BASKETBALL AI
Welcome Readers,
This edition, we focus on the the use of AI for selecting the NBA Draft top prospects best fit for teams and why humans still need to play a role.
We will explore how coaches can use AI in the off season for self improvement and provide guidance on how any coaching staff can implement an NBA level rookie onboarding workflow on a high school budget using AI tools.
In this issue:
NBA Top Draft Picks: AI Fit
How Coaches Can Use AI for Off Season Self Improvement
NBA Level Rookie Onboarding on a High School Budget
The Jokić and Reaves Paradox: Over Reliance on AI
Let’g Go
NBA DRAFT
☑ NBA Top Draft Picks: AI Fit
Overview: The NBA Draft is here. A "consensus tier" has formed among major draft media outlets (including ESPN, CBS Sports, The Athletic, and Yahoo Sports). While the top four picks have solidified into a nearly universal order, a bit of late breaking movement and high upside workouts have introduced some fresh intrigue at the number five spot.
Here is the current projected top 5 based on the latest consensus media reports and the analytical logic driving each match.
1. Washington Wizards: AJ Dybantsa (Wing, BYU)
Consensus Across: ESPN, CBS Sports, The Athletic, NBADraft.net
A dynamic 6-foot-9, 217-pound wing who led college basketball in scoring. He possesses elite shot creation ability, high end vertical athleticism, and an NBA ready frame that allows him to absorb contact on drives.
The Wizards have kept their cards close to their vest, but draft intelligence indicates that Dybantsa’s physical and statistical profile perfectly matches Washington's long term timeline.
AI Driven Analysis Fit
Advanced spatial tracking software isolates Dybantsa's scoring efficiency independent of BYU's offensive system. Data reveals elite separation metrics meaning his footwork and change of pace generate clean look windows regardless of how tightly he’s guarded.
Predictive modeling ranks Dybantsa as the highest ceiling three level shot creator in this class, capable of generating separation against isolated NBA defenses.
Draft algorithms heavily weight "initiator wings" (e.g., Jayson Tatum) due to their historic value in building deep playoff rosters. Dybantsa hits premium thresholds for usage rate matched with physical length.
2. Utah Jazz: Darryn Peterson (Guard, Kansas)
Consensus Across: ESPN, The Athletic, NBADraft.net (Note: Some outlets like SI lean Cameron Boozer here, but Peterson is the dominant mock trend)
AI Driven Analysis Fit
There is significant pre-draft smoke around Peterson, who reportedly held an exclusive workout for Washington trying to claim the top spot. However, the Jazz are widely expected to snag him at No. 2, completely comfortable picking an elite talent even without an individual workout (similar to their selection of Ace Bailey last year).
A highly polished 6-foot-5 scoring guard. At Kansas, he excelled as a movement shooter and secondary off-ball weapon, though his high school tape proves he possesses immense on-ball creation juice.
Advanced lineup simulators show Peterson as a flawless mechanical partner for Keyonte George. While his role at Kansas was more conservative, machine learning models that weight his high school isolation tracking alongside his collegiate catch and shoot numbers project an elite, multi-dimensional combo guard.
Multi-Dimensional Synergy. AI tracking showcases Peterson’s elite close out attacking and rapid processing speeds. The data projects him not just as a standard shooting guard, but as a dynamic combo guard capable of switching seamlessly between playing on or off the ball.
3. Memphis Grizzlies: Cameron Boozer (Forward, Duke)
Consensus Across: ESPN, CBS Sports, The Athletic, NBADraft.net
AI Driven Analytics Fit
The consensus pairing between Memphis and Boozer has been rock solid. He is widely considered the safest, highest floor prospect in the top tier.
An incredibly skilled, high feel 6-foot-9 power forward. Boozer led the NCAA in Box Plus-Minus (17.1) as a freshman, offering elite rebounding, precise secondary playmaking, and a reliable three-point shot.
