Protocol engineering is the application of systematic methods to the development of communication protocols. It uses many of the principles of software engineering, but it is specific to the development of distributed systems. == History == When the first experimental and commercial computer networks were developed in the 1970s, the concept of protocols was not yet well developed. These were the first distributed systems. In the context of the newly adopted layered protocol architecture (see OSI model), the definition of the protocol of a specific layer should be such that any entity implementing that specification in one computer would be compatible with any other computer containing an entity implementing the same specification, and their interactions should be such that the desired communication service would be obtained. On the other hand, the protocol specification should be abstract enough to allow different choices for the implementation on different computers. It was recognized that a precise specification of the expected service provided by the given layer was important. It is important for the verification of the protocol, which should demonstrate that the communication service is provided if both protocol entities implement the protocol specification correctly. This principle was later followed during the standardization of the OSI protocol stack, in particular for the transport layer. It was also recognized that some kind of formalized protocol specification would be useful for the verification of the protocol and for developing implementations, as well as test cases for checking the conformance of an implementation against the specification. While initially mainly finite-state machine were used as (simplified) models of a protocol entity, in the 1980s three formal specification languages were standardized, two by ISO and one by ITU. The latter, called SDL, was later used in industry and has been merged with UML state machines. == Principles == The following are the most important principles for the development of protocols: Layered architecture: A protocol layer at the level n consists of two (or more) entities that have a service interface through which the service of the layer is provided to the users of the protocol, and which uses the service provided by a local entity of level (n-1). The service specification of a layer describes, in an abstract and global view, the behavior of the layer as visible at the service interfaces of the layer. The protocol specification defines the requirements that should be satisfied by each entity implementation. Protocol verification consists of showing that two (or more) entities satisfying the protocol specification will provide at their service interfaces the specified service of that layer. The (verified) protocol specification is used mainly for the following two activities: The development of an entity implementation. Note that the abstract properties of the service interface are defined by the service specification (and also used by the protocol specification), but the detailed nature of the interface can be chosen during the implementation process, separately for each entity. Test suite development for conformance testing. Protocol conformance testing checks that a given entity implementation conforms to the protocol specification. The conformance test cases are developed based on the protocol specification and are applicable to all entity implementations. Therefore standard conformance test suites have been developed for certain protocol standards. == Methods and tools == Tools for the activities of protocol verification, entity implementation and test suite development can be developed when the protocol specification is written in a formalized language which can be understood by the tool. As mentioned, formal specification languages have been proposed for protocol specification, and the first methods and tools where based on finite-state machine models. Reachability analysis was proposed to understand all possible behaviors of a distributed system, which is essential for protocol verification. This was later complemented with model checking. However, finite-state descriptions are not powerful enough to describe constraints between message parameters and the local variables in the entities. Such constraints can be described by the standardized formal specification languages mentioned above, for which powerful tools have been developed. It is in the field of protocol engineering that model-based development was used very early. These methods and tools have later been used for software engineering as well as hardware design, especially for distributed and real-time systems. On the other hand, many methods and tools developed in the more general context of software engineering can also be used of the development of protocols, for instance model checking for protocol verification, and agile methods for entity implementations. == Constructive methods for protocol design == Most protocols are designed by human intuition and discussions during the standardization process. However, some methods have been proposed for using constructive methods possibly supported by tools to automatically derive protocols that satisfy certain properties. The following are a few examples: Semi-automatic protocol synthesis: The user defines all message sending actions of the entities, and the tool derives all necessary reception actions (even if several messages are in transit). Synchronizing protocol: The state transitions of one protocol entity are given by the user, and the method derives the behavior of the other entity such that it remains in states that correspond to the former entity. Protocol derived from service specification: The service specification is given by the user and the method derives a suitable protocol for all entities. Protocol for control applications: The specification of one entity (called the plant - which must be controlled) is given, and the method derives a specification of the other entity such that certain fail states of the plant are never reached and certain given properties of the plant's service interactions are satisfied. This is a case of supervisory control. == Books == Ming T. Liu, Protocol Engineering, Advances in Computers, Volume 29, 1989, Pages 79–195. G.J. Holzmann, Design and Validation of Computer Protocols, Prentice Hall, 1991. H. König, Protocol Engineering, Springer, 2012. M. Popovic, Communication Protocol Engineering, CRC Press, 2nd Ed. 2018. P. Venkataram, S.S. Manvi, B.S. Babu, Communication Protocol Engineering, 2014.
