Knowledge types
You can create three types of knowledge. Pick the type that matches the information you want to provide.- Terminology defines a term your test or app uses so the agent resolves it the way your team means it. You provide a canonical term, a definition, and optional examples that ground how the term is used. Use this when a word is ambiguous, such as what “the selected tab” actually refers to in your UI.
- Agent rule is a binding instruction that one agent should follow at runtime. You give it a title, choose the agent it applies to, and write the instruction. Only the selected agent receives the rule, so you can shape behavior precisely, such as how elements are located or how a failure is classified. Rules can also target the heal subagent, which repairs one failing test at a time. Product-specific recovery guidance reaches the agent that edits or verifies the repair without being applied to broader failure-bucketing.
- Flow is a known workflow with an expected outcome. You describe the intent (the user-level goal, like “log in”), the steps (one per line), and the success state (what should be true once the flow finishes). Flows give the agent a reliable map of how a journey through your product is supposed to go.
Adding knowledge
- Open the Knowledge section, click Add knowledge, and choose Create manually.
- Choose a type. The form shows the fields relevant to that type.
- Fill in the content and, optionally, set a scope.
- Save. The item is visible immediately and becomes searchable when indexing finishes.
Scope
By default, knowledge applies across your whole organization. You can narrow an item so it’s only retrieved in a more specific context:- Test scope limits the item to a single test.
- Environment scope limits the item to a specific environment.
- App scope limits the item to a specific app.
Bulk upload
To import an existing knowledge base in one step, choose Bulk upload from the Add knowledge menu and upload or paste a JSON array or CSV of items. Momentic accepts up to 200 rows per upload and validates the whole upload together: if any row is invalid, Momentic creates nothing and the error lists the offending rows. Each row carries atype of TERMINOLOGY, AGENT_RULE, or FLOW (defaulting
to TERMINOLOGY when omitted) plus that type’s fields:
- Terminology:
canonicalTerm,definition, and optionalexamples. - Agent rule:
title,agentSubtype, andinstruction. - Flow:
intent,steps, andsuccessState.
examples field accepts either a JSON string array or a newline-separated
string (one example per line), which is convenient for a single CSV cell. Add an
optional appId, testId, or environmentId to a row to scope it;
omit them to keep the item organization-wide. The dialog includes JSON and CSV
samples you can load as a starting point.
Suggestions
Momentic captures candidate knowledge from your sessions and collects it in the Suggestions tab for review. These are entries Momentic inferred about your product that aren’t part of your knowledge base yet.- Approve a suggestion to promote it into your organization’s knowledge base, where it starts informing agents.
- Reject a suggestion to discard it.
Enabling and disabling
Active knowledge can be turned on or off without deleting it:- Enabled: the item is live and eligible for retrieval.
- Disabled: the item is kept but excluded from retrieval.
Trust and conflicts
Each item carries a trust score from 0 to 100 that shows how authoritative it is. Manually authored knowledge is trusted more than auto-generated suggestions, and Momentic’s own system knowledge is trusted highest by default. Prompts instruct agents to prefer the higher-trust entry when entries conflict. Agent rules are treated as binding instructions and are given extra retrieval weight.How agents use knowledge
Momentic uses semantic retrieval to select entries relevant to an agent’s task and includes the retrieved entries as priority context. Heal runs also retrieve knowledge scoped to the test being repaired, so rules, terminology, and known flows can guide the repair for that specific failure. Prompts require agents to follow entries that directly address the task and cite entries they rely on in written reasoning or summaries. Use those citations to trace which knowledge influenced a decision.Versioning and usage
Editing an item records a new version. Inspect its history in two tabs:- About keeps the full version history, including who changed what and when.
- Usage lists and links the runs that cited the item, the test each run belongs to, and when it was cited.
Memory
Memory gives the agent its past decisions to help it resolve ambiguous references such as “the selected tab” consistently. Momentic uses it for the locator agent (Click, Type) and the assertion agents (AI check, Element check). Memory counts as caching, so it is skipped when caching is disabled.- Memory is stored per organization and is read only during authenticated runs.
- An entry expires after 30 days without use. Momentic prunes memory to the most relevant traces.
- Memory can include failed locator results and false assertion results. The agent can reuse them when the page shows the same failure.
ai.useMemory.