a few players for the incision.

Carries Map — progressive ball-carries, squad-wide

The question
Where does Hamburg actually progress the ball with their feet, not a pass?

117 progressive carries this season across the whole squad (24% of 491 tracked carries total), grouped into up to 4 spatial patterns by where each carry starts and ends together — not just its origin zone. Median 16m, longest 47m. Most active carrier: Omari (12). Filter to one player below.

First (34)Second (33)Third (31)Fourth (19)grouped by carry pattern (start + end position), largest group first
startendown goal left, attacking →
Chance creation4 sections

Chance creation — how the shots come

The question
Where do Hamburg's chances actually come from?

Every shot sorted twice. First by the kind of attack: an attacking transition (the shot came within 15 seconds of winning the ball), a settled attack (open play after the team had the ball), or a set piece. Then by how it was set up: a cross, a cut-back, a long ball, a pass into the box, or no pass at all (the player created it himself). So a cut-back from an attacking transition is counted apart from a cut-back in a settled attack.

75shots
5.9xG
0.08xG per shot
3big chances (0.3+ xG)
6goals
#17key passes / game in the league
#17box entries / game in the league
Attacking transition: 17 shots (23%)23%17Settled attack: 39 shots (52%)52%39Set piece: 19 shots (25%)25%1975SHOTS
Kind of attack, then how the shot was set upShotsGoalsxGxG / shot
Attacking transition 23% of shots1701.550.09
Cross100.070.07
Pass into the box / short pass1000.730.07
Own creation (carry, dribble, rebound)600.750.13
Settled attack 52% of shots3942.960.08
Cross520.650.13
Cut-back410.480.12
Long ball100.030.03
Pass into the box / short pass2011.230.06
Own creation (carry, dribble, rebound)900.580.06
Set piece 25% of shots1921.390.07
Corner1321.260.10
Free kick600.130.02

Every attempt to create — and what came of it

Every pass into the box, every cut-back and every pass before a shot. Red led to a shot, gold to a goal; grey ones were tried but no shot came: solid found a team-mate, dashed lost the ball. Filter by outcome, type or player; tap an arrow for the detail.

Who sets the shots up

PlayerSet-upsxG createdGoals
Albert Sambi Lokonga70.681
Albert Grønbæk40.461
Fábio Vieira30.300
Miro Muheim50.291
Nicolai Remberg20.230

Who takes them

PlayerShotsxGGoals
Yussuf Poulsen91.222
Fábio Vieira140.930
Patson Daka80.760
Terem Moffi60.741
Nicolás Capaldo60.691
Vision AI Model Insight
The biggest source of Hamburg's chances, by xG, is settled attack (3.0 of 5.9 xG, 39 of 75 shots), mostly pass into the box / short pass. 17 of the 75 shots (23%) came within 15 seconds of winning the ball. 19 of the 75 shots came from set pieces; 6 goals from 5.9 xG (+0.1).

Chance Creation — the pass map

The football question
How does Hamburg consistently create dangerous chances — from which zones, and who creates them?

Key passes (the pass immediately before a shot) grouped into 5 real categories: CB, Wide→FB, Central, Long Wide, Long Central. Each gets its own panel below, so nothing competes for attention. Arrow width = volume, labelled with the exact count; hover for the top creator.

Pass types

5CB · 10%
2Long Wide · 4%
4Long Central · 8%
16Wide → FB · 33%
22Central · 45%

Sequence success — final-third

86final-third sequences this season
22%succeed — produce a shot
36%turned over with nothing to show

Danger Funnel — which service carries threat

Every key pass pooled by where it was played FROM, then drawn with its arrow width set by total xT rather than by count. A zone that produces a lot of cheap balls shrinks; one that produces a few decisive ones dominates. Where this disagrees with the volume map, the volume map is the misleading one.