Vision transformer
A vision transformer (ViT) is a transformer designed for computer vision. A ViT decomposes an input image into a series of patches (rather than text into tokens), serializes each patch into a vector, and maps it to a smaller dimension with a single matrix multiplication. These vector embeddings are then processed by a transformer encoder as if they were token embeddings. ViTs were designed as alternatives to convolutional neural networks (CNNs) in computer vision applications. They have different inductive biases, training stability, and data efficiency. Compared to CNNs, ViTs are less data efficient, but have higher capacity. Some of the largest modern computer vision models are ViTs, such as one with 22B parameters. Subsequent to its publication, many variants were proposed, with hybrid architectures with both features of ViTs and CNNs. ViTs have found application in image recognition, image segmentation, weather prediction, and autonomous driving. == History == Transformers were introduced in Attention Is All You Need (2017), and have found widespread use in natural language processing. A 2019 paper applied ideas from the Transformer to computer vision. Specifically, they started with a ResNet, a standard convolutional neural network used for computer vision, and replaced all convolutional kernels by the self-attention mechanism found in a Transformer. It resulted in superior performance. However, it is not a Vision Transformer. In 2020, an encoder-only Transformer was adapted for computer vision, yielding the ViT, which reached state of the art in image classification, overcoming the previous dominance of CNN. The masked autoencoder (2022) extended ViT to work with unsupervised training. The vision transformer and the masked autoencoder, in turn, stimulated new developments in convolutional neural networks. Subsequently, there was cross-fertilization between the previous CNN approach and the ViT approach. In 2021, some important variants of the Vision Transformers were proposed. These variants are mainly intended to be more efficient, more accurate or better suited to a specific domain. Two studies improved efficiency and robustness of ViT by adding a CNN as a preprocessor. The Swin Transformer achieved state-of-the-art results on some object detection datasets such as COCO, by using convolution-like sliding windows of attention mechanism, and the pyramid process in classical computer vision. == Overview == The basic architecture, used by the original 2020 paper, is as follows. In summary, it is a BERT-like encoder-only Transformer. The input image is of type R H × W × C {\displaystyle \mathbb {R} ^{H\times W\times C}} , where H , W , C {\displaystyle H,W,C} are height, width, channel (RGB). It is then split into square-shaped patches of type R P × P × C {\displaystyle \mathbb {R} ^{P\times P\times C}} . For each patch, the patch is pushed through a linear operator, to obtain a vector ("patch embedding"). The position of the patch is also transformed into a vector by "position encoding" (the paper tried no embedding, 1D embedding, 2D embedding, and relative embedding: 1D was adopted). The two vectors are added, then pushed through several Transformer encoders. The attention mechanism in a ViT repeatedly transforms representation vectors of image patches, incorporating more and more semantic relations between image patches in an image. This is analogous to how in natural language processing, as representation vectors flow through a transformer, they incorporate more and more semantic relations between words, from syntax to semantics. The above architecture turns an image into a sequence of vector representations. To use these for downstream applications, an additional head needs to be trained to interpret them. For example, to use it for classification, one can add a shallow MLP on top of it that outputs a probability distribution over classes. The original paper uses a linear-GeLU-linear-softmax network. == Variants == === Original ViT === The original ViT was an encoder-only Transformer supervise-trained to predict the image label from the patches of the image. As in the case of BERT, it uses a special token
Spectral shape analysis
