Autonom8 vs Camunda (2026)

Workflows reach outside systems through service tasks, which run JavaScript or TypeScript services, Java classes or expressions to call web services, APIs and databases as a step in the process. Credentials for those calls can sit in secure variables, and A8Flow has built in SMS providers, MSG91 and Prowtext, for one time passwords, password resets and task notices. Each integration is written as a custom service, with no catalog of ready connectors. Agent tools are still on the way, so an AI agent cannot call an outside system itself today.

Sourcedocs.autonom8.com studio services, service tasks and ai-agents, flow integrationread 2026-10-12

Agents act through the BPMN activities a builder places in an ad hoc sub process, so any service task, connector call or sub process becomes a tool the model can choose. Camunda offers more than 400 prebuilt connectors, including Salesforce, SAP OData and RFC, HubSpot, Slack, Microsoft Teams, GitHub, Twilio, WhatsApp, Google Drive and Sheets, Amazon S3, DynamoDB and Lambda, plus generic REST, SOAP, GraphQL and SQL. Credentials sit in secrets, a connector SDK builds custom connectors, and MCP client connectors let an agent discover and call tools on outside MCP servers.

Sourcedocs.camunda.io/docs/components/connectors/out-of-the-box-connectors/available-connectors-overviewread 2026-10-12

A8Studio builds each app around a BPMN journey with user, service, script, send, receive, manual and business rule tasks, so one process can run steps in sequence or in parallel across people, systems and AI agent steps. Assisted journeys have several actors working a case, such as loan origination, while Solo journeys let one customer complete a flow made of form, condition, timer, webhook and service nodes. Deployed apps run in the A8Flow runtime, which moves each instance through its steps and tracks it to completion, and A8Flow processes and Solo sessions can call each other.

Sourcedocs.autonom8.com studio journey, task types and solo nodes, autonom8.com a8flowread 2026-10-12

Processes run on the Zeebe engine as BPMN, with gateways, timers, events, sub processes and DMN decisions. An AI agent is an addressable loop inside that process. The model picks the next activity from an ad hoc sub process, the engine runs it as a governed step, and the result goes back to the model until the goal is met. Several agents can share one process, agents built in LangGraph, Amazon Bedrock or custom code can be connected and tracked as agent instances, and predictable steps run straight through while agents handle the judgment calls.

Sourcedocs.camunda.io/docs/components/agentic-orchestration/ai-agentsread 2026-10-12

Work reaches a running app on its own. A8Chat takes customer messages from channels such as Facebook Messenger through a webhook, and BPMN receive tasks hold a process until a message arrives from an outside system.

A webhook node hands a third party a callback address, then authenticates the caller, checks the incoming data and moves the journey on when the provider reports back, as with a payment or identity check. Server side functions can be exposed as endpoints that outside systems call, protected by an API key. Timer nodes pause a journey for anything from 30 seconds to 30 days, though nothing starts a new run on a schedule.

Sourcedocs.autonom8.com chat integration, solo webhook and timer nodes, receive tasks and expose endpointread 2026-10-12

Processes start or move on without anyone pressing a button. Inbound connectors listen on an HTTP webhook, Kafka, RabbitMQ, Amazon SQS and SNS, Amazon EventBridge, Slack, email, Microsoft 365 mail, GitHub and Twilio, and BPMN timer and message events start or resume instances on a schedule or when a message arrives. An MCP start event registers a deployed process as a tool that outside AI clients can call, and each call starts a new instance.

Sourcedocs.camunda.io/docs/components/connectors/out-of-the-box-connectors/available-connectors-overviewread 2026-10-12

Agents in A8Studio work from the instructions, variables and output fields set on each agent, with workflow data passed in when the agent runs. Knowledge bases for agents are still to come, so today an agent cannot search a company's own files or policies, and nothing ingests or indexes them for it. A8iQ studies operational data from running workflows to produce process metrics, and agents do not draw on it as company knowledge.

Sourcedocs.autonom8.com studio ai-agentsread 2026-10-12

Agents can draw on company knowledge kept in a vector store. The Vector Database connector splits documents into chunks, embeds them with Amazon Bedrock Titan, Azure OpenAI, Google Vertex AI or OpenAI models, and writes them to Amazon OpenSearch, OpenSearch, Elasticsearch, Azure AI Search or Azure Cosmos DB. At run time it retrieves the most relevant passages by semantic similarity, so an agent can look up policies and procedures, search a large product catalog, reuse answers to past support questions or quote the exact policy behind a decision. The store grows as new documents are embedded.

Sourcedocs.camunda.io/docs/components/agentic-orchestration/rag-ai-agentsread 2026-10-12

Long running workflows keep their state across channels and steps until they finish, and the variables on each assisted instance can be viewed, edited or deleted by users with the right permissions. The Export Application API returns those variables for instances started within a chosen window. Agents start each run from their instructions and the variables a workflow passes in, and keep nothing they can recall in a later, separate run.