0 key passes shown● low threat● mid● high threatarrow width = total xT, not count
CB5 · 10%
left: 3 passes, most from Capaldo3right: 2 passes, most from Capaldo2
Long Wide2 · 4%
left: 2 passes, most from Fernandes2
Long Central4 · 8%
left: 3 passes, most from Muheim3
Wide → FB16 · 33%
right: 11 passes, most from Daka11left: 5 passes, most from Lokonga5
Central22 · 45%
right: 13 passes, most from Muheim13left: 9 passes, most from Wolfe9

Who creates — volume × threat

9Muheim
7Grønbæk
5Lokonga
4Wolfe
4Daka
3Capaldo
3Adeline
49key passes #17 of 18
9.3box entries/game #17 of 18
23.3final-3rd entries/game #16 of 18
0.84xG/game #18 of 18
6goals #15 of 18
+0.1finishing vs xG #11 of 18
◆ Vision AI Insight
Hamburg lean right — 47% of their key passes come from that flank and its half-space (23 of 49), most often from Muheim (5). They funnel chances into the c of the final third, most often via RHS att → C att (10 key passes, most often from Lokonga). Muheim is the primary source overall. They generate 0.84 xG a game and finish it clinical — they beat their xG, led by Miro Muheim (2G), Yussuf Poulsen (2G), Nicolás Capaldo (1G).

Crosses & Cutbacks — squad-wide

The question
How does Hamburg deliver into the box from wide areas, and what comes of it?

70 crosses: 21 found a team-mate (30%), 6 led to a shot (9%). 17 cut-backs: 8 found a team-mate (47%), 5 led to a shot (29%). A cross starts wide and is aimed into the box; a cut-back starts near the byline and is squared back. Grey ones were tried but no shot came: solid found a team-mate, dashed lost the ball.

Crosses by Territory

The question
Which part of the final third does Hamburg actually cross from?

70 crosses this season (the same crosses as the map above), split into fifteen territories — five channels (both wings, both half-spaces and the centre) by three depths from the halfway line to the byline. 21% come from one territory, the byline right wing; 9 come from the half-spaces and 0 from the centre.

deep right wing: 5 crosses (7%)7%5deep right half-space: 1 crosses (1%)1%1deep centre: 0 crosses (0%)deep left half-space: 1 crosses (1%)1%1deep left wing: 6 crosses (9%)9%6advanced right wing: 12 crosses (17%)17%12advanced right half-space: 4 crosses (6%)6%4advanced centre: 0 crosses (0%)advanced left half-space: 0 crosses (0%)advanced left wing: 8 crosses (11%)11%8byline right wing: 15 crosses (21%)21%15byline right half-space: 1 crosses (1%)1%1byline centre: 0 crosses (0%)byline left half-space: 2 crosses (3%)3%2byline left wing: 15 crosses (21%)21%15
TerritoryCrossesShareLed to a shot
byline · right wing1521%2
byline · left wing1521%0
advanced · right wing1217%0
advanced · left wing811%1
deep · left wing69%0
deep · right wing57%0
advanced · right half-space46%2
byline · left half-space23%1
deep · right half-space11%0
deep · left half-space11%0
byline · right half-space11%0
Finishing3 sections

Shot Map

75 shots for 5.9 xG (0.84/game, #18 in the league). Click an area of the box to see who shoots from there; filter by outcome, player or match.

Low-output attack. 10.7 shots/game at 0.079 xG/shot. Box entries 9/game (#17). Threat created 8.8 xT/game (#17).

Goal Sequences

The move behind each of Hamburg’s 6 goals this season, from the moment they got the ball to the finish. Pick a goal from the list, then step through it or press Play: numbered circles are passes and touches, dotted lines are carries (the ball travelling with a player), dashed grey is a pass that was lost, the star is the shot.

Each goal’s possession, rebuilt from the raw event feed — 6 goals traced.

How Do They Score?

The question
Where do the goals actually come from — open play, dead balls, which foot?

Every goal Hamburg scored across the loaded matches, broken down by how it was created and finished.