Spectral shape analysis relies on the spectrum (eigenvalues and/or eigenfunctions) of the Laplace–Beltrami operator to compare and analyze geometric shapes. Since the spectrum of the Laplace–Beltrami operator is invariant under isometries, it is well suited for the analysis or retrieval of non-rigid shapes, i.e. bendable objects such as humans, animals, plants, etc. == Laplace == The Laplace–Beltrami operator is involved in many important differential equations, such as the heat equation and the wave equation. It can be defined on a Riemannian manifold as the divergence of the gradient of a real-valued function f: Δ f := div grad f . {\displaystyle \Delta f:=\operatorname {div} \operatorname {grad} f.} Its spectral components can be computed by solving the Helmholtz equation (or Laplacian eigenvalue problem): Δ φ i + λ i φ i = 0. {\displaystyle \Delta \varphi _{i}+\lambda _{i}\varphi _{i}=0.} The solutions are the eigenfunctions φ i {\displaystyle \varphi _{i}} (modes) and corresponding eigenvalues λ i {\displaystyle \lambda _{i}} , representing a diverging sequence of positive real numbers. The first eigenvalue is zero for closed domains or when using the Neumann boundary condition. For some shapes, the spectrum can be computed analytically (e.g. rectangle, flat torus, cylinder, disk or sphere). For the sphere, for example, the eigenfunctions are the spherical harmonics. The most important properties of the eigenvalues and eigenfunctions are that they are isometry invariants. In other words, if the shape is not stretched (e.g. a sheet of paper bent into the third dimension), the spectral values will not change. Bendable objects, like animals, plants and humans, can move into different body postures with only minimal stretching at the joints. The resulting shapes are called near-isometric and can be compared using spectral shape analysis. == Discretizations == Geometric shapes are often represented as 2D curved surfaces, 2D surface meshes (usually triangle meshes) or 3D solid objects (e.g. using voxels or tetrahedra meshes). The Helmholtz equation can be solved for all these cases. If a boundary exists, e.g. a square, or the volume of any 3D geometric shape, boundary conditions need to be specified. Several discretizations of the Laplace operator exist (see Discrete Laplace operator) for the different types of geometry representations. Many of these operators do not approximate well the underlying continuous operator. == Spectral shape descriptors == === ShapeDNA and its variants === The ShapeDNA is one of the first spectral shape descriptors. It is the normalized beginning sequence of the eigenvalues of the Laplace–Beltrami operator. Its main advantages are the simple representation (a vector of numbers) and comparison, scale invariance, and in spite of its simplicity a very good performance for shape retrieval of non-rigid shapes. Competitors of shapeDNA include singular values of Geodesic Distance Matrix (SD-GDM) and Reduced BiHarmonic Distance Matrix (R-BiHDM). However, the eigenvalues are global descriptors, therefore the shapeDNA and other global spectral descriptors cannot be used for local or partial shape analysis. === Global point signature (GPS) === The global point signature at a point x {\displaystyle x} is a vector of scaled eigenfunctions of the Laplace–Beltrami operator computed at x {\displaystyle x} (i.e. the spectral embedding of the shape). The GPS is a global feature in the sense that it cannot be used for partial shape matching. === Heat kernel signature (HKS) === The heat kernel signature makes use of the eigen-decomposition of the heat kernel: h t ( x , y ) = ∑ i = 0 ∞ exp ( − λ i t ) φ i ( x ) φ i ( y ) . {\displaystyle h_{t}(x,y)=\sum _{i=0}^{\infty }\exp(-\lambda _{i}t)\varphi _{i}(x)\varphi _{i}(y).} For each point on the surface the diagonal of the heat kernel h t ( x , x ) {\displaystyle h_{t}(x,x)} is sampled at specific time values t j {\displaystyle t_{j}} and yields a local signature that can also be used for partial matching or symmetry detection. === Wave kernel signature (WKS) === The WKS follows a similar idea to the HKS, replacing the heat equation with the Schrödinger wave equation. === Improved wave kernel signature (IWKS) === The IWKS improves the WKS for non-rigid shape retrieval by introducing a new scaling function to the eigenvalues and aggregating a new curvature term. === Spectral graph wavelet signature (SGWS) === SGWS is a local descriptor that is not only isometric invariant, but also compact, easy to compute and combines the advantages of both band-pass and low-pass filters. An important facet of SGWS is the ability to combine the advantages of WKS and HKS into a single signature, while allowing a multiresolution representation of shapes. == Spectral Matching == The spectral decomposition of the graph Laplacian associated with complex shapes (see Discrete Laplace operator) provides eigenfunctions (modes) which are invariant to isometries. Each vertex on the shape could be uniquely represented with a combinations of the eigenmodal values at each point, sometimes called spectral coordinates: s ( x ) = ( φ 1 ( x ) , φ 2 ( x ) , … , φ N ( x ) ) for vertex x . {\displaystyle s(x)=(\varphi _{1}(x),\varphi _{2}(x),\ldots ,\varphi _{N}(x)){\text{ for vertex }}x.