Boozer is an analytical model’s dream. Predictive linear regressions that evaluate historical front court prospects flag Boozer as an outlier due to his unique blend of elite defensive rebounding and soft perimeter shooting (41% on catch-and-shoot three-pointers).
Roster architecture simulations show him acting as a high IQ connective piece that seamlessly bridges the spacing gap between Ja Morant's paint penetration and Jaren Jackson Jr.'s rim protection.
4. Chicago Bulls: Caleb Wilson (Forward, North Carolina)
Consensus Across: ESPN, CBS Sports, The Athletic, NBADraft.net
AI Driven Analytics Fit
The top four picks are viewed as a distinct tier in this draft, and Chicago is in a position where their internal data modeling dictates taking the absolute best player available. That player is unanimously projected to be Wilson.
A versatile 6-foot-10 forward with an elite wingspan, Wilson is a high motor defender capable of guarding multiple positions while providing vertical spacing and face up utility on offense.
Defensive evaluation algorithms look heavily at "event rates" such as the statistical frequency of deflections, blocks, steals, and successful shot contests. Wilson’s elite lateral quickness metrics for a 6-foot-10 forward put him in a rare tier.
Computer-vision tracking shows him as a highly versatile defensive weapon who can recover ground quickly out of drop coverages and fluidly switch onto smaller ball handlers in pick-and-roll schemes.
5. LA Clippers: Keaton Wagler (Guard, Illinois) or Mikel Brown Jr. (Guard, Louisville) or Darius Acuff (Guard, Arkansas)
The Media Split: CBS Sports and NBADraft.net project Keaton Wagler; Sports Illustrated and certain CBS sub-reports favor Mikel Brown Jr.
AI Driven Analytics Fit
The Clippers acquired this pick via a deadline trade, and the number five spot is where the consensus groupthink of the draft officially fractures.
The Keaton Wagler Analytical Edge: Wagler was the definitive outlier star of the NBA Draft Combine in Chicago. When a prospect’s raw biometric data, lane agility, and vertical leap test significantly higher than their seasonal media ranking, front office algorithms trigger an automatic "buy signal." His spatial tracking data maps out a lightning fast catch and shoot release (39.7% from deep), projecting massive structural floor gravity to open up driving lanes for the Clippers' veteran playmakers.
The Mikel Brown Jr. Analytical Edge: If the Clippers pivot to Brown, it's driven by pure transition optimization data. Brown's tracking metrics profile him as an elite push ahead passer who consistently forces defenses into scrambled cross-matches.
The Darius Acuff Analytical Edge: If the Clippers pass on Keaton Wagler or Mikel Brown Jr., Acuff offers a higher developmental ceiling as a potential true franchise standard bearer. His elite ability to create offense matches the Clippers projected needs. He validated his shooting stroke at the collegiate level, converting 44% of his three-point attempts on high volume. NBA defensive models simulate significant floor spacing gravity derived from his quick catch-and-shoot release.
Why It Matters: While the media consensus has locked in on the top four names, league executives note that behind closed doors, master draft boards are rarely finalized until 24 hours before the event. With significant trade rumors swirling around teams like Milwaukee and Brooklyn, the tail end of the lottery remains highly volatile.
COACH IMPROVEMENT
💭 How Coaches Can Use AI for Off Season Self Improvement
Overview: While summer is the prime window for player development, the best coaches use the off season to upgrade their own tactical and leadership skills. Traditionally, professional growth meant traveling to coaching clinics or endlessly reviewing old game tape. Today, generative AI tools such as ChatGPT, Gemini and Claude allow coaches to turn an LLM (Large Language Model) into a personal "Chief of Staff" to audit their performance, stress test their philosophies, and enter next season sharper than before.
The Details: Coaches can leverage conversational AI for immediate professional development through three high yield off season workflows:
The System Audit: Upload your playbook or a standard two hour practice plan from last season. Prompt the AI: "Analyze this practice plan for efficiency. Identify potential bottlenecks where players stand around too long, and suggest modifications to increase conditioning and repetitions."