By situation

Open play
4 · 67%
Set pieces
2 · 33%
Penalties
0 · 0%

By finish

Right foot
1 · 17%
Left foot
3 · 50%
Header
2 · 33%
Vision AI Model Insight
6 goals scored. 67% come in open play, but 33% from set pieces — a genuine dead-ball weapon that bypasses the open-play build-up.
When they lose it1 section

Ball-Loss Map — where attacks die

Every turnover has a location and a cause. This is a rate, not a raw count — the share of pass attempts from each zone that end in a turnover, so a zone they simply play through more often doesn't automatically look riskier. Grey cells are real zones with too few attempts to trust a rate.

Loss rate by zone

43 of 124 pass attempts lost here (35%).35%43/124Capaldo35 of 153 pass attempts lost here (23%).23%35/153Fernandes84 of 374 pass attempts lost here (22%).22%84/374Fernandes26 of 150 pass attempts lost here (17%).17%26/150Fernandes49 of 126 pass attempts lost here (39%).39%49/126Wolfe68 of 286 pass attempts lost here (24%).24%68/286Capaldo57 of 277 pass attempts lost here (21%).21%57/277Capaldo31 of 232 pass attempts lost here (13%).13%31/232Remberg38 of 231 pass attempts lost here (16%).16%38/231Grønbæk46 of 214 pass attempts lost here (21%).21%46/214Wolfe50 of 144 pass attempts lost here (35%).35%50/144Ouahdi32 of 93 pass attempts lost here (34%).34%32/93Ouahdi20 of 56 pass attempts lost here (36%).36%20/56Capaldo29 of 67 pass attempts lost here (43%).43%29/67Lemke33 of 107 pass attempts lost here (31%).31%33/107Wolfeattacking →

How they lose it

Incomplete pass — attacking third
164
Failed forward pass
115
Failed take-on
46
Lost in the defensive third
237
Their weakest zone is the left half-space in the attacking third: 43% of 67 pass attempts there are lost (29 times). Separately, 26% of all losses happen in the attacking third — a fair share happen deeper, which invites transitions.
Out of possession

Out of possession

How they press, where they win the ball back, and how they concede.

Pressing2 sections

Pressing — the full picture

The football question
How hard does Hamburg press, where, and does it actually work — beyond a single PPDA number?

A composite Pressing Index built from four event-derived dimensions, each ranked against the league. Not one metric — intensity, height, effectiveness and opponent disruption together. The pitch shows every defensive action (the only five events this data records); the white line is the average height that feeds the score. Toggle by action type below, hover any dot for the player.

15
Pressing Index
/100 · passive
Intensity24
PPDA, high-press share, high-zone actions
Height11
how high up the pitch they defend
Effectiveness6
high recoveries & high-regain share
Disruption19
opponent completion & progression allowed

Every defensive action & where it happens

Where they win the ball back — by lane

RW
18%
RHS
22%
C
27%
LHS
17%
LW
17%
By third (high / mid / low regain)
Def 51%
Mid 35%
Att 14%
Read
Ranked #15 of 18 for press intensity, this is a high press. Note the tension: 51% of their raw defensive actions still occur in their own third — a possession effect, not a passive one. Dominating the ball (21% high-press share) means that when they do defend, it is often deep. Of recoveries, 44% are won high up the pitch.

Every pressing metric, ranked in the league

metricvaluerankmeaning
PPDA (opp passes per def action)—#15/18lower = more intense; rank is what matters
Defensive actions / game177#5/18
High-press share21%#13/18def actions won high up
Defensive-action height (0–100)36.4#16/18avg pitch height of actions
High recoveries / game17.3#17/18ball won in mid+att third
High-recovery share44%#17/18share of recoveries won high
Opponent completion allowed84%#18/18lower = more disruptive
Opponent progressive allowed9.8%#11/18of opp passes, lower = better
Transition timing
This source carries per-event timestamps, so genuine transition metrics — counter-attack shots, press→shot conversions, time-to-recover — are measured; see the dedicated Transitions section below.