} Spectral matching consists of establishing the point correspondences by pairing vertices on different shapes that have the most similar spectral coordinates. Early work focused on sparse correspondences for stereoscopy. Computational efficiency now enables dense correspondences on full meshes, for instance between cortical surfaces. Spectral matching could also be used for complex non-rigid image registration, which is notably difficult when images have very large deformations. Such image registration methods based on spectral eigenmodal values indeed capture global shape characteristics, and contrast with conventional non-rigid image registration methods which are often based on local shape characteristics (e.g., image gradients).
Digital art
Digital art, or the digital arts, is artistic work that uses digital technology as part of the creative or presentational process. It can also refer to computational art that uses and engages with digital media. Since the 1960s, various names have been used to describe digital art, including computer art, electronic art, multimedia art, and new media art. Digital art includes pieces stored on physical media, such as with digital painting, as well as digital galleries on websites. Digital art also extends to the field of visual computing. == History == In the early 1960s, John Whitney developed the first computer-generated art using mathematical operations. In 1963, Ivan Sutherland invented the first user interactive computer-graphics interface known as Sketchpad. Between 1974 and 1977, Salvador Dalí created two big canvases of Gala Contemplating the Mediterranean Sea which at a distance of 20 meters is transformed into the portrait of Abraham Lincoln (Homage to Rothko) and prints of Lincoln in Dalivision based on a portrait of Abraham Lincoln processed on a computer by Leon Harmon published in "The Recognition of Faces". The technique is similar to what later became known as photographic mosaics. Andy Warhol created digital art using an Amiga where the computer was publicly introduced at the Lincoln Center in July 1985. An image of Debbie Harry was captured in monochrome from a video camera and digitized into a graphics program called ProPaint. Warhol manipulated the image by adding color using flood fills. == Art made for digital media == Artwork that is highly computational, presented through digital media, and explicitly engages with digital technologies are categorized as "art made for digital media". This differs from art using digital tools, which incorporate digital technology in the creation process but may exist outside the digital world. Digital art historian Christiane Paul writes that it "is highly problematic to classify all art that makes use of digital technologies somewhere in its production and dissemination process as digital art since it makes it almost impossible to arrive at any unifying statement about the art form". == Art that uses digital tools == Digital art can be purely computer-generated (such as fractals and algorithmic art) or taken from other sources, such as a scanned photograph or an image drawn using vector graphics software using a mouse or graphics tablet. Artworks are considered digital paintings when created similarly to non-digital paintings but using software on a computer platform and digitally outputting the resulting image as painted on canvas. Despite differing viewpoints on digital technology's impact on the arts, a consensus exists within the digital art community about its significant contribution to expanding the creative domain, i.e., that it has greatly broadened the creative opportunities available to professional and non-professional artists alike. == Art theorists and art historians == Notable art theorists and historians in this field include: Oliver Grau, Jon Ippolito, Christiane Paul, Frank Popper, Jasia Reichardt, Mario Costa, Christine Buci-Glucksmann, Dominique Moulon, Roy Ascott, Catherine Perret, Margot Lovejoy, Edmond Couchot, Tina Rivers Ryan, Fred Forest and