Inwire Module User Guides
This section is the official user-facing manual for Inwire platform modules. Engineering analysis, historical plans, audits, and progress trackers are archived under analysis-docs/ and are not the user manual.
| Module | What It Covers | Guide |
|---|---|---|
| Access Control | Manage organizations, teams, users, roles, API keys, RBAC policies, SSO, and audit logs for the Inwire platform. | Open guide |
| Synthex | Prepare, profile, transform, and generate synthetic datasets for model training, evaluation, and privacy-safe testing. | Open guide |
| Model Training | Run experiments, training jobs, hyperparameter tuning, dataset selection, approvals, recipes, and training observability. | Open guide |
| ModelOps | Register, version, build, deploy, monitor, govern, and optimize models across Kubernetes, Docker, hosted inference, and GitOps targets. | Open guide |
| InferenceIQ | Optimize inference cost, latency, throughput, hardware fit, serving engine settings, and production feedback loops. | Open guide |
| RAG | Build retrieval-augmented generation systems with data sources, pipelines, indexes, retrieval tuning, security, analytics, and workflows. | Open guide |
| Evaluation | Create datasets, benchmarks, safety checks, model comparisons, leaderboards, and evaluation jobs for models and prompts. | Open guide |
| Agent Studio | Design, test, publish, deploy, and monitor AI agents and multi-step workflows with tools, knowledge, schemas, runs, and endpoints. | Open guide |
| CCE | Context and Cognitive Engineering for prompts, context packs, memory, profiles, test suites, token analysis, regressions, and A/B tests. | Open guide |
| Data Studio | Create projects, manage datasets, design pipelines, label and curate data, and connect data workflows to Synthex, training, and evaluation. | Open guide |
| Launchpad | Discover, test, evaluate, and launch curated open-source and enterprise model templates with guided deployment paths. | Open guide |
| Model Fine-Tuning | Prepare datasets, choose base models, create fine-tuning jobs, manage adapters, evaluate outputs, and promote tuned models. | Open guide |
| Inwire Observe | Monitor model, agent, and platform behavior through traces, metrics, alerts, costs, drift, errors, events, topology, and runbooks. | Open guide |
| Infrastructure and Agents | Connect Kubernetes clusters, Docker VM targets, multi-cloud resources, and outbound-only Inwire agents to the control plane. | Open guide |
| Serving and Inference Gateway | Manage inference endpoints, keys, requests, observability, incidents, policies, rollouts, snapshots, routing, and failover. | Open guide |