Regal Copilot — Capabilities, Use Cases, and Limits

1. Overview

What Copilot is

Regal Copilot is an AI assistant backed by agent-service. It works inside your Regal brand: AI agents, test cases, simulations, real calls and transcripts, contacts, journeys, IVRs, and task routing. Most actions are read-only; a smaller set creates or updates drafts, tests, or simulation runs (see section 3).

The primary Copilot reasoning model today is Claude Sonnet 5, which is capable of multi-step reasoning across long-context inputs

How requests are routed

Copilot decides which guided workflow applies (for example building an agent vs analyzing calls vs troubleshooting routing) from the user’s intent. Refining an existing agent is handled differently from building a new one from scratch.

Safety

Copilot asks before deleting or bulk-creating content. Agent changes are saved as drafts unless you explicitly confirm a publish. For Journeys and Routing Rules, only support read-only capabilities.
When Copilot loads your AI agent, journey, or IVR configuration, secret values in HTTP headers for webhooks and custom actions are masked so they are not included in what gets sent to the assistant to read.

In scope vs out of scope

In scope: Your Regal agents, calls, tests, simulations, journeys, IVRs, tasks, and contacts—even when the question is vague; Copilot should ask a short follow-up instead of refusing.
Out of scope: non-Regal questions, unrelated web research, or “analyze our entire warehouse” style asks.
In the works: Copilot does not run Looker, Snowflake, or broad “query the whole dataset” reporting. Where enabled, it can read Regal’s own observability metrics catalog (see section 2.13). We are actively adding data access for Copilot!

Framing — what works well vs. what’s harder currently

Where Copilot shines

For a deep dive on something specific—one journey and how it’s set up, one AI agent or small samples of calls / recording, one task’s routing history, or a similarly bounded question—Copilot is built to give quick, accurate guidance tied to what’s in Regal.

What’s harder (and still evolving)

Anything that depends on scanning across very large sets of records from a vague prompt (for example “show me every problem call last year” with no other detail) is difficult: answers may be partial, take multiple steps, or need you to narrow the ask. Broader “query everything” style work is not Copilot’s sweet spot today—see section 5 for scale and roadmap notes.

How to get better answers

Share specific anchors whenever you can so Copilot can narrow quickly instead of guessing across the whole brand. Examples that help a lot:

Calls / recordings: a call or recording id, disposition, or paste the Recording link if you have it.
Contacts: profile context—phone, email, name, or id—especially when the name is common.
Time: a date range or clear timeframe (“since the deploy Tuesday”, “last 48 hours”).
Automation: journey name or id, event name, or what changed and which version you care about.
Routing / tasks: Task id as shown in Regal, queue, or the agent you expected—plus what triggered the question (campaign, rule change, customer report).

Even one or two concrete details usually improve the answer more than a long story with no identifiers.

2. Tools Copilot has access to

Copilot’s MCP server registers the tools below (names are exact MCP identifiers).

2.1 Regal knowledge base

Tool	Typical use
`query-regal-kb`	Search or fetch relevant chunks from the official developer and support docs for Copilot replies and workflows.
`list-knowledge-bases`	List your brand's active knowledge bases with source counts.
`fetch-knowledge-base`	Inspect one knowledge base — source type, name/URL, status, and counts.

2.2 AI agents (list, fetch, build helpers, writes)

Tool	Typical use
`fetch-agent`	Fetch the active version of a specific agent variant, including its full configuration and prompt.
`fetch-latest-agent`	Fetch highest version (regardless of status: active, draft or deactivated) of a specific agent variant; use before `edit-agent` for `updates.version`.
`fetch-agent-version`	Fetch a specific historical version of an agent variant (lookup or diffs).
`list-agents` / `list-ai-agents`	List agents with filters (same handler, two names).
`list-ai-agent-variants`	Lists the variants of a specific agent.
`list-ai-agent-versions`	List version history for one agent (version, name, model, is_active), newest first.
`list-ai-agent-voices`	List available voices for the brand (name, provider, preview URL).
`create-agent`	Write — create a new voice or SMS AI agent.
`create-ai-agent-variant`	Write — create a new variant on an existing agent; saved at 0% traffic.
`set-variant-traffic-allocations`	Write — set traffic % across all variants of an agent (must sum to 100).
`edit-agent`	Write — update agent; always saves as draft.
`save-agent-live`	Write — publish an agent (or variant) live; requires explicit confirmation via `confirm_publish=true`.
`explore-agent-context`	Builder: compare existing agents as references before a new build.
`summarize-agent-plan`	Builder: compact plan for user confirmation before generation.
`generate-agent-config`	Builder / reference: section-by-section config guidance for `edit-agent`.
`get-prompting-best-practices`	Reference: voice prompt style, formatting, action invocation.
`get-ai-agent-tool-context`	Reference: action schemas, failures, deprecated patterns.
`list-ai-agent-templates`	List available AI agent templates.
`fetch-ai-agent-template`	Fetch a specific AI agent template.