Edward A. Shanken. === Digital painting === Digital painting is either a physical painting made with the use of digital electronics and spray paint robotics within the digital art fine art context or pictorial art imagery made with pixels on a computer screen that mimics artworks from the traditional histories of painting and illustration. === Artificial intelligence art === Artists have used artificial intelligence to create artwork since at least the 1960s. Since their design in 2014, some artists have created artwork using a generative adversarial network (GAN), which is a machine learning framework that allows two "algorithms" to compete with each other and iterate. It can be used to generate pictures that have visual effects similar to traditional fine art. The essential idea of image generators is that people can use text descriptions to let AI convert their text into visual picture content. Anyone can turn their language into a painting through a picture generator. == Digital art education == Digital art education has become more common with the advancement of digital hardware and software. From hardware such as graphics tablets, styluses, tablets, 3D scanners, virtual reality headsets, and digital cameras; to software such as digital art software, 3D modeling software, 3D rendering, digital sculpting, 2D graphics software, digital painting, 3D terrain generation, 2D animation software, 3D animation software, raster graphics editors, vector graphics editors, mathematical art software, and video editing software. == Scholarship and archives == In addition to the creation of original art, research methods that utilize AI have been generated to quantitatively analyze digital art collections. This has been made possible due to the large-scale digitization of artwork in the past few decades. Although the main goal of digitization was to allow for accessibility and exploration of these collections, the use of AI in analyzing them has brought about new research perspectives. Two computational methods, close reading and distant viewing, are the typical approaches used to analyze digitized art. Close reading focuses on specific visual aspects of one piece. Some tasks performed by machines in close reading methods include computational artist authentication and analysis of brushstrokes or texture properties. In contrast, through distant viewing methods, the similarity across an entire collection for a specific feature can be statistically visualized. Common tasks relating to this method include automatic classification, object detection, multimodal tasks, knowledge discovery in art history, and computational aesthetics. Whereas distant viewing includes the analysis of large collections, close reading involves one piece of artwork. Whilst 2D and 3D digital art is beneficial as it allows the preservation of history that would otherwise have been destroyed by events like natural disasters and war, there is the issue of who should own these 3D scans – i.e., who should own the digital copyrights. === Computer demos === Computer demos are based on computer programs, usually non-interactive. It produces audiovisual presentations. They are a novel form of art, which emerged as a consequence of the home computer revolution in the early 1980s. In the classification of digital art, they can be best described as real-time procedurally generated animated audio-visuals. This form of art does not concentrate only on the aesthetics of the final presentation, but also on the complexities and skills involved in creating the presentation. As such, it can be fully enjoyed only by persons with a relatively high knowledge level of relevant computer technologies. An example is that, as said by Hua Jin and Jie Yang, Using computer-aided design software to present the class content in art design teaching," is not to advocate computer-aided design instead of hand-drawn performance, but to make it serve the profession earlier through a more reasonable course arrangement." On the other hand, many of the created pieces of art are primarily aesthetic or amusing, and those can be enjoyed by the general public. === Digital installation art === Digital installation art constitutes a broad field of artistic practices and a variety of forms. Some resemble video installations, especially large-scale works involving projections and live video capture. By using projection techniques that enhance an audience's impression of sensory envelopment, many digital installations attempt to