Orchestration
Turn one-off agent runs into repeatable, reviewable workflows.
Define a workflow as a DAG of agent and exec nodes, validate it, then run it. Each run produces a run record you can watch live and review afterward. Start from a template or build it on the canvas. Everything is tenant-scoped behind row-level security.
trigger
manual / cron
agent · plan
claude-code
exec · test
npm test
agent · fix
claude-code
exec · merge
git · gate
How it works
1
Define the DAG
Lay out agent nodes (a Claude Code session with a prompt) and exec nodes (a shell command) and the edges between them.
2
Validate
Before anything runs, the server checks the graph: no cycles, every dependency resolves.
3
Run it
Kick off the workflow manually or on a schedule. Each node runs in order, respecting its dependencies.
4
Watch the run
Follow the run record live in the canvas and run viewer, then review the completed run later.
Deep dives
Agent + exec nodes
An agent node is a Claude Code session driven by a prompt; an exec node is a shell command. Compose them into a DAG to chain planning, code changes, tests, and gates into one run.
Node timeouts → SIGTERM
Every node can carry a timeout. On breach the node is sent SIGTERM so a stuck agent or runaway command can't hold the run open indefinitely.
Templates & visual canvas
Start from a built-in starter template, then edit on the visual canvas. The run viewer shows each node's status as the run progresses.
Define and run a workflow
config · workflow.yaml
name: ci-triage
nodes:
- id: plan
type: agent
prompt: "triage the failing build"
timeout: 15m # SIGTERM on breach
- id: test
type: exec
run: npm test
needs: [plan]
$ synaptyx workflow run ci-triage
✓ validated DAG · 2 nodes · no cycles
run_id: wf_3c8a… · watch the run record live in the canvas
Orchestration that's auditable, not opaque.
A workflow is just a DAG you can read, version, and review. Each run is recorded, so you can see exactly which node did what, no black-box automation.
Compare
| Caldyr | Shell scripts | Generic CI | |
|---|---|---|---|
| Agent-native nodes | yes | no | no |
| Pre-run DAG validation | cycles + deps checked | no | partial |
| Live run record | canvas + run viewer | logs only | logs only |
| Node timeout → SIGTERM | per node | manual | job-level only |
| Tenant isolation | RLS-scoped | no | shared runners |
FAQ
Two kinds today: an agent node runs a Claude Code session from a prompt, and an exec node runs a shell command. You wire them into a DAG and connect each node's output to the next via its dependencies.
Each node can declare a timeout. When it's exceeded the node is sent SIGTERM, so a stuck agent or long-running command is stopped instead of holding the whole run open.
No. There are starter templates to clone, and a visual canvas/editor to adjust the graph. You can also define a workflow as a definition and run it via the API.
No. Workflows and their runs are tenant-scoped and enforced with row-level security in Postgres, so they're only visible inside the company that owns them.
Ready to orchestrate your agents?
Request access in minutes, or talk to us about your workflow patterns.