Agentic Index
Feature taxonomy
The 14 buyer-facing dimensions for evaluating agentic AI capabilities. Use this taxonomy to compare vendors and understand the competitive landscape.
Vendor inclusion
Products must be shipping or in documented public beta to be included. We focus on AI agents with multi-step action, tool use, and autonomy — not single-turn chatbots.
Feature scoring
14 buyer-facing features, equal weight (7.1% each). Full = 1.0, Partial = 0.5, No/Unknown = 0.0. Coverage score is sum ÷ 14.
Pricing normalization
All data from public sources. Confidence levels reflect evidence clarity. Unknown means insufficient public sources — not capability absence.
Public-source research. Feature coverage is assessed from public vendor documentation, product pages, and analyst materials. Unknown means evidence was insufficient in reviewed sources, not that the capability is absent.
Action & orchestration
Integrations & Tool Calling
Ability to connect agents to real systems through native integrations, OAuth-authenticated actions, custom tools, APIs, webhooks, or MCP-compatible tools.
See which vendors document it →Workflow Orchestration
Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps.
See which vendors document it →Triggers & Channel Coverage
How agents wake up and where they work: schedules, webhooks, message events, CRM events, inbox events, chat, email, voice, and collaboration tools.
See which vendors document it →Knowledge & context
Knowledge Grounding & RAG
Ability to ground agent behavior in company data through document ingestion, retrieval, external knowledge APIs, semantic search, or RAG layers.
See which vendors document it →Memory & State Persistence
Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer.
See which vendors document it →Control & trust
Human Oversight & Guardrails
Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls.
See which vendors document it →Security, Identity & Governance
RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy.
See which vendors document it →Observability & Auditability
Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior.
See which vendors document it →Deployment & Data Residency
Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting.
See which vendors document it →Solution readiness
Prebuilt Agents, Templates & Packs
Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value.
See which vendors document it →Platform extensibility
Model Flexibility & Routing
Ability to work across multiple foundation models, route tasks to different models, or let buyers bring their own providers and keys.
See which vendors document it →APIs, SDKs & MCP Extensibility
Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems.
See which vendors document it →Testing, Debugging & Optimization
Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment.
See which vendors document it →Specialist automation
Browser & Computer Use
Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone.
See which vendors document it →