create immersive environments. While others go even further and attempt to facilitate a complete immersion in virtual realms. This type of installation is generally site-specific, scalable, and without fixed dimensionality, meaning it can be reconfigured to accommodate different presentation spaces. Scott Snibbe's "Boundary Functions" is an example of augmented reality digital installation art, which responds to people who enter the installation by drawing lines between people, indicating their personal space.Noah Wardrip-Fruin's "Screen"(2003) utilizes a Cave Automatic Virtual Environment (CAVE) to create an interactive, text-based digital experience that engages the viewer in a multi-sensory interaction. === Internet art and net.art === Internet art is digital art that uses the specific characteristics of the Internet and is exhibited on the Internet. The term "internet art" is included by "net art" for which artists assume that network will be refreshed through history. So the term "post-internet art" is used to exclude artworks outside of the internet media. A representative example is Protocols for Achievements, which is a digital photo frame that confronts the aestheti
Metigo
metigo is a software application that performs image-based modelling and close range photogrammetry. It produces rectified imagery plans, true ortho-projections on planar, cylindric and conic surfaces, 3D photorealistic models, measurements from photography and mappings on a photographic base for uses in the cultural heritage sector, mainly conservation. == Products == The metigo product line currently consists of the mapping software metigo MAP, the stereo-photogrammetry modeling software metigo 3D, the free viewer metigo VIEW. These products are all standalone and are not depending on other software, such as AutoCAD. === metigo MAP === metigo MAP is mainly used to map findings and conservation measured on a uniform metric photographic base. Therefore, photos of planar surfaces can be rectified based on geometrical informations, e.g. height and width of a rectangle, or cartesian coordinates measured by total station. Beside rectified imagery several other metric mapping bases can be imported and used: true ortho-projections; scaled scans of plans and plots; CAD-files; 3D models, such as digital surface models (DSM) produced by stereo-photogrammetry, SfM or 3D scanning. metigo MAP 's strong point is that rectified imagery taken with different techniques (visual light, sided light, IR, UV, UV-fluorescence, X-ray), historic images and photos taken at various stages of the conservation process can be superimposed and evaluated mutually. The user can allocate several attributes, such as different conservation measures and damage classes, to the mapped geometries. The mappings can be analysed by geometries as well as by user-defined attributes at any stage of the project. metigo MAP targets mainly conservators in different cultural heritage fields. Using it no specialist knowledge of surveying and photogrammetric techniques are needed. === metigo 3D === metigo 3D is a stereo-photogrammetric kit that allows to calculate bundle adjustments (axios3D), create high-quality 3D point clouds using multiple stereo photo pairs combined with metric survey data, mesh these point clouds, texture the meshes with high-resolution image data to create photo-realistic models, ortho-project orientated images on digital surface models (DSM) on planes and best-fit cylinders and cones, create unwrappings and developed views of curved surfaces, analyse deformations of 3D surfaces. metigo 3D targets metric survey specialists working in the cultural heritage sector. == Supported file formats == metigo has the ability to read the following formats: images: JPEG (.jpg), Tiff (.tif), Bitmaps (.bmp), CompuServ (.gif), Encapsualated Postscript (.eps), PCX (.pcx), Photo-CD (.pcd), PICT (.pcd), PNG (.png), Targa (.tga), RAW-format of several camera brands. CAD: DBX, DXF, DWG. 3D: many ASCII-formats (.stl, .wrl, etc.) point data: format editor for ASCII files. == Supported languages == Currently, an English and German version of the software is supported. For metigo MAP beside these a French and Polish GUI is offered for sale. == Applications == The main applications of metigo are: conservation in the cultural heritage context, e.g. stone conservation paintings tapestry etc. architecture, archaeology, many other are possible, e.g. forensics. == History == The first public release of metigo was in 2000.
