AI & machine learning

Agent runs: start sessions, stream events, read transcripts, and fetch results and artifacts

Inbox, channels, AI agents and integrations: manage conversations, agents, files and workspace data

AI agent platform: build and run agents, workflows, memory, approvals and messaging channels

AI agents: manage agent workspaces, tools, scheduled tasks and conversation invocations

AI image, video, 3D and audio generation: create media, upload assets, train styles, run node apps

Agent platform: manage agents, folders, skills, integrations, credentials, billing and chat rooms

LLM gateway: chat, embeddings, images and audio, plus keys, credits and usage analytics

Inference: chat, completions, embeddings, rerank, audio transcription, plus model listing and runtime pool coordination

Data labeling: manage projects, tasks, annotations, reviews, storage and ML backends

GenAI platform: build agents, prompts and knowledge bases, run evals, and query logs and traces

AI agents: run conversations, manage knowledge bases for retrieval, and issue API keys

Platform API for workspaces, datasets, model gateways, robots, SCIM users and usage billing

Search inference: run encode, score, extract and generate models, plus embeddings and transcription

Hotel and voice AI platform: manage AI agents, calls, knowledge bases, campaigns, docs and spreadsheets

Hosted AI gateway: proxy OpenAI and Anthropic models, store files, run agents and manage auth

Agent tools: live MCP endpoint, private memory, spending caps, handovers, code audit and lead generation

AI task orchestration: run agents, tools, threads, models, workspaces and voice calls

Scanning pipeline: register customers, sites, cameras and scans, ingest video, track AI results and measurements

AI platform: chat, images, audio, video and files, plus sessions, agents and projects

AI game asset generation: create images, video, audio and 3D with models, training and workflows

AI agent governance: manage agents, policies, API keys, deployments, traces and compliance

Agents and tasks: run multi-agent workflows, schedules, skills, MCP servers and approvals across coding agents

AI agent training and evaluation: trajectories, training runs, benchmarks, deployments and model endpoints

LLM observability: trace spans, run datasets and experiments, evaluate outputs, and monitor model metrics