Appian

Appian agents act in real systems. Agents "perform actions such as routing cases, updating records, or starting processes" through tools; process models configured as tools create or update records through a Write Records node; the Query Records tool reads synced record types; and "AI agents can also use external tools hosted on MCP servers". The platform and pricing pages list 200+ prebuilt connectors, REST and SOAP, and ODBC, JDBC and message queue integration, with Snowflake and Kafka on Advanced and Premium. Process models, expression rules and other agents serve as custom tools.

Query Records is read only and does not apply record security expressions; writes go through process models.

Sourcedocs.appian.com 26.8 create-and-configure-ai-agent, ai-agent-reference; readread 2026-09-17

Appian combines deterministic process steps with agent steps. "Process agents run inside a process model using the Execute AI Agent smart service", where the agent interprets the prompt, selects tools and executes each step.

The configuration guide says: "Keep deterministic or rule-based logic (such as conditional flows, validations, or calculations) inside the process model itself, and let the AI agent handle only the reasoning or decision steps." Process models serve as agent tools, and "agents can be added directly as tools" for multi agent collaboration up to two levels deep. A flow can therefore sequence, branch, retry and route around autonomous agent steps, and agents are versioned.

Sourcedocs.appian.com 26.8 agent-studio, create-and-configure-ai-agent, ai-agent-reference; readread 2026-09-17

Appian agents ground on a maintained, queryable copy of the customer's data. Agents query record data with the Query Records tool, which can join across related record types, over synced record types: Appian's data fabric keeps a synchronized copy of source data that stays queryable, so new knowledge is available without retraining. Agents also connect to enterprise data and documents, using document resources to retrieve context and AI DocCenter models for trained extraction, and the same SQL API infrastructure backs the data fabric tools on the Appian MCP Server.

Unsynced and legacy record types, smart search and record security expressions are not available to the Query Records tool.

Sourcedocs.appian.com 26.8 ai-agent-reference, create-and-configure-ai-agent; readread 2026-09-17

Oversight comes from the process around each agent. Process agents run as one step inside a process model, and the documentation tells designers to keep conditional flows and validations in the process and let the agent handle only the reasoning or decision step.

The human task, review and escalation nodes of the surrounding process then decide what happens to the agent's output, so approvals can be placed at the node level around any agent step.

The AI Agents overview names "combining AI reasoning with optional human oversight" as a core use, agents fail to start when the person starting them lacks access to a required tool, and Appian's AI agents page describes actions and escalations to people managed in the same workflow.

No approval tool specific to agents, and no per action approval setting, is documented; the gate is the process design.

Sourcedocs.appian.com 26.8 agent-studio, create-and-configure-ai-agent; readread 2026-09-17

Access controls apply to every agent action, and the attestations are deep. The 26.8 AI Agent Reference says "when an AI agent invokes a tool, user access determines whether the process continues or stops", that an agent "fails to start if the initiator doesn't have access to required tools", and that a sub agent "must respect all access controls defined for that sub-agent". Chat sessions are scoped to the user who started them.

Appian Government Cloud holds FedRAMP High and a DoD Impact Level 5 provisional authorization; Appian Cloud holds FedRAMP Moderate; and Appian is SOC 1, SOC 2, SOC 3, ISO 27001 and HITRUST CSF certified, per its trust center and Government Cloud documentation. Appian's private AI commitment is never to train on customer data.

Sourcedocs.appian.com 26.8 ai-agent-reference; appian.com/support/resources/trust/compliance; readread 2026-09-17

A buyer can inspect each agent run after the fact, step by step. In the 26.8 Monitor AI Agents documentation, "the run history uses a timeline layout that displays each step chronologically, including tool calls, AI agent reasoning, and outputs".

A Monitor view logs every agent request with run ID, agent version, status, request, AI actions consumed, tool call count, initiator, duration and start time, per agent and across agents, and active runs can be stopped.

The AI Agent Reference adds system level audit logs for AI agent executions, which track all AI interactions and can optionally capture prompts and responses, separate from the runtime traces.

Feedback and LLM grading serve testing, and Process HQ process mining looks at processes rather than agents.

Sourcedocs.appian.com 26.8 monitor-ai-agents, ai-agent-reference; readread 2026-09-17

Chat agents keep a documented memory with a stated scope and lifetime. In the 26.8 documentation, "conversation persistence stores chat interactions between an end user and a chat agent across sessions".

Each conversation is stored as a session tied to a specific user and chat agent; users can return to and switch between earlier sessions without losing context, and the agent keeps prior messages within a session.

Scope is a single user (other users cannot view, access or share another user's sessions), conversations are retained for audit purposes and end users cannot clear them, and sessions are tied to the environment where they were created.