AI agent
In the context of generative artificial intelligence, AI agents (also referred to as compound AI systems or agentic AI) are a class of intelligent agents that can pursue goals, use tools, and take actions with varying degrees of autonomy. In practice, they usually operate within human-defined objectives, constraints, and available tools. == Overview == AI agents possess several key attributes, including goal-directed behavior, natural language interfaces, the capacity to use external tools, and the ability to perform multi-step tasks. Their control flow is frequently driven by large language models (LLMs). Agent systems may also include memory components, planning logic, tool interfaces, and orchestration software for coordinating agent components. AI agents do not have a standard definition. NIST describes agentic AI as an emerging area requiring standards for secure operation, interoperability, and reliable interaction with external systems. A common application of AI agents is task automation: for example, booking travel plans based on a user's prompted request. Companies such as Google, Microsoft and Amazon Web Services have offered platforms for deploying pre-built AI agents. Several protocols have been proposed for standardizing inter-agent communication, with examples including the Model Context Protocol, Gibberlink, and many others. Some of these protocols are also used for connecting agents to external applications. In December 2025, Linux Foundation announced the formation of the Agentic AI Foundation (AAIF), with the goal of ensuring agentic AI evolves transparently and collaboratively. == History == AI agents have been traced back to research from the 1990s, with Harvard professor Milind Tambe noting that the definition of an AI agent was not clear at the time. Researcher Andrew Ng has been credited with spreading the term "agentic" to a wider audience in 2024. == Training and testing == Researchers have attempted to build world models and reinforcement learning environments to train or evaluate AI agents. For example, video games such as Minecraft and No Man's Sky as well as replicas of company websites, have also been used for training such agents. == Autonomous capabilities == The Financial Times compared the autonomy of AI agents to the SAE classification of self-driving cars, likening most applications to level 2 or level 3, with some achieving level 4 in highly specialized circumstances, and level 5 being theoretical. == Cognitive architecture == The following are some internal design options for reasoning within an agent: Retrieval-augmented generation ReAct (Reason + Act) pattern is an iterative process in which an AI agent alternates between reasoning and taking actions, receives observations from the environment or external tools, and integrates these observations into subsequent reasoning steps. Reflexion, which uses an LLM to create feedback on the agent's plan of action and stores that feedback in a memory cache. A tool/agent registry, for organizing software functions or other agents that the agent can use. One-shot model querying, which queries the model once to create the plan of action. === Reference architecture === Ken Huang proposed an AI agent reference architecture, which consists of seven interconnected layers, with each layer building on the functionality of the layers beneath it: Layer 1: Foundation models - provide the core AI engines to power agent capabilities. Layer 2: Data operations - manage the complex data infrastructure required for AI agent operations, including Vector database, data loaders, RAG. Layer 3: Agent frameworks - sophisticated software and tools that simplify the development and management of the AI agents. Layer 4: Deployment and infrastructure - provide the robust technical foundation for running AI agents. Layer 5: Evaluation and observability - focus on assessing the safety and performance of AI agents. Layer 6: Security and compliance - a crucial protective framework ensuring AI agents operate safely, securely, and conform to regulatory boundaries. At this layer security and compliance features embedded into all the AI agent stack layers are integrated together. Layer 7: Agent ecosystem - represents the AI agents' interface with real-world applications and users. == Orchestration patterns == To execute complex tasks, autonomous agents are often integrated with other agents or specialized tools. These configurations, known as orchestration patterns or workflows, include the following: Prompt chaining: A sequence where the output of one step serves as the input for the next. Routing: The classification of an input to direct it to a specialized downstream task or tool. Parallelization: The simultaneous execution of multiple tasks. Sequential processing: A fixed, linear progression of tasks through a predefined pipeline. Planner-critic: An iterative pattern where one agent generates a proposal and another evaluates it to provide feedback for refinement. == Multimodal AI agents == In addition to large language models (LLMs), vision-language models (VLMs) and multimodal foundation models can be used as the basis for agents. In September 2024, Allen Institute for AI released an open-source vision-language model. Nvidia released a framework for developers to use VLMs, LLMs and retrieval-augmented generation for building AI agents that can analyze images and videos, including video search and video summarization. Microsoft released a multimodal agent model – trained on images, video, software user interface interactions, and robotics data – that the company claimed can manipulate software and robots. == Applications == As of April 2025, per the Associated Press, there are few real-world applications of AI agents. As of June 2025, per Fortune, many companies