momentic.config.yaml ai.agentConfig
block. Momentic announces agent deprecations at least 90 days in advance.
Supported locator and assertion agents use memory
(insights saved from past runs) and custom knowledge base
entries.
Agents can fall back to configured alternative models when a provider fails.
Fallbacks can change latency and decisions. Memory,
the knowledge base, and
failure recovery reduce the
frequency and impact of AI non-determinism on your tests.
Web agents
Mobile agents
V5 effort routing
V5 requiresmomentic 3.52.10 or later.
v5 routes each locator and assertion query to one of three effort levels
(fast, medium, or extended) based on the query’s complexity. You set v5 in
agentConfig; the effort level is not configurable.
The effort level multiplies the AI step rate for the query:
Multipliers apply to usage-based plans: Free, Scale, and older Free and
Pay-as-you-go plans, where they multiply the usage a query bills. Enterprise
contracts priced per test are not affected.
visual-assertion v5 does not use effort routing. Every visual assertion
bills at the 1x AI step rate, the same as v4. Setting visual-assertion: v5
in momentic.config.yaml requires momentic 3.60.0 or later; selecting it in
workspace settings works with any CLI version.
What each agent does
Locates elements from a natural language description, used by Click,
Type, and Element check steps. Exact single-quoted text constrains
matching. Successful resolutions can populate the step cache.
Evaluates natural language statements against a snapshot of the page, used by
AI check steps. Prioritizes exact single-quoted text values and resolves
visual detail from the current page context.
Evaluates natural language statements from a viewport screenshot. Use it for
visible layout, text, and appearance within the viewport.
Extracts structured data from the page given a JSON schema, used by AI
extract steps. Supports nested objects and arrays.
Generates and executes recovery steps when a recoverable failure is detected.
Requires
ai.failureRecovery.Locates elements in the Android UI hierarchy from a natural language
description, used by mobile Tap, Type, and Element check steps.