Sourcedocs.autonom8.com flow history access control and export application api, autonom8.com a8flowread 2026-10-12

Each agent keeps a short term conversation inside its process instance, passing the last 20 messages to the model by default while always keeping the system prompt. Those messages can live in a process variable, in Camunda document storage with a time to live set to the process's expected lifetime, in Amazon Bedrock AgentCore Memory, or in a custom store on self managed setups. Recall from one process instance to the next relies on an outside service such as AgentCore Memory, which AWS runs.

Sourcedocs.camunda.io/docs/components/connectors/out-of-the-box-connectors/agentic-ai-aiagent-subprocessread 2026-10-12

People can be placed at any point in a process. When a journey reaches a user task, A8Flow creates a task and the instance waits until a person completes it, whether that means filling a form, checking data or signing off.

Tasks go to a named assignee, candidate users or candidate groups, show up in My Tasks and My Group Tasks lists, can be claimed or reassigned under permission rules, and can send SMS notices to the group. A8Chat pairs its chatbot with live chat support.

Review points are designed into each journey by its builder, and there is no separate setting that holds an AI agent's output for approval.

Sourcedocs.autonom8.com studio user tasks, flow tasks and group managementread 2026-10-12

People sit in the process as user tasks, and Tasklist shows each assigned task whether the step before it ran automatically or an AI agent produced the result a person now acts on. A user task can be one of an agent's tools, so the agent asks for help or sign off inside its loop. For MCP tools, a gateway in front of the client lets listing and read operations through and routes selected calls to a user task for confirmation before they run. Task work can also reach people in Microsoft Teams, and teams can build their own task apps on the API.

Sourcedocs.camunda.io/docs/components/connectors/out-of-the-box-connectors/agentic-ai-mcp-client-human-in-the-loopread 2026-10-12

Access is controlled at a fine grain. A8Flow signs users in through OpenID Connect single sign on, with an optional mixed mode that keeps passwords alongside it and a default group for first time users.

Authorization rules allow or deny each user or group specific actions on process definitions, instances, tasks, users and other resources, and A8Studio policies build custom roles with separate rights to edit AI agents, deploy live or export audit logs.

Secure variables are encrypted with AES 256 GCM, variable groups carry their own access lists, and audit logs are immutable and record the source IP of each request. The product docs show no SOC 2 report or ISO 27001 certificate behind these controls.

Sourcedocs.autonom8.com flow sso, authorization and audit logs, studio policy and secure variablesread 2026-10-12

Camunda runs two identity layers, the Orchestration Cluster admin for runtime work and the management identity for Hub and Optimize, and both connect to an outside OpenID Connect provider such as Entra ID for single sign on, with LDAP and Active Directory on the licensed editions. Authorizations, roles, groups, mapping rules and tenants decide who can start, see and change processes, tasks and other resources. The company holds SOC 2 Type II, ISO 27001 and TISAX and is listed with the Cloud Security Alliance on its trust center.

Sourcetrust.camunda.comread 2026-10-12

Each run can be traced afterward. The Solo history lists finished sessions as complete, expired, errored or timed out, and its timeline shows the exact path a session took, including the branch it followed at each condition. Assisted history covers running and completed instances and their variables.

The A8Flow audit log records every create, edit and delete on tasks, users, deployments and settings, tagged with the user, process instance, task and source IP. Application logs stream live during a session and are kept in the cloud for search and export through the a8flow command line tool. What an AI agent was prompted with and returned inside a step does not appear in these views.

Sourcedocs.autonom8.com solo history, flow audit logs, logs and cliread 2026-10-12

Operate shows each agent instance's state, such as thinking or calling a tool, its usage metrics and its conversation history grouped by loop iteration, including the tools it picked and the results it got back, for native and connected external agents alike. Health indicators and limit warnings flag an agent that keeps calling the same tool or nears its configured limits. Every process and decision instance can be inspected step by step, audit log APIs record user and user task actions, and Optimize builds reports, dashboards and KPI alerts.

Sourcedocs.camunda.io/docs/components/agentic-orchestration/evaluate-agents/monitor-ai-agentsread 2026-10-12

Workflows, forms and agents run on Autonom8's own cloud, deployed from A8Studio into A8Flow environments that an organization sets up with a runtime address and an API key. The rules engine is the exception. DMN Hub runs as a Docker container with its own Postgres and Redis on the customer's systems, so decision tables can be built, stored and evaluated in house while A8Flow calls them through its SDK. Workflows themselves have no region choice, private cloud or self hosted runtime.

Sourcedocs.autonom8.com dmnhub overview and install, studio environments and deploymentread 2026-10-12

SaaS customers choose the region for each cluster. On Google Cloud the choices include Belgium, London, Iowa, South Carolina, Montréal, Toronto, Singapore and Sydney, and on AWS they include Frankfurt, Paris, Ohio, Oregon, Virginia and Singapore, each paired with a secondary backup region. Enterprise customers can ask for custom regions. Self managed Camunda runs the whole stack on the customer's own infrastructure, and agent model calls can route through a private endpoint inside the customer's network.

