Agents#
pyCSAMT agents provide AI-assisted and rule-based workflow automation for survey loading, quality control, static-shift correction, phase analysis, inversion preparation, interpretation, reporting, and orchestration. Start with the orchestrating chat agent for guided end-to-end runs, browse the catalogue when you need one specialised agent, and use the family pages for the full reference of every agent group.
Start Here#
The orchestrating chat agent — plans and runs multi-step workflows end to end, grounded by the RAG assistant.
How the agent layer is organised: roles, inputs and outputs, and where agents plug into the processing workflow.
Browse every specialised agent — foundation, processing, inversion, and more — with capabilities and entry points.
Point pyCSAMT at your LLM provider and tune agent behaviour, budgets, and safety rails.
Agent Families#
Loader, metadata, and survey-intake agents that bring field data into the canonical containers.
QC, denoising, static-shift, frequency, and phase-analysis agents for data conditioning.
Forward modelling, inversion preparation, 2-D/3-D engines, and evaluation agents.
Deep-learning inversion, ensembles, anomaly detection, and the pretrained model-zoo agents.
Pipeline, reporting, export, and map/plot output agents that close out a workflow.
The low-level coordinator that sequences agents, shares state, and arbitrates between plans.