How long they keep it — passes and seconds until the ball is won

The question
Once the opponent has the ball, how many passes and how many seconds pass before Hamburg win it back with a defensive action?

Counted over the 224 opposition possessions that Hamburg ended with a tackle, interception, recovery or challenge. Fewer passes and seconds means the ball is won quickly (a press); more means the opponent is allowed to play before Hamburg step in. Hamburg win it after 8.4 opponent passes in the first half-hour and after 5.7 after the hour mark (sooner).

PASSES THEY GET
7.0passes
median 4 · before Hamburg win it
TIME THEY KEEP IT
22sec
median 10s · 32.0 wins per game
How many passes the opponent got in before the ball was won
33%
26%
14%
26%
0–2 passes3–5 passes6–9 passes10+ passes
Through the match — every 15 minutes
0–15′
9.7
32s
15–30′
6.9
20s
30–45+′
7.7
24s
45–60′
6.6
22s
60–75′
7.1
24s
75–90+′
4.6
12s
average passesaverage seconds

Attitude in each third

Every other style number here says how much Hamburg does. This says how: wide or central, short or long, patient or direct. Bars are standard deviations from the league mean for passes played from that third; a solid bar marks a dimension where Hamburg are genuinely unusual, and a verdict is only written where something clears 0.85 sd — a side that is ordinary in a third is told so rather than given a label for average play.

Build-up (own third) 927 passes

slower

Width of use-0.4420.10
Wide-channel share-0.300.29
Side bias+0.030.27
Pass length+0.5224.58
Long-ball share+0.480.28
Forward gain per pass+0.7414.65
Backward-pass share-0.600.17
Deep-pass share+0.680.35
Completion-0.670.74
Seconds between passes+0.883.86
Side used

left 25% · central 50% · right 25%

Progression (middle third) 1,240 passes

nothing unusual in this zone

Width of use+0.8227.30
Wide-channel share+0.400.43
Side bias-0.82-3.17
Pass length+0.1117.38
Long-ball share+0.040.10
Forward gain per pass-0.333.11
Backward-pass share+0.200.34
Deep-pass share+0.020.16
Completion-0.610.80
Seconds between passes+0.533.43
Side used

left 35% · central 24% · right 41%

Final third 467 passes

trying to break lines, longer passing

Width of use-0.1131.34
Wide-channel share-0.210.57
Side bias-0.64-5.00
Pass length+0.9016.86
Long-ball share+0.190.11
Forward gain per pass+0.661.92
Backward-pass share-0.120.38
Deep-pass share+1.130.13
Completion-0.660.64
Seconds between passes-0.153.29
Side used

left 35% · central 16% · right 48%

Reference measured across roughly 3,500 match-teams in this competition, per third, so the comparison is with Hamburg's own league. The means behave as football should: width of use grows 21.0 → 25.6 → 31.6 going forward, pass length shrinks 22.7 → 17.2 → 15.5 m, and completion is hardest in the final third. Tempo is integer-resolution because the feed records whole seconds.

Transitions1 section

Transitions — attacking & defensive

The question
When Hamburg win or lose the ball, what actually happens in the seconds after?

Reconstructed from the full timestamped event stream: real possession spells (not zone-clustered), and shots that follow a regain within a fixed window. This phase of play needs ordered, per-event timestamps — which every match here carries.

Direct play share16%
#14 of 18 · reaches final third in ≤3 passes
Patient build-up share23%
#12 of 18 · spells of 6+ passes
Tempo (possession length)17.5s
#10 of 18 · shorter = faster tempo
Passes per possession4.1
#13 of 18
Counter-attack shots /game1.32
#6 of 18 · shot within 12s of a regain in own half
Press→shot /game2.44
#18 of 18 · shot within 8s of a high regain
Speed to final third after regain13.8s
#16 of 18 · lower = faster break

Sequence success — attacking transition

7attacking transition sequences this season
29%succeed — produce a shot
0%turned over with nothing to show