Tactical Stress Testing: Force yourself out of confirmation bias by using AI to play devil's advocate. If you run a specific system like a Pack-Line defense or a 5-Out Continuity offense, prompt the AI: "Act as an elite offensive coordinator. What spacing alignments and quick-hitter plays best exploit the systemic weaknesses of my defense? Tell me exactly how you would attack it."
Communication Role Playing: Simulate difficult conversations before they happen. You can practice off season role playing with the AI to refine your delivery when delivering tough news, such as discussing a reduced role with a returning player or navigating an awkward conversation with a parent.
Why It Matters: Coaching can be an isolating profession. Honest objective feedback is incredibly hard to find. Using AI as a collaborative sounding board allows you to systematically dismantle your own biases and structural inefficiencies from the comfort of your couch. By treating your own coaching development with the same urgency you apply to player workouts, you ensure your program takes a massive strategic leap forward long before training camp tips off.
ROOKIE ONBOARDING
💻 NBA Level Rookie Onboarding on a High School Budget
Overview: The massive, three inch paper playbook is officially dead. NBA front offices use automated workflows and computer vision to onboard rookies. AI driven systems ingest thousands of hours of tape, instantly indexing every pick-and-roll or defensive rotation the rookie executed in college, and deliver bite sized video playlists straight to the player's smartphone.
While you might not have an NBA franchise's custom tech budget, any coaching staff can replicate this elite onboarding workflow using free or low cost consumer AI tools this off season.
The Details - Workflow Breakdown: Replicating this process comes down to three simple, automated steps:
The Content Feed: Instead of long film sessions, record 60 second screen shares of your playbook using tools like Descript. Focus on one specific concept per video, such as "Handling Drop Coverage."
The AI Translation Layer: Take your raw coaching thoughts or the video's transcript and drop them into a generative AI tool like ChatGPT or Claude. Use this prompt: "Act as a player development coach. Translate these tactical notes into three scannable, high-impact bullet points written for a 19-year-old athlete."
The Delivery & Accountability: Push the video and the AI generated summary directly to your players via your existing team messaging apps. To ensure retention, create a quick, weekly 3-question video quiz using Google Forms. Embed a 5-second clip, pause it, and ask: "What is your coverage rule here?"
Why It Matters: Gen-Z athletes process information through short form, mobile first content. By shifting from dense playbooks to automated, bite sized mobile learning, you meet your players exactly where they are.
Streamlining this mental preparation during the summer ensures your incoming players report to training camp with a high basketball IQ, maximizing your actual on court practice time when the season begins.
NBA DRAFT
❌ The Jokić and Reaves Paradox: Over Reliance on AI
Overview: What players will drop in the draft or will be totally missed on because of the over reliance on AI?
AI models train on historical data, which can bias them toward established archetypes of success. Basketball is defined by improvisational creativity, elite spatial awareness, and raw grit which are traits that are difficult to quantify. Over relying on predictive algorithms can cause teams to completely miss out on "unquantifiable anomalies" like Nikola Jokić, who famously slipped to the 41st pick because traditional and early analytical metrics failed to project his unique style of play.
Details: Early tracking data labeled Jokics’ slow foot speed and low vertical leap as disqualifying athletic outliers. Similarly, Jimmy Butler's lack of an elite perimeter shot coming out of Marquette and Jalen Brunson’s "undersized and ground bound" physical profile caused algorithmic projections to flag them as low probability NBA prospects.
AI models measure standard physical metrics perfectly, but they fail to quantify cognitive processing speed, situational spatial awareness and elite functional coordination.
More Recent Examples of Overlooked Stars:
Tyrese Haliburton (Drafted 12th, 2020): Haliburton slid outside the top 10 largely because tracking models and shooting datasets flagged his highly unconventional, "broken" shooting form as an unsustainable outlier for the NBA level. Algorithms struggled to separate mechanics from his elite, fast processing cognitive vision and processing speed under pressure.