are primarily experimenting with AI agents. The Information divided AI agents into seven archetypes: business-task agents, for acting within enterprise software; conversational agents, which act as chatbots for customer support; research agents, for querying and analyzing information (such as OpenAI Deep Research); analytics agents, for analyzing data to create reports; software developer or coding agents (such as Cursor); domain-specific agents, which include specific subject matter knowledge; and web browser agents (such as OpenAI Operator). By mid-2025, AI agents have been used in video game development, gambling (including sports betting), cryptocurrency wallets (including cryptocurrency trading and meme coins) and social media. In August 2025, New York Magazine described software development as the most definitive use case of AI agents. Likewise, by October 2025, noting a decline in expectations, The Information noted AI coding agents and customer support as the primary use cases by businesses. In November 2025, The Wall Street Journal reported that few companies that deployed AI agents have received a return on investment. === Applications in government === Several government bodies in the United States and United Kingdom have deployed or announced the deployment of agents, at the local and national level. The city of Kyle, Texas deployed an AI agent from Salesforce in March 2025 for 311 customer service. In November 2025, the Internal Revenue Service stated that it would use Agentforce, AI agents from Salesforce, for the Office of Chief Counsel, Taxpayer Advocate Services and the Office of Appeals. That same month, Staffordshire Police announced that they would trial Agentforce agents for handling non-emergency 101 calls in the United Kingdom starting in 2026. In December 2025, the Department of Neighborhoods in Detroit, Michigan, in partnership with a local business, deployed a pilot project in two Detroit districts for an AI agent to be used for customer service calls. In February 2025, Thomas Shedd, the director of the Technology Transformation Services, proposed using AI coding agents across the United States federal government. A recruiter for the Department of Government Efficiency proposed in April 2025 to use AI agents to automate the work of about 70,000 United States federal government employees, as part of a startup with funding from OpenAI and a partnership agreement with Palantir. This proposal was criticized by experts for its impracticality, if not impossibility, and the lack of corresponding widespread adoption by businesses. In December 2025, the Food and Drug Administration announced that it would offer "agentic AI capabilities" to its staff for "meeting management, pre-market reviews, review validation, post-market surveillance, inspections and compliance and administrative functions." That same month, the United States Department of Defense launched GenAI.mil, an internal platform for American military personnel to use generative AI-based applications based on Google Gemini, including "intelligent agentic workflows". Defense Secretary Pete Hegseth listed applications such as "[conducting] deep r
Eaze
Eaze is an American company based in San Francisco, California that launched a medical cannabis delivery app of the same name in 2014. == History == Eaze was launched in 2014 by Keith McCarty to deliver medical marijuana to patients in California. McCarty started the company in his San Francisco apartment with four employees. The company provides a mobile app to connect users with cannabis dispensaries, but does not grow or sell marijuana itself, and has been nicknamed “the Uber of Weed”. As of 2017, the company operates in more than 100 cities within California. In 2017, Eaze reported 300 percent growth over the previous year. It has 81 employees, and performs 120,000 deliveries per month to 250,000 users. A survey of Eaze users revealed that 66% are male, 57% are between 22 and 34, just over half have a bachelor's degree, and 49% have an annual income over $75,000. The company's vaporizer cartridge sales reached $1 million in sales in 4 months, and 31% of customers had ordered a vaporizer by the end of 2016. In 2016, Eaze founder Keith McCarty stepped down from his position as CEO and was replaced by Jim Patterson, who served as the company's chief product and technology officer. == EazeMD == EazeMD is a service that helps people acquire a medical marijuana card. It is a California-based telemedicine service in which physicians assess patients through an online video chat. It is California's largest telemedicine service for marijuana referrals. In June 2017, a former employee of one of these physicians accessed patient data in the physician's records system, causing a security breach. However, there was no evidence that Eaze data was accessed. == Eaze Insights == Eaze Insights conducts surveys of their users and compiles data into reports on cannabis use. Statistics from their reports have been cited in Seattle Weekly, Forbes, The Huffington Post, Business Insider, Fortune, and other general interest publications. == Financing == The company announced its $10 million Series A funding in April 2015 by multiple venture capital firms, including the Snoop Dogg-backed Casa Verde Capital. In October 2016, Eaze announced its series B funding in the amount of $13 million from five investors, making the company "the highest-funded startup in the history of the cannabis industry, as well as its fastest-growing one". In September 2017, the company raised another $27 million in venture funding. The Series B funding was led by Bailey Capital, joined by DCM Ventures, Kaya Ventures, and FJ Labs. According to the company' officials in 2017, Eaze managed to raise more than $52 million since its inception in 2014.