Sequence success — defensive transition

39defensive transition sequences this season
51%succeed — reach the next third or a shot
13%turned over with nothing to show
Vision AI Model Insight
Hamburg are balanced between tempo and patience: 16% of possessions reach the final third in 3 passes or fewer (#14 of 18), against 23% built patiently over 6+ passes (#12 of 18). Winning the ball back leads to a shot inside 12 seconds 1.32 times a game (#6), and a high regain converts to a shot within 8 seconds 2.44 times a game (#18 of 18) — not yet a major source of chances.
Defending the box2 sections

Vulnerability Map — how opponents hurt them

The report flipped: where do opponents create their threat against Hamburg? 402 opponent progressive passes and 131 shots faced (12.5 xG against) across the season.

Opponent threat by lane (attacking into Hamburg)

Right wing
28%
Right half-space
14%
Central
17%
Left half-space
11%
Left wing
29%
Where the danger came from. Opponents generated most of their threat through the left wing (29% of the danger conceded).

How Do They Concede?

The question
Where do the goals against Hamburg actually come from — open play, dead balls, and who supplies them?

Every goal Hamburg conceded across the loaded matches — the opponent's shots in Hamburg's own matches — plus every individual opponent key pass faced, each drawn as its own real arrow (not zone-clustered) with the % share of each zone behind it.

Where the goals go in

← opponent shot at own goal

Every opponent key pass against them (96 total)

2%1%3%5%3%3%18%21%18%15%11%Tjark SchellerRaphael ObermairJano ter HorstTom BaackRaphael ObermairLaurin CurdaFelix GötzeGiannis KonstanteliasKonstantinos KaretsasJobe BellinghamJulian RyersonKonstantinos KaretsasGiannis KonstanteliasMaximilian BeierKonstantinos KaretsasMaximilian BeierSerhou GuirassyLaurin CurdaRayan PhilippeRaphael ObermairFelix GötzeJobe BellinghamSerhou GuirassyJobe BellinghamPhillip TietzStefan PoschNadiem AmiriLee Jae-SungKaishu SanoAlexander SchwolowKaishu SanoSheraldo BeckerLee Jae-SungSheraldo BeckerPhillipp MweneNadiem AmiriNadiem AmiriPhillip TietzLee Jae-SungPhillipp MweneAssan OuédraogoNeil El AynaouiEzechiel BanzuziDavid RaumAssan OuédraogoAntonio NusaDavid RaumTidiam GomisDavid RaumBrajan GrudaDavid RaumAntonio NusaOzan KabakAdam DaghimLeon AvdullahuVladimír CoufalVladimír CoufalBambasé ContéVladimír CoufalFisnik AsllaniFisnik AsllaniVladimír CoufalAdam DaghimLeon AvdullahuEzechiel BanzuziLinton MainaLinton MainaLuka LochoshviliGideon MensahGideon MensahThijs DallingaSaïd El MalaLinton MainaTom KraußÍsak JóhannessonTom KraußEllyes SkhiriJamie LewelingJamie LewelingBilal El KhannoussBilal El KhannoussBilal El KhannoussAtakan KarazorJamie LewelingBilal El KhannoussBilal El KhannoussRamon HendriksAngelo StillerAtakan KarazorRamon HendriksAngelo StillerChris FührichGrischa PrömelLeo SauerChris FührichDzenan Pejcinovic← own goal

By situation

Open play
15 · 100%
Set pieces
0 · 0%
Penalties
0 · 0%
Vision AI Model Insight
15 goals conceded. 100% come in open play; set pieces account for only 0%, so dead-ball defending is not the main issue. 7% are headers — aerial defending is not where the damage comes from. Their supply line runs mainly through the right half-space of the attacking third (21% of key passes faced) — that is the zone to shut off.
Context

Shape and tactics

Set pieces, strengths and weaknesses, and who they resemble.

