The execution engine
Give it a goal. It runs the graph.
Sophon Graph runs your request as a durable, concurrent graph: independent steps execute in parallel in isolated sessions, results join cleanly, and work that finished is never redone. A restart brings the run back exactly where it stopped — and hands you the decision to carry on.
Why a graph beats a loop.
The old way ran steps one at a time in a single growing transcript. The graph changes the physics of a run.
Parallel
Independent steps run concurrently — a briefing with three fetches finishes in roughly the time of the slowest one.
Durable
Every transition is checkpointed, so completed steps are never re-run. If the Gateway restarts mid-step, the run comes back paused and waits for you to resume it — nothing side-effecting is replayed behind your back.
Isolated
Each step runs in its own child session with a small, clean context — no noisy tool output polluting the next step, and lower cost than one ever-growing transcript.
A run, end to end
From one ask to delivered work.
Every transition below is written to the store the moment it happens — so a restart never repeats finished work.
Durable approvals
When the plan changes, the run waits for you.
A step that keeps failing gets the plan repaired around it — and a repair that raises the risk, reaches for a new kind of tool, or adds a step with side effects parks the run behind a durable gate. No thread is blocked, no timeout ticks away in memory: the run's entire state is checkpointed.
- Answer a revision gate from the Dashboard, a push notification, or a numbered chat reply — hours later, not seconds (24h by default, up to 72h).
- If the Gateway restarts while you're deciding, nothing is lost — the run is still parked when it comes back.
- No answer? The gate times out and rejects — it never auto-approves.
- A tool approval or question raised inside a running step is a live request on a short fuse instead: answer it in your main chat, and if the Gateway restarts mid-wait that step attempt fails and retries rather than resuming the wait.
Built for big jobs.
40 invoices, one run
Each invoice is processed in its own fresh, isolated step — and the run checkpoints after every item. Restart at item 25 and the 24 finished items are never re-run or re-billed; item 25 is the only one waiting, and it waits for you to press Resume.
When a branch dies, the plan repairs itself
A failed step retries with an alternative approach; if that fails, just that subgraph is patched into a new immutable version of the plan while finished steps stay frozen. Repairs are bounded — you get partial results instead of nothing.
Guardrails, on by default.
Parallel power needs hard rails — every run gets them.
Run budget
Every plan run carries a $2.00 default cost cap and a token backstop, checked between steps. A breach stops the run and names the limit it hit — steps already in flight finish first, so spending lands near the cap, and the stopped run is reported failed rather than left resumable. Sub-agent delegation graphs are held by the token backstop alone.
Injection boundary
A step never sees the parent conversation. Dependency outputs arrive wrapped and clearly marked as untrusted.
Taint-aware approvals
Plan steps that touched the open web lower the auto-approve ceiling for whatever consumes their output — riskier actions then need a human.
Liked that run? Keep it.
One click exports a completed run's graph to the visual workflow builder — tweak it, put it on a schedule, run it forever. Honest about it too: a conversion note lists anything that doesn't translate 1:1.
Also honest: Graph drives a run from one Gateway instance — scale the machine, not the replica count. A dedicated engine reference lands in an upcoming release; until then, Planning covers how a plan is compiled, run, checkpointed, and revised.
Open the workflow builderExecution modes
Graph and Classic. Your call, per conversation.
Graph is on by default. Switch any conversation with the in-chat pill in the composer, set your own default in Settings → Execution, or use /mode in the CLI. Admins set the workspace default — and the ceiling.
Put the graph to work.
Install Sophon, connect a model, and give it a goal. The Personal tier is free for individual, non-commercial use.