Synera

Agents can read and write in 80+ named engineering tools, call web APIs with OAuth, and use remote MCP servers as tools.

The platform page says "connect 80+ CAD, meshing, analysis and productivity tools" with 1000+ nodes, including read-write control ("remote control industry leading CAD applications like CATIA, NX or SolidWorks to generate, modify and optimize geometries"), FEA meshers and solvers (HyperWorks, ANSYS, Abaqus), a Teamcenter connector to "interact with your Siemens Teamcenter environment", ODBC database queries, and web API nodes that call "any REST API... and authenticate with OAuth".

Release 26.07 lets customers "plug any existing remote MCP server straight into an agent or Supervisor node" as a tool. Connectors are native plus partner-built (20+ software partners in the marketplace), and custom nodes and Python, C#, MATLAB and TCL scripts add custom tools.

Credential scoping, rotation and revocation are not publicly documented.

Sourcesynera.ai/platform, /webinar/product-release-26-07-quick-quilla; portal.synera.io FAQ Integrating Synera with External Software; readread 2026-09-16

Deterministic workflow nodes and autonomous agent steps mix in both directions, under coordinating agents. The AI Agents FAQ says engineers build low-code workflows that "are then made available as tools for agents", with "management agents coordinat[ing] tasks while engineering agents focus on specialized processes".

The orchestration article describes "a coordinator agent that manages the full workflow: passing context between specialized agents, maintaining state across the process, and handling exceptions when input data is incomplete", and a Supervisor that validates output before each handoff. Release 26.07 adds "one entry point" that brings agents into "both multi-agent conversations and rule-based workflows".

Workflows are saved as templates or new nodes in individual or shared team libraries, publishing errors are shown as the workflow is built, and workflow errors can be inspected on the Run server (25.11).

Explicit branching and fallback-path configuration for agent steps is not described on public pages.

Sourcesynera.ai/ai-agents, /news/ai-agent-orchestration-engineering-use-cases, /webinar/product-release-26-07-quick-quilla, /platform; read; synera.ai/news/ai-agent-orchestration-engineering-use-casesread 2026-09-16

Two persistent retrieval structures sit over the customer's own content: Knowledge Spaces and geometry similarity search. Release 26.03 Phenomenal Phoenix (19 March 2026) introduced "Knowledge Spaces that let agents accumulate and apply expert decisions over time", taught through a "Remember this" interaction, where "that knowledge is stored, managed, and reused"; and Part Comparison nodes that "turn CAD geometry into a 100-dimensional fingerprint and search an entire part database for similar designs".

Release 26.07 adds an Advanced AI add-in that finds similar parts "across a product lifecycle management (PLM) system or local files", and the RFQ case study has a geometry agent searching the CAD library for comparable parts. Both persist, stay queryable between runs and take new knowledge without retraining. Workflows are tools the agent runs, not knowledge it retrieves.

Document ingestion and refresh, retrieval visibility, citation of sources, and stale entry handling are not publicly documented, and the product docs at portal.synera.io/docs require a login.

Sourcesynera.ai/webinar/product-release-26-03-phenomenal-phoenix, /webinar/product-release-26-07-quick-quilla, /news/ai-agent-orchestration-engineering-use-cases; readread 2026-09-16

The engineer is cast as the reviewer of agent work, but no approval step is documented. The orchestration article says the engineer's role shifts to "reviewer", the agents handle cross-tool execution, and "the engineer retains judgment over the results"; in the RFQ build a requirements agent flags ambiguities for engineer review; and the aerospace article describes the engineer "directing the work". That is a boundary stated rather than enforced.

No configurable sign off is shown: where approvals can be inserted (node, workflow or policy layer), who signs off and what happens when nobody does are not documented. Product documentation at portal.synera.io/docs and /dev-docs sits behind a login.

Sourcesynera.ai/news/ai-agent-orchestration-engineering-use-cases, /news/agentic-ai-for-engineering-in-aerospace-and-defense; portal.synera.io API probes; readread 2026-09-16

Synera holds TISAX Level 2 and brokers single sign-on to the customer's identity provider. Its announcement (23 October 2024) states "Synera has successfully achieved TISAX Level 2 certification", the automotive information-security assessment derived from ISO/IEC 27001, independently audited and verifiable on the ENX portal under Scope ID S007M3 and Assessment ID AX6WMT; the TISAX mark sits in the site footer on every page.

