48 wired modules. 43 typed tools. One sealed evidence chain.
The agent that runs the platform. It plans the work, asks before spending, executes typed Python tools, and self-heals when a quality gate trips.
Not a chatbot — a multi-step autonomous pipeline across every engine, with a human-approval gate on spend and the whole run sealed into one evidence bundle.
- 48
- modules
- 43
- typed tools
- 6
- engines
- sealed
- per run
48 specialised modules. One coherent runtime.
Six families, each with one job. The 16 below are the core control surface; the rest are wired end-to-end in code.
Planning & approval
4 modulesAgent Planner
Decomposes intent into a typed step graph; estimates cost per node before any tool fires.
Plan Executor
Runs the graph with structured concurrency, retries and per-step checkpointing.
Human Approval Gate
Pauses on high-cost or high-risk steps; surfaces a typed approval card to the operator.
Shadow
Dry-runs proposed plans against last week's data to surface regressions before commit.
Cost & scheduling
2 modulesCost Manager
Hard caps per project, soft caps per turn; halts when burn rate exceeds policy.
Engine-Level Scheduler
Routes work to the cheapest engine that satisfies the contract (Mock vs Synthesize vs SCADA).
Physics validation
1 modulePhysics Validator
Constrains generation to physically-realisable signal shapes with a physics-honest response model.
Self-heal & resilience
5 modulesSelf-Healing Execution
Watches the evidence chain; if a quality gate fails, repairs the artefact and replays downstream.
Replan
Mid-run plan revision when an unexpected error or insight makes the original plan stale.
Risk Evidence Graph
Risk-stratified evidence graph; flags brittle or low-confidence sub-paths for review.
Cross-Correlation Rebuilder
Preserves PK/FK and joint distributions when artefacts are regenerated.
Consistency-Aware Builder
Re-derives downstream artefacts when upstream inputs change so the chain stays consistent.
Code generation & review
2 modulesCode-Gen Critic
Reviews tool-generated Python before execution; rejects unsafe or undefined behaviour.
Code Change Manager
Versions every tool-generated Python; lets the operator diff and roll back at any step.
Evidence & narrative
2 modulesProof Packets
Bundles per-step inputs, outputs, hashes and parameters into the signed evidence chain.
Narrative Generator
Produces a plain-English run-log alongside the JSON artefacts — for the audit reviewer.
Also wired: approval_timeout · contract_context · dataset_resolver · evidence_parser · executor_eval · grounded_output · hypothesis_tree · memory · moderation · observer · patch_planner · policy_adapter · prompt_registry · replan_evaluator · replay_bundle · retry_escalate · rseg_calibration · scenario_selector · turn_context · validation_runner · budget · hagp_pause · surrogate · diff_builder · domain_prompt · … and more
43 typed tools the agent can wield.
All five families run through both the chat interface and POST /v1/agent/tools/{name}/execute for direct invocation from the SDK or your own UI.
Data preparation
6 toolsMachine learning
7 toolsExplain & report
8 toolsSynthetic data
5 toolsIndustrial / ICS
6 toolsQuality gate fails? It heals itself.
When a divergence widens, a constraint slips or a hash mismatches, the self-healing layer isolates the failing sub-graph, repairs the artefact, and rebuilds the chain — without losing what already passed. The narrative file explains, in English, what happened and why the rebuild is sound.
Sense
Self-healing execution watches every quality gate, artefact hash and chain segment in real time.
Diagnose
The risk-evidence graph isolates the failing sub-graph; the rebuilder identifies which downstream artefacts are now stale.
Repair
Replan rewrites the affected sub-plan; the code-gen critic reviews any generated code before re-execution.
Re-seal
The consistency-aware builder rebuilds the chain; proof packets commit the new root; the narrative generator appends to the run-log.
Water treatment pump station SCADA, 60 seconds, Modbus + OPC-UA, 8 signals: discharge pressure, suction pressure, motor temperature, VFD output, flow rate, tank level, and an over-pressure alarm. [Protocols: modbus, opcua] [Duration: 1m] [Poll: 1 Hz] [Streaming: off]
small_wwtpRun a SCADA simulation for the water treatment pump station.
Verify the quality and provenance of the simulated data.
Every engine under one orchestrator.
The scheduler routes work to the cheapest engine that satisfies the contract; the physics validator keeps generation realisable; proof packets seal the result. The team that writes the contract sees the plan card, the cost gate, the quality verdict and the sealed bundle — nothing locked behind a platform admin.
Mock Data
Sub-minute deterministic synth from a prompt.
Synthesize
The trained synthesis engine on uploaded data.
Virtual SCADA
Physics-honest telemetry over real protocols.
ICS Security
Ground-truth ATT&CK ICS attack injection.
Tool executor
43 typed Python tools, in-process or queued.
Connectors
14 encrypted source adapters, browse + import.
Built so an autonomous agent survives procurement.
Tenant-isolated
Every plan, prompt, dataset preview and tool I/O lives in your tenant prefix only.
Spend-bounded
Soft + hard cost caps; the agent stops, asks or downgrades the engine before exceeding policy.
Audit-ready
A sealed transcript per project — prompt, plan, approvals, tool I/O, evidence root.
Reproducible
Re-run the same contract + seed on a different cluster: the dataset hash matches byte-for-byte.
Bring a real prompt. Watch every module work.
A 90-minute working session: bring a representative dataset and one open question. We drive the agent end to end — you watch the plan card, the cost gate, the live stream and the self-heal trigger. You keep the sealed transcript bundle.