Agentic workflows

Agentic workflows are how amAIra goes beyond a general chat. You ask in ordinary language, or you run a short slash command. The assistant uses the scene you are actually looking at.

Antinode Antinode
amAIra amAIra

Scenaven, Antinode, and AI costs

What you need

Requirement Why it matters
Sign in on the home page Unlocks amAIra and Python session. See Antinode
Infrastructure on Connected A skill that reads or runs on the simulation calls the server
Something loaded Answers refer to the current scene and time step

If the amAIra tab is missing, sign in on the home page and open the viewer from there.

The amAIra tab lives in the docked panel on the right (next to Python session):

amAIra chat in the Antinode slide-in panel
amAIra chat in the Antinode slide-in panel

The pieces

Piece What it is for
Antinode Home-page sign-in, identity, and agent gateway
amAIra The chat tab on the right
Knowledge Notes the assistant can read: how a Scenaven session works, your own cheat sheet, or context for your discipline
Skills Actions you can call, often with a slash command, that read live data or run an approved step on the simulation
Scripts Short Python a skill can run on the server, with the same limits as the Python session. You choose the skill in chat. The skill runs its script

Scenaven ships example skills — describe the session, field reports, frame compare, design-limit checks, and similar — so you can see what is possible on on-prem (or on hosted cloud when your account includes the full tool set). The real power is tailoring workflows to your team: upload your own Knowledge, Skills, and short Scripts in amAIra Workflows, using the shared ones as patterns to copy and adapt.

Shared examples and your own workflows

Kind Who it is for
Shared (examples) Built-in slash commands and knowledge — starting points, not the only way to work
Personal What you add in Workflows — discipline-specific checks, report wording, slash commands for your process

Shared items show the pattern: a Skill (often a / command) calls the server against the mesh you have open; optional Python in a Script does the analysis (same sandbox as the Python session). Personal items use the same mechanics — you are not limited to the built-in catalog.

Typical reasons to add your own:

  • Repeatable QA on your fields (limits, hotspots, percentiles) with your naming and thresholds
  • Knowledge that documents your mesh conventions, units, or “always run X before Y”
  • Slash skills for steps your group runs on every review (still read-only until you add server features)

In the amAIra panel, open Workflows (next to Chat) to add Knowledge (markdown) or Skills. For Python-backed skills, upload the Script there too and link it to the skill (script_ref). Start from a shared skill’s behavior in chat, or mirror the small Hello session example — then change the script and skill for your case.

You can chat without uploading anything. Shared examples and guidance may already be there after you sign in.

What the assistant uses

A shared example skill and a skill you added yourself run the same way. You ask, or you type / and pick a skill. The skill runs on the server against the simulation you have open. The answer shows in the chat, sometimes with a hint in the viewer.

You can leave field names and frame numbers out. The assistant uses the current selection unless you ask about something else. If the skill needs a detail, it asks for that — a field, a frame, or which object.

The assistant updates when you:

  • Load an example or open a file
  • Select a different row in Scene
  • Move to another time step
  • Apply a filter or start a new scene

Ways to use it

Ask in plain language

  • “What fields are on this mesh?”
  • “Summarize this transient dataset.”
  • “What clip would isolate the high-stress region?”

The answer mixes Knowledge with the live session when a matching Skill exists.

Slash commands and @ references

  • Type / to pick a Skill, for example to describe the session or compare two frames.
  • Apply clip and Apply warp change filters on the scene you name — same path as Scene → Selected prim (compile), not a separate confirm step.
  • Type @ to pull a Knowledge note into the message by name.

A slash command runs on the server against the simulation you have open, and the result comes back in the chat (and act skills also update the 3D view).

Chat and the Python session

Workflows answer and suggest. The Python session is where you edit and run a snippet yourself. A skill that runs Python follows the same limits: no import, and the names session, np, and vtk. A common pattern is to ask in chat, then try the snippet the assistant offered.

Troubleshooting

What you see What to check
No amAIra tab Sign in on the home page and open the viewer from there
Chat works, but / lists nothing Open Workflows and see what is published. Shared skills may not be available yet
A personal upload fails You need to be signed in. Knowledge is a markdown note. A skill that runs Python needs its script uploaded in Workflows and attached to that skill
Answers feel generic Shared notes may be broad. Add your own in Workflows
A skill fails or times out Infrastructure should say Connected, and a dataset should be loaded
A skill says it cannot run its script In Workflows, confirm the script is uploaded and the skill is attached to it
The answer is about the wrong object or frame Select the row or time step you mean, then ask again

Next steps