Serdar Gündoğdu

AI Learning System

Learn AI. Put it to work.

Explore a learning map from AI foundations and agents to digital twins and humanoid robots. Open an application, follow the connections, and put ideas into practice through experiments.

Pinch with two fingers to zoom. Drag to explore the enlarged map.

Connected applications and their sub-applications Eight stages connect foundations, runtime, agent systems, assurance, deployment, physical AI, industrial twins and embodied AI. Frames group GPU with POL and GEX; USL with ADP; LLM with TFL; HNS with ARL, DPL, CUL and AOS; CTX with MEM; WFM with WML; SWI with ANT and BEE; and ITL with PDT and DTR. The CTX/MEM group exchanges feedback with SEC and EVL. LCL and CLD share one frame, with their joint laboratory DCL below them. ENG and its sub-application HEX share a frame, with HEX below ENG. Arrows describe learning relationships, not runtime integrations. 01· FOUNDATION Ecosystem, compute, runtimeand adaptation foundations;explore programmingfoundations in POL andexperiment with GEX, TFL andADP. 02· RUNTIME Model runtime and servinglayer; support multipleproviders and hardwarebackends. 03· AGENT SYSTEM Agents reason, use context,tools and computerenvironments; turn researchinto open-source runtimes andreusable components. 04· CONTEXT & ASSURANCE Design context, memory,security and evaluationtogether for bounded,reviewable behavior. 05· DEPLOYMENT Local and cloud deploymentoptions; test workload,memory, privacy and costassumptions. 06· PHYSICAL AI World models and swarmintelligence; connect toindustrial twins and humanoidsystems. 07· INDUSTRIAL TWIN Digital twins and digitaltriplets for industrialsystems and real-worldresearch. 08· EMBODIED AI Humanoid and embodiedintelligence research. Opens in a new tab AIA AI ecosystem Opens in a new tab GPU GPU kernels Opens in a new tab POL Programming basics Opens in a new tab GEX Kernel execution Opens in a new tab USL Model adaptation Opens in a new tab ADP Model adaptation Opens in a new tab LLM Runtime · serving Opens in a new tab TFL Token serving Opens in a new tab HNS Harness engineering Opens in a new tab ARL Agent runtime Opens in a new tab DPL Decision plane Opens in a new tab CUL Computer use Opens in a new tab AOS Agent operating system Opens in a new tab CTX Context · knowledge Opens in a new tab MEM Agent memory Opens in a new tab SEC Trust · security Opens in a new tab EVL Evaluation Opens in a new tab LCL Local compute Opens in a new tab DCL Shared lab Opens in a new tab CLD Cloud deployment Opens in a new tab WFM World models Opens in a new tab WML World model laboratory Opens in a new tab SWI Swarm intelligence Opens in a new tab ANT Ant colony Opens in a new tab BEE Honey bee Opens in a new tab ITL Industrial twin lab Opens in a new tab PDT P-101 interactivedigital twin Opens in a new tab DTR Digital triplet Opens in a new tab ENG Humanoid engineering Opens in a new tab HEX Humanoid exploration ASERDARGUN.COM AI Learning System

What would you like to explore?

Start with a question. Take it further with an experiment.

Understand models

Explore how a request becomes tokens and how serving resources affect the wait.

LLM → TFL

Start with token flow

Explore agents

Inspect tool use, execution steps, and the points where an agent needs human approval.

HNS → ARL

Start with agent execution

Explore the physical world

Get to know pump components, then compare predictions and outcomes in a digital triplet.

PDT → DTR

Start with pump anatomy

Explore an idea. Run an experiment.

Six starting experiments. Pick a question, explore the variables, interpret the outcome.

Illustrations represent the topics. Experiments are educational; applications run independently.

Choose your next step.

Explore another application that sparks your curiosity.

View all applications