Premium
Tactical Phase Read
The tactical idea behind each phase of this team's play, written from the same numbers shown above — what they do in build-up, how they progress, where they create, and how they defend it.
Subscribe →

Set-Piece Threat

How much of the goal threat is manufactured from dead balls — a route to goal that bypasses their open-play mechanism entirely.

Open play
4 g · 4.5 xG
Set pieces
2 g · 1.4 xG
Penalties
0 g
33% of goals come from set pieces (2 of 6), worth 1.4 xG from 19 shots. A genuine set-piece weapon — defend the box seriously.

Where do Hamburg's corners go?

26 corners taken this season, split by which flag they were taken from — arrows from the flag, dots at the delivery point, shaded by % of that side's corners landing in each zone (same treatment as the concede map below). No swing-direction (inswinger/outswinger) data is recorded here, only a start and end point per pass, which cannot show how the ball curved — so this shows what is genuinely knowable: where it lands, and short vs actually delivered. Tap or hover a dot for who took it and the match; filter to one match below and the shading recomputes for just that game.

Right side (13)

8%8%31%15%8%31%
Delivered into the box 100%Short 0%

Left side (13)

15%15%15%8%31%15%
Delivered into the box 100%Short 0%

Where opponents attack Hamburg from set pieces

21 shots from opponent corners against Hamburg, 0 conceded, split by the flag the corner came from — arrows from the flag, dots where the shot was taken (gold = goal), shaded by the % of that flag's shots in each zone. Tap or hover a shot for who took it, the minute and the match; filter to one match and the shading recomputes for just that game.

Right flag (9)

22%22%33%11%11%
Shot 9Goals 0

Left flag (12)

8%25%33%17%8%8%
Shot 12Goals 0

Tactical Strengths & Weaknesses

Strengths (top-third vs league)
  • none stand out
Weaknesses (bottom-third vs league)
  • xG created /game — 0.84 (0th pct)
  • field tilt % — 34.65 (0th pct)
  • box entries /game — 9.29 (0th pct)
  • threat created /game — 8.80 (6th pct)
  • pass retention % — 75.66 (11th pct)

Style Archetype & Similar Teams

Team archetype: Direct / counter high-press. Their closest stylistic matches in the league (cosine similarity on style metrics) — sides that play a similar way.

Union Berlin
88%
Elversberg
79%
Schalke
77%
Paderborn
71%
Borussia Monchengladba
55%

Performance vs Opponent Styles

The question
Not just how Hamburg results against a high press or a low block — how does their own play actually change?

Every match split into three tiers by how hard that specific opponent pressed (opponent PPDA — lower means a more aggressive press), matching Hamburg's own passing behaviour to the result.

Results

opponent typegoals for/ggoals against/gpoints/g
vs high-pressing opponents (2m)1.501.501.50
vs mid-block opponents (2m)1.500.503.00
vs low-block opponents (3m)0.004.000.00

Behaviour — how Hamburg actually play against each

opponent typeretentiondirectness (long balls)prog. passes/gxT/gbox entries/g
vs high-pressing opponents68%21%358.38.5
vs mid-block opponents74%18%387.610.5
vs low-block opponents80%11%499.99.0
Vision AI Model Insight
Facing a high press, retention drops to 68% vs 80% against a low block (12pt lower under pressure), and directness (long-ball share) sits at 21% when pressed vs 11% against a low block — a real style switch: they go noticeably more direct when pressed rather than trying to play through it.

Scouting Summary — the team in brief

In brief. Hamburg are territorially-dominated with a aggressive high-press. Their attack creates 0.84 xG a game and they concede 1.78 a game. [Event-data based — no tracking, so off-ball structure and marking scheme need video.]
Squad

Players

Who drives the numbers.

On-Ball Value — who moved the game

Every pass, carry, take-on, shot and ball win is worth the change it made to the chance of scoring minus the chance of conceding in the next 10 seconds. This is Hamburg’s last 7 matches added up: where the value came from, who produced it, and the six biggest single moves. OBV only measures what a player does with the ball: it shows who added the most on-ball value, not who was the most important player (defending off the ball, positioning and pressing are not in it).

