Rules and decisions

The rule set is the contract between you and your agent. It lists, per surface (mapping jobs, unmatched results, mismatch reports, coverage, data sources/sinks, exports, bulk updates, notifications), what the agent is allowed to do autonomously. Tool calls against a disabled rule return error: "rule_disabled" to the LLM, which then adapts — typically by filing a pending item or summarising differently.

Orchestration + triage, not confidence judgement

Agents in v1 are an orchestration and triage layer, not a per-row confidence-judgement layer. Confidence-threshold rules (e.g. “auto-approve any match above 0.95 confidence”) are not supported in v1. The PartnerMappingResult.matchConfidence field is nullable in production and is not relied upon by the rule engine.

What this means in practice:

The agent proposes matches for unmatched rows. A human approves.
The agent drafts proposed resolutions for mismatch reports. A human marks FIXED / REJECTED.
The agent never auto-links a result to a reference hotel.
The agent never auto-marks a mismatch as fixed or rejected.

Confidence-based auto-approval is on the roadmap but explicitly excluded from v1. See the overview roadmap section.

Rule set JSON shape

{
  "mapping_jobs": {
    "trigger_on_new_inventory_upload": true,
    "trigger_on_cron": false,
    "re_run_on_golden_dataset_change": false
  },
  "unmatched_results": {
    "propose_candidates_for_review": true,
    "max_candidates_per_row": 3,
    "search_strategies": ["geo", "name"]
  },
  "mismatch_reports": {
    "auto_transition_open_to_in_progress": false,
    "group_similar": true,
    "post_proposed_resolution": true
  },
  "coverage": {
    "alert_below_pct": 95,
    "weekly_digest": true
  },
  "data_sources": {
    "auto_pull_on_schedule": true,
    "pause_source_after_failures": 3
  },
  "data_sinks": {
    "auto_push_on_job_complete": false,
    "retry_failed_push": 2
  },
  "mode_preference": { "allow_auto_change": false },
  "export":          { "allow_auto_export": false },
  "bulk_update":     { "allow_auto_bulk_update": false },
  "notifications": {
    "on_action": true,
    "on_escalation": true,
    "on_pause": true,
    "on_cost_threshold_pct": 80
  }
}

What the agent can vs cannot do (v1)

Surface	Agent CAN	Agent CANNOT
`MappingJob`	Trigger on upload + cron, poll, summarise	Cancel a running job (deferred)
`PartnerMappingResult` (unmatched)	Search candidates, file proposed matches as pending	Auto-link a result
`PartnerMappingResult` (matched)	Read, count, report	Modify or unlink
`MismatchReport`	`OPEN → IN_PROGRESS` (rule-gated, default off), group, post proposed resolution	Auto-mark `FIXED` or `REJECTED`
`ReferenceHotelDuplicateReport`	Read + summarise	Anything mutating (cross-tenant golden data)
Coverage statistics	Compute, alert, weekly digest	—
`mapping_mode_preference`	Read	Change (rule-gated, default off)
Exports	Read	Auto-export (rule-gated, default off)
Bulk partner updates	Nothing	Nothing
Data sources (inbound)	Auto-pull (default on once configured)	Pull from unconfigured sources
Data sinks (outbound)	Auto-push (rule-gated, default off)	Push to unconfigured sinks
Memory + pending items	Read/write its own	—

Versioning

Every rule-set save creates a new row with version = max(version) + 1 and a supersedes_id pointing to the previous version. Every AgentRun records the version it executed under. The UI shows “this action was taken under rule set v3” alongside historic runs.

Editing rules

Web UI
API

Go to Agents → [your agent] → Settings → Rules. Toggle the rule, click Save. Active cycles finish under the old rule set; the next cycle picks up the new one.

curl -X POST https://api.mapping.travel/api/v1/agents/{id}/rule-sets \
  -H 'X-API-Key: mt_...' \
  -H 'Content-Type: application/json' \
  -d @new-rules.json

Returns the new version with supersedes_id set.

Agents overview — what agents are and the trust model.
Configuration reference — field-by-field.
Audit and undo — every rule-set change is audit-logged.
Cost and limits — separate from rules but co-enforced.

Get Started

Core Concepts

Guides

Delivery destinations

MCP

Agents

Orchestration + triage, not confidence judgement

Rule set JSON shape

What the agent can vs cannot do (v1)

Versioning

Editing rules

​Orchestration + triage, not confidence judgement

​Rule set JSON shape

​What the agent can vs cannot do (v1)

​Versioning

​Editing rules

​Related

Orchestration + triage, not confidence judgement

Rule set JSON shape

What the agent can vs cannot do (v1)

Versioning

Editing rules

Related