Sourcedocs.camunda.io/docs/components/saas/regionsread 2026-10-12

Builders start from shared parts more than finished agents. The Prompt Gallery holds prebuilt prompts for common jobs that fill in an agent's instructions, and Generate Prompt turns a plain request into a structured one. A8Marketplace is a store of form widgets an organization installs, built with the create a8 component command line tool, and the A8Studio library carries flows, templates, components, services, integrations and themes. There is no catalog of ready made agents or journeys for a job such as loan origination or account opening.

Sourcedocs.autonom8.com studio ai-agents and marketplaceread 2026-10-12

Camunda Marketplace carries model blueprints and connectors from Camunda, partners and the community, installed straight into a Hub project or downloaded for the desktop modeler. AI agent blueprints such as AI Agent Chat Quick Start and AI Agent Chat With Tools run out of the box on the Camunda provided LLM in SaaS. Partner and community connectors sit outside Camunda's commercial support, and administrators of a self managed Hub can switch the Marketplace off.

Sourcedocs.camunda.io/docs/components/hub/workspace/modeler/modeling/camunda-marketplaceread 2026-10-12

The builder picks the model behind each agent from a configuration panel, choosing among Google Gemini (Gemini Pro, Gemini Flash), OpenAI (GPT 4, GPT 4o, GPT 4o mini) and Anthropic (Sonnet, Opus, Haiku) models, with guidance to weigh cost against capability. Temperature, output token limit (4,000 by default) and top p are set per agent, and output can be plain text or JSON with typed, required fields. TARS, the code helper inside A8Studio, runs on GPT 3.5 Turbo. There is no bring your own key option and no automatic routing or fallback between models.

Sourcedocs.autonom8.com studio ai-agents and tarsread 2026-10-12

The builder picks the provider and the backend for each agent. Anthropic Claude models run directly, through AWS Bedrock or through Microsoft Foundry, OpenAI models run directly, through Foundry or through any OpenAI compatible endpoint, and Google Gemini runs directly or through Google's Enterprise Agent Platform, with custom endpoints for private network setups and a custom provider on self managed installs. SaaS adds a Camunda provided LLM with a free budget for testing, so teams can switch between models such as Claude Sonnet 4.6 before moving to their own account.

Sourcedocs.camunda.io/docs/components/connectors/out-of-the-box-connectors/agentic-ai-aiagent-model-providersread 2026-10-12

Four APIs open the platform to code, each reached with a scoped API key that carries its own expiry date. The Deployment API pushes A8Studio apps into the A8Flow runtime, the Export Application API returns instance data and variables for any window up to 24 hours, the Start New Process API opens an assisted case remotely, and Check Dedupe tests for duplicate records. Android and iOS SDKs embed A8Flow in mobile apps, the a8flow command line tool handles sign in and logs, and services and functions are written in JavaScript or TypeScript against the A8Data, A8Config, A8Astro and A8Func SDKs.

Sourcedocs.autonom8.com flow api keys, export application api, sdks and cliread 2026-10-12

The Orchestration Cluster REST API drives processes, instances, user tasks, decisions, identities and audit logs, with SDKs for Java, TypeScript, Python, C# and PHP and the c8ctl command line tool. The Orchestration Cluster MCP Server opens operational work such as incidents, user tasks and process instances to AI clients under the same authentication and authorization model as the REST API. Older Operate and Tasklist REST APIs remain available for existing integrations.

Sourcedocs.camunda.io/docs/apis-tools/orchestration-cluster-api-mcp/orchestration-cluster-api-mcp-overviewread 2026-10-12

Tuning happens after launch. A8iQ tracks business metrics across activated workflows so teams can adapt each workflow to those metrics in a continuing loop, and flow mining shows key measures and bottlenecks for each flow and each version over a chosen period, so a new version can be compared with the last one in production. There is no test suite or quality gate that checks an AI agent's answers before a release.

Sourceautonom8.com a8iq, docs.autonom8.com flow miningread 2026-10-12

Camunda Process Test runs an agent process as an integration test, keeping the real model in the loop while mocking outside tool calls. Conditional behavior reacts to whichever tools the agent activates instead of one fixed order, and judge assertions send an output and a plain language expectation to a model that rates the match against a set threshold, alongside semantic similarity checks. Tests run through a Spring Boot starter inside the project's own build.

Sourcedocs.camunda.io/docs/components/agentic-orchestration/evaluate-agents/test-ai-agentsread 2026-10-12

Autonom8 connects to other systems through services, APIs and SMS providers, and its agents work on the data a workflow hands them. Scanner, selfie, signature and video KYC widgets collect documents and identity checks from customers inside the app's own forms. Nothing in the platform drives a browser, a desktop or another application's screen on a user's behalf.

Sourcedocs.autonom8.com studio services and widgets, autonom8.com a8flowread 2026-10-12

Camunda RPA runs Robot Framework scripts on a standalone RPA worker to operate legacy mainframe applications, desktop applications such as ERP systems and websites that expose no API. Each script runs as a step in a process, so screen work on an old system sits in the same flow as API calls, agent steps and user tasks, and scripts are built and tested before they move to production workers.

Sourcedocs.camunda.io/docs/components/rpa/overviewread 2026-10-12