+9.2on-ball value, 7 matches
Where the value came from
Passes2634 actions+3.77
Carries491 actions+0.33
Dribbles83 actions+0.42
Shots75 actions+2.62
Ball wins412 actions+2.05
Most on-ball value (OBV)ActionsOBVper 100
Daniel Heuer Fernandes371+1.00+0.27
Albert Grønbæk207+0.94+0.46
David Møller Wolfe234+0.92+0.39
Yussuf Poulsen87+0.91+1.04
Fábio Vieira163+0.80+0.49
Nicolás Capaldo307+0.74+0.24
Terem Moffi49+0.64+1.31
Nicolai Remberg248+0.56+0.22
123456
Biggest single movesOBV
1  Yussuf Poulsen · shot+0.391
2  Terem Moffi · shot+0.343
3  Yussuf Poulsen · take-on+0.281
4  Sebastiaan Bornauw · pass+0.275
5  Fábio Vieira · shot+0.227
6  Sebastiaan Bornauw · pass+0.197

Set Pieces by Player

Who delivers Hamburg’s dead balls and who finishes them this season. 26 corners taken, most by Albert Grønbæk (10); 19 shots from corners and free kicks, 2 goals, led by Nicolás Capaldo (1 goals, 0.49 xG). “Into the box” counts corners that landed inside the penalty area; free-kick takers are the players who shot from one, because this feed does not mark who delivers the others.

PlayerCorners takenInto the boxSet-piece shotsGoalsxGFree-kick shotsPenalties
Fábio Vieira66 (100%)5—0.444—
Albert Grønbæk109 (90%)1—0.021—
Sebastiaan Bornauw——3—0.16——
Nicolás Capaldo——310.49——
Miro Muheim54 (80%)110.03——
David Møller Wolfe32 (67%)1—0.06——
Bilal Nadir——1—0.031—
Zakaria El Ouahdi——1—0.04——
Patson Daka——1—0.04——
Yussuf Poulsen——1—0.06——
Louis Lemke——1—0.04——
Albert Sambi Lokonga11 (100%)——0.00——
Kofi Amoako10 (0%)——0.00——

Top Performers

Ranked by Vision AI Score — the same tactical behavioural evaluation each player's own report page shows (min 189 minutes). Coloured chips are that player's strongest capability blocks.

playerposminVision AI Scorecapability blocks
Daniel Heuer FernandesGK6535.5Shot-Stopping 55%
David Møller WolfeCM5343.1Progression 35%Successful Dribble 32%Chance Creation 31%Ball-Carrying 25%
Nicolás CapaldoCB5593.0Ball-Winning 64%Progression 32%Ball-Carrying 21%Aerial & Box Defending 4%
Sebastiaan BornauwCB4682.5Ball-Winning 42%Aerial & Box Defending 36%Progression 14%Ball-Carrying 8%

Top Creators

Chance creation leaders — key passes /90 and box entries.

playerposminkey P /90box entriesxT
Albert GrønbækM3851.64124.4
Miro MuheimM2183.7252.0
David Møller WolfeM5340.6785.8
Albert Sambi LokongaM3591.2564.6
Fábio VieiraM3440.7841.7
Martin AdelineM3600.7542.9
Patson DakaM2111.7130.8
Nicolás CapaldoD5590.4844.4

Wide Delivery Leaders

Crosses and cutbacks — wingers and full-backs only (by real average position, not the raw D/M position code), ranked by combined volume.

playerposmincrosses (completed)cutbacks (completed)
Otto StangeW21901 (0%)

Defensive Volume Leaders

Who does the defensive work — tackles, interceptions, recoveries.

playerposmindef actionstacklesinterceptrecoveries
Nicolás CapaldoD559165181436
Sebastiaan BornauwD46810141010
Warmed OmariD395794914
Martin AdelineM3607913425
David Møller WolfeM534783419
Jordan TorunarighaD31171369
Nicolai RembergM411665519
Albert GrønbækM385638212