Users cannot delete their history, process agents carry no memory beyond the process, and learning agents have been announced but not shipped. Process and case state is the application's data, not agent memory.

Sourcedocs.appian.com 26.8 conversation-persistence-chat-agents; readread 2026-09-17

Appian runs in several named environments. Appian Cloud is managed SaaS across multiple cloud regions. Appian Government Cloud runs in an AWS GovCloud virtual private cloud with full commercial feature parity, including AI. Customers can also self manage on Kubernetes (with RPA included from release 24.2), deploy hybrid on AWS, Azure or Google, or run on premises.

Agent Studio is included in the Advanced and Premium tiers, and agent availability on self managed installs is not confirmed. The region count has been reported as 24.

Sourcedocs.appian.com 26.5 appian-government-cloud-overview; appian.com/products/pricing; read 7 August 2026, datedread 2026-09-17

Packaged assets are ready for a customer to adopt. AI skills come as packaged automation for defined work (classification, extraction and summarization), alongside packaged industry solutions and an application template library, and the 26.8 documentation adds AI DocCenter extraction and classification models that agents call through a process model. Each works on its own when adopted.

No catalog of prebuilt AI agents, as distinct from skills and solutions, is documented. Appian's promise of a first application in eight weeks is a services commitment rather than a packaged asset.

Sourceappian.com/products/platform/artificial-intelligence (read 7 August 2026); docs.appian.com 26.8 create-and-configure-ai-agent; datedread 2026-09-17

Work reaches Appian agents without a person starting it. Process agents run as a step inside a process model through the Execute AI Agent smart service, so they start whenever the process does, and the AI Agents overview says agents "trigger workflows automatically" and are used to automate case triage. The pricing entitlements list consuming events from external Apache Kafka topics on Advanced and Premium as a way to start a process, so an outside event can reach an agent with nobody asking. Chat agents respond when an end user messages them.

The agent pages do not describe process start events such as timers, record events or messages, and the agent summary table's Initiator field shows that runs started by people are common.

Sourcedocs.appian.com 26.8 agent-studio; appian.com/products/pricing (read 7 August 2026); readread 2026-09-17

Designers choose the model for each agent. "AI agents use the model configured in the Model Selection section of the Advanced tab." By default new agents use Auto, "which uses the latest model from the configured provider with automatic fallback", and designers "can also select a specific model or route execution through your own provider account". Per agent selection and a bring your own provider account put the choice with the customer.

Which models and providers sit on that list is not stated in the agent configuration guide. Appian's commitment not to train on customer data is a security point rather than model choice.

Sourcedocs.appian.com 26.8 create-and-configure-ai-agent; readread 2026-09-17

Outside agents and systems can call Appian, and Appian agents can call out. The Appian 26.8 AI Agent Reference names the Appian MCP Server, whose data fabric tools share the agents' SQL API infrastructure, so outside agents can reach Appian. The Appian World 2026 release describes organizations administering their own Appian MCP servers so third party agents reach Appian business rules, processes and data, alongside Appian's REST and SOAP web APIs. Appian's own agents also consume external MCP tools, so MCP runs in both directions.

Appian also makes a broader claim, Composer, an MCP representation of the entire application estate.

Sourcedocs.appian.com 26.8 ai-agent-reference; Appian World 2026 release (read 7 August 2026); datedread 2026-09-17

Evaluation covers agents before and after deployment. Agents are tested in a test pane (process agents) or a chat test experience before deployment, and the AI Agent Reference lists three feedback sources for both agent types: developer feedback at design time in the test pane, an automated LLM grader, and dev and ops feedback in production, with chat agents appearing in the same quality metrics as process agents. The AI Agents overview lists "test and monitor other AI agents to ensure reliable performance" as a supported use, and agents are versioned.

No test suites built on fixed datasets are documented.

Sourcedocs.appian.com 26.8 ai-agent-reference, agent-studio, monitor-ai-agents; readread 2026-09-17

Real application interfaces are controlled through Appian RPA. RPA is a licensed part of the platform, sold by bot count per tier and available to self managed Kubernetes customers from release 24.2, and Appian RPA bots operate the interfaces of applications that expose no programmatic route, per the pricing and Government Cloud parity pages. These are deterministic bots operating application screens, so how often they break when an interface changes is a live question for any bot estate.

The agent tool list in the 26.8 documentation (process models, expression rules, other agents, system tools and external MCP tools) includes no computer use tool, so an AI agent choosing and driving a session itself is not documented.

Sourceappian.com/products/pricing, /industries/public-sector/appian-government-cloud (read 7 August 2026); docs.appian.com 26.8 create-and-configure-ai-agent; datedread 2026-09-17