For sign in, the public FAQ on the server stack names the Synera Identity Manager (IDM, Keycloak), "an SSO broker between your identity provider (Entra ID, Active Directory, SAML, OIDC) and Synera components", and Run server publishing is permission-controlled. The security FAQ states that no canvas data is sent with analytics, only usage statistics and interface interactions.

TISAX results are not public by design, and role based access across tools, knowledge and model usage is not publicly documented. On-premises delivery is a deployment property, not a security control.

Sourcesynera.ai/news/synera-achieved-tisax-level-2-certification; portal.synera.io FAQ What are the 5 components of the Synera server stack, Since Synera is an open platform what features are there for security; readread 2026-09-16

Every step of a run across several agents is narrated by the Supervisor agent, and the record stays visible in the product. Synera's Hannover Messe recap says "the Supervisor agent narrates every step of the process, from the inputs taken from the engineer to the outputs delivered to each specialized agent", and every geometry change, simulation result and calculation "remains visible and accessible in the Synera UI".

Release 26.07 lets users "inspect 3D outputs directly in the chat" an agent just produced; release 25.11 adds Workflow Diagnostics to "inspect workflow errors directly on the server"; and the MAS support FAQ directs customers to collect MAS server log files. A per-agent narration of handoffs kept in the UI is step-by-step visibility a buyer can inspect after the fact.

Audit logs separate from runtime traces, export to monitoring or SIEM, and retention are not documented, and the MAS token FAQ says no built-in token tracking exists. The step narration is described in an event recap rather than product documentation. Design outputs and simulation results are the customer's product artifacts, not a record of the agent.

Sourcesynera.ai/news/agentic-engineering-blueprint, /webinar/product-release-26-07-quick-quilla, /news/release-webinar-25-11-outstanding-odysseus; portal.synera.io MAS FAQ; readread 2026-09-16

Conversation state carries through a session, but no memory layer with a stated scope and lifetime is documented. The MAS token FAQ says each message sends "the system prompt, tool descriptions, and the conversation history" to the model, history grows through a session, and "starting a new session creates a fresh conversation"; the orchestration article's coordinator agent maintains state across a multi-agent run. That state disappears when the session ends.

No per-user or per-agent memory with a stated scope and lifetime is shown, so there is no memory store to review, edit, delete or scope. Knowledge Spaces ("Remember this") is a store of expert decisions that agents query rather than memory of their own, and a workflow library is the application's own data.

Sourceportal.synera.io FAQ How does token usage work in MAS; synera.ai/news/ai-agent-orchestration-engineering-use-cases, /webinar/product-release-26-03-phenomenal-phoenix; readread 2026-09-16

Synera installs on the customer's own infrastructure, with an AWS option for the agent solution. The public FAQ on the Synera server stack lists a Desktop Client "installed on each user's machine", a Token License Server (RLM), and an optional Synera Server (exposing the Run Daemon and MAS), Identity Manager and PostgreSQL databases that "customers who already run their own PostgreSQL server can simply create there"; consumer users reach the customer's Synera Server URL in a browser.

The platform page says automation experts "host their engineering workflows on an on-premise Synera Run server", the releases FAQ documents installers and rollback for Windows 10/11, and the AI Agents page says the agent solution is "deployable on AWS". On-prem, hybrid, local runtime and self-hosting are modes available now, and the customer installs upgrades and rollbacks from the portal.

Feature differences between self-hosted and AWS deployment are documented only for Run versus local machine, and no Synera-hosted region list is published.

Sourceportal.synera.io FAQ server stack; synera.ai/platform, /releases, /ai-agents; readread 2026-09-16

Workflow templates come as a browsable catalog of downloads. The Synera Marketplace lists 189 templates on its public templates endpoint, each a downloadable.syn workflow tagged by application and industry (for example Advanced FEA, Advanced FEA with Altair HyperMesh and OptiStruct, Advanced LS-DYNA Simulation Modification, AM Line Supports), and the platform page offers "pre-built templates for different industries and applications". Each template runs as a whole workflow when opened, and templates are editable in the visual editor and can be saved as custom nodes.

The catalog mixes production-grade simulation workflows with small utilities (Alphabetical Sorting), no prebuilt agent teams are cataloged, and customer references are not tied to templates. Nodes are building blocks rather than packs.