Full Squad Data

Every player with 100+ minutes (21 players).

playerposappsmingoalsxGkey PprogdefxT
Daniel Heuer FernandesG765300.01501410.8
Nicolás CapaldoD655910.73271654.4
David Møller WolfeM653400.4437785.8
Sebastiaan BornauwD546800.20111013.4
Nicolai RembergM541100.2111663.0
Warmed OmariD539500.0210793.4
Albert GrønbækM638500.1724634.4
Zakaria El OuahdiM536600.2214552.6
Martin AdelineM636000.0313792.9
Albert Sambi LokongaM535900.1519554.6
Fábio VieiraM634400.9310441.7
Jordan TorunarighaD431100.0010712.7
Terem MoffiF726910.712290.7
Yussuf PoulsenF626821.225621.2
Louis LemkeM526500.0110391.3
Otto StangeF621900.103460.7
Miro MuheimM321820.199322.0
Shafiq NandjaD321300.005451.6
Patson DakaM421100.841340.8
Bilal NadirM421100.119452.0
Bakery JattaM310200.0012181.2

Player Role Architecture

The question
Who does what — and what tactical job does each key player actually perform?

The nine most-used players (450+ minutes), each with the role their event fingerprint points to — not just their listed position.

Daniel Heuer Fernandes
Goalkeeper · Goalkeeper
minutes653
goals · xG0 · 0.0
prog passes /906.9
key passes /900.14
def actions /901.9
pass accuracy70%
Nicolás Capaldo
Stopper / marker · Defender
minutes559
goals · xG1 · 0.7
prog passes /904.3
key passes /900.48
def actions /9026.6
pass accuracy69%
David Møller Wolfe
Deep-lying playmaker · Midfielder
minutes534
goals · xG0 · 0.4
prog passes /906.2
key passes /900.67
def actions /9013.1
pass accuracy64%
Sebastiaan Bornauw
Stopper / marker · Defender
minutes468
goals · xG0 · 0.2
prog passes /902.1
key passes /900.00
def actions /9019.4
pass accuracy80%
Nicolai Remberg
Ball-winner / destroyer · Midfielder
minutes411
goals · xG0 · 0.2
prog passes /902.4
key passes /900.22
def actions /9014.5
pass accuracy90%
Warmed Omari
Stopper / marker · Defender
minutes395
goals · xG0 · 0.0
prog passes /902.3
key passes /900.46
def actions /9018.0
pass accuracy84%
Albert Grønbæk
Advanced creator · Attacking mid
minutes385
goals · xG0 · 0.1
prog passes /905.6
key passes /901.64
def actions /9014.7
pass accuracy71%
Zakaria El Ouahdi
Ball-winner / destroyer · Midfielder
minutes366
goals · xG0 · 0.2
prog passes /903.4
key passes /900.49
def actions /9013.5
pass accuracy73%
Martin Adeline
Ball-winner / destroyer · Midfielder
minutes360
goals · xG0 · 0.0
prog passes /903.2
key passes /900.75
def actions /9019.8
pass accuracy77%

Recruitment Intelligence — profiles to sign

The question
If you were sporting director, which player profiles would move the needle most?

Each recruitment target is derived directly from the team's weakest areas vs the league — the gap, why it shows in the data, and the profile that closes it.

Need — bottom-third: xG created /game (0th pct)
Sign a higher-volume goalscorer or chance creator. The data flags this because the attack under-produces xG (0.84, 0th percentile vs the league).
Need — bottom-third: field tilt % (0th pct)
Sign a possession-controlling midfielder to win the territorial battle. The data flags this because they get pinned back (34.65, 0th percentile vs the league).
Need — bottom-third: box entries /game (0th pct)
Sign a penetrative wide player or runner to create box entries. The data flags this because few entries into the box (9.29, 0th percentile vs the league).
Vision AI · building report