Austin Reaves (Undrafted, 2021): Reaves completely cleared the algorithmic filter. On paper, a older, 23 year old guard with limited vertical explosiveness and low defensive lateral quickness scores poorly in predictive athletic models. What data couldn't measure was his elite functional coordination, deceleration capacity, and situational basketball IQ.
Alperen Şengün (Drafted 16th, 2021): Similar to the Jokić profile, Şengün’s traditional athletic testing metrics (vertical pop, straight-line speed) were mediocre. Automated visual tracking platforms in Europe often flagged his defensive footwork as a major liability. However, models missed his rare spatial intuition, processing speed, and elite elite hand-eye coordination.
The Hybrid Solution: Marrying Data with Instinct
To avoid missing on these hidden gems, front offices are shifting away from using AI as a final decision maker, moving instead toward a hybrid scouting architecture.
AI as the Macro Filter: Teams use machine learning models to parse massive, global datasets. AI is perfect for flagging baseline efficiency baselines, tracking medical durability indicators, and weeding out prospects who fall completely below mandatory physical or behavioral thresholds.
Human Scouts as the Micro Evaluator: Once the data limits the field, human scouts step in to analyze what data cannot see: how a player processes instructions during a timeout, locker room maturity, competitive grit under distress, and how they improvise when a play breaks down.
Feedback Loops: When an anomaly like Brunson or Jokić succeeds, teams must feed that tape back into the machine to teach the algorithm why it was wrong, adjusting weights on factors like spatial anticipation versus raw vertical leap.
Why It Matters: Front offices cannot rely on a single source of truth. The future belongs to a hybrid scouting architecture. Teams must use algorithmic AI as a high throughput filter to flag baseline efficiency, medical durability, and physical capacity. However, they must empower traditional human scouts to evaluate the "unquantifiable anomalies". By marrying data science with the nuance of human intuition, organizations avoid can avoid algorithmic blindness that may miss the next transcendent superstar.
🛠 Tools Spotlight:
Tools mentioned in this edition:
Descript - AI editing for every kind of video.
SportsVisio - AI-powered stat-tracking & Video highlights.
Basketball AI - Free website access to guides, tools, research, and more!
📰 Everything Else in Basketball AI:
On Democratizing AI Technology:
SportsVisio / Grassroots Basketball Media:
"Today you point a phone at the court, hit record, and an AI hands you a full box score and a highlight reel before the team finishes shaking hands... Computer vision models go to work frame by frame. They track the ball, recognize each player, and classify what is happening... Coaches stop spending Sunday night with a clipboard."
— NBA Guard Duncan Robinson added: "Quick access to stats and highlights is like having a coach and a video assistant in my pocket."
On Quantifying Context and "Invisible" Play:
Traditional basketball statistics capture what happened—points, rebounds, assists but miss the context that determines game outcomes. A missed shot that draws three defenders and creates an open corner three-pointer generates zero points for the passer in the box score yet fundamentally shifts win probability."
— Ian McKiernan, Senior Lead Product Manager of NBA Stats Platform & Operations, noted: “We all have seen game winners. But securing that defensive rebound when an offensive rebound gives the other team a chance to score—leverage is created in that boxout.”
📆 Upcoming Conferences, Events and Latest Guides:
June 9, 2026 Last issue of Basketball AI
Latest Basketball AI Guides:
Conferences:
NBA Summer League Tech Expo: Monday July 13, 2026
Tech event anchored directly within The NBA Summer League. 40+ technology companies showcasing cutting edge platforms.
Heavy presence of computer vision, automated tagging, predictive tracking, and generative scout reporting tools. It’s an interactive, booth style environment specifically designed for team decision makers looking to acquire new front office and player development tech.
That’s a wrap for this edition. The next newsletter will be published Tuesday July 7, 2026.
Tell us what you thought of today's newsletter to help us improve it for you.
Until next time, Terry and Dan