Sourceportal.synera.io/marketplace and /api/marketplace/v2/templates; synera.ai/platform; readread 2026-09-16

Every documented entry point to Synera's agents is invoked by a person or by another system calling in. Agents are reached through multi-agent conversations with a Supervisor, through Synera Run workflows an engineer opens by link and feeds input files, through the built-in Synera Run MCP server that external agents such as Copilot Studio, Claude and ChatGPT call, and through Synera Headless, which external software can start from a command line (syneraheadless.exe execute).

No schedule, webhook, or PLM or file event is documented that starts an agent without someone initiating it. Headless can be woken by the customer's own scheduler, but that is the customer's mechanism, not a Synera trigger, and no requirements or design change trigger is documented either. The AI Agents page's "work continuously around the clock" describes capacity, not a trigger.

Sourcesynera.ai/webinar/product-release-26-07-quick-quilla, /ai-agents; portal.synera.io FAQ (Synera Headless, Integrating Synera with External Software); readread 2026-09-16

Customers assign models per agent on their own model deployments.

The MAS (Managed AI Services) FAQ on a slow Supervisor explains that "an agent may be assigned a model with a lower token limit, while other agents use models with higher limits", and tells the customer to "deploy a model with a higher token limit for the Supervisor", configured "in your model deployment settings (e.g., Azure OpenAI)", with rate limits set on the customer's own LLM deployments (for example Azure AI Foundry) by their IT administrator.

The MAS token FAQ advises users to "choose models with larger context windows", and release 26.07 adds GPT-5-class model support. Model choice is customer and admin controlled, per agent, on the customer's own providers and keys.

No provider list beyond the Azure examples is enumerated, and model policy by workspace or action, benchmarking and fallback policy are not documented beyond automatic retry with back-off on rate limits.

Sourceportal.synera.io FAQ entries: Why does the Supervisor in MAS sometimes respond slowly or get stuck; How does token usage work in MAS; synera.ai/webinar/product-release-26-07-quick-quilla; readread 2026-09-16

Synera serves its workflows to outside agents through a built-in MCP server, and to outside software through a command-line runner. Release 26.07 Quick Quilla (17 August 2026) states "the built-in Synera Run MCP server lets external agents like Copilot Studio, Claude, and ChatGPT execute the engineering workflows your experts already built", turning a Synera workflow "into a tool an external agent can execute" from Codex, Cursor and VS Code as well.

Synera Headless runs any workflow from a command line (syneraheadless.exe execute --file --jsoninput --output), so external software can start Synera and read its results, per the public FAQ, with developer documentation at portal.synera.io/dev-docs. Synera both consumes and serves MCP, and a shipped MCP server that triggers actions fits it directly into other agent systems. Custom nodes and Python, C#, MATLAB and TCL scripts extend the platform.

No REST API or SDK reference is publicly readable, since /dev-docs requires a login, and authentication and versioning of the MCP server are not publicly described.

Sourcesynera.ai/webinar/product-release-26-07-quick-quilla, /releases, /platform; portal.synera.io FAQ Synera Headless; readread 2026-09-16

A workflow is checked before it is released to users, but no evaluation of what the agent produces is documented. Release 25.11 adds a "new publishing checklist" for Synera Run, and possible publishing errors "are now shown dynamically as you build the workflow", so a workflow is checked before release. The MAS Supervisor FAQ documents automatic retry "with exponential back-off" when an LLM rate limit is hit.

The publishing checklist reads on whether a workflow will publish and run, not on what the agent produced. Testing with fixtures or datasets before production, and scoring output quality over time, are not documented. Simulation and validation loops in Synera test the customer's part design, not the agent workflow.

Sourcesynera.ai/news/release-webinar-25-11-outstanding-odysseus; portal.synera.io FAQ Why does the Supervisor in MAS sometimes respond slowly or get stuck; readread 2026-09-16

Engineering applications are driven through their APIs rather than their screens, though one marketplace add-in may automate graphical interfaces. The platform page's CAD control ("remote control industry leading CAD applications like CATIA, NX or SolidWorks") and the Run any CAD add-in, which automates "any CAD application offering an API", both drive applications through their APIs, not through the screen, so neither is computer use.

The public FAQ Integrating Synera with External Software names the RPA by stone-dev add-in in Synera's own marketplace for applications that "cannot be connect[ed] via standard add-ins, Python-, Run External Program- or the Web Request-nodes". It may be GUI automation shipped in Synera's catalog, but the marketplace search and the add-in page sit behind a login, so whether it drives a visual interface is not published.

Sourceportal.synera.io FAQ Integrating Synera with External Software; synera.ai/platform; readread 2026-09-16