2.3 Test cases

Tool	Typical use
`fetch-test-cases`	List test cases for an agent.
`create-test-cases`	Write — create tests (max 10 per call).
`edit-test-case`	Write — update one test case.
`propose-test-case-changes`	Build a test-case change proposal for review in chat before applying an edit.
`delete-test-cases`	Write — delete tests by id.

2.4 Simulations

Tool	Typical use
`start-simulations`	Write — start a simulation test run (`test_run_id`).
`get-simulation-progress`	Poll run status and per-case results until `completed=true`.
`list-simulation-runs`	List past simulation runs for an agent, newest first.
`fetch-simulation-transcript`	Read simulation transcript for analysis.

2.5 Production recordings and transcripts

Tool	Typical use
`list-recordings`	Filter and page recordings (e.g. agent, disposition, search).
`fetch-recording-transcripts`	Load transcript + metadata for up to five `recording_sids` per call.
`get-trackers-lookup`	Tracker lookup helper for transcript-related workflows.

2.6 Profiles and contacts

Tool	Typical use
`lookup-profile`	Resolve contact by phone, email, name, or external id.
`fetch-profile`	Full profile by id.
`list-profile-versions`	Profile version history for a contact (newest first).
`fetch-profile-version`	Load a historical profile snapshot by version number.
`fetch-profile-events`	Recent profile events (paginated).

2.7 Journeys

Tool	Typical use
`list-journeys`	Search / list journeys.
`fetch-journey`	Full journey by UUID (webhook headers masked).
`list-journey-versions`	Version history for a journey.
`fetch-journey-version`	Full payload for one version (diffs).
`list-profile-journey-executions`	List a contact's executions of a specific journey (newest first, paginated).
`get-profile-journey-execution-nodes`	Per-node detail of one execution — branches taken, webhook responses, task IDs.

2.8 IVRs

Tool	Typical use
`list-ivrs`	List IVRs for the brand. Filter by friendly ID or name.
`fetch-ivr`	Fetch a single IVR by ID, including the full node definition.

2.9 Event schema

Tool	Typical use
`list-event-definitions`	List known event names for a category (`regalVoiceEvent` or `customEvent`).
`get-event-schema`	Field names, types, and stable field IDs for one event (contact attributes via `identify`).

2.10 Task routing and queues

Tool	Typical use
`list-tasks`	List tasks with filters (state, queues, time window, etc.).
`fetch-task`	One task by customer Task id.
`get-task-events`	Routing / reservation timeline for a task.
`list-users`	Browse brand users/agents.
`fetch-user`	User/agent by email (capacity, queues, attributes).
`list-queues`	Queues and eligibility expressions.
`get-routing-rules`	Active routing rulesets.
`get-routing-rule-versions`	Version history for a ruleset.

2.11 Custom analysis fields and dispositions

Tool	Typical use
`list-analysis-data-points`	List custom ai analysis field definitions (paginate when `has_more`).
`create-analysis-data-points`	Write — create one or more custom ai analysis data points.
`edit-analysis-data-points`	Write — edit one or more existing custom ai analysis data points.
`delete-analysis-data-points`	Write — delete one or more existing custom ai analysis data points.
`list-dispositions`	Lists dispositions in the account.
`create-dispositions`	Write — creates dispositions (max 10 per call).
`edit-dispositions`	Write — updates existing dispositions (max 10 per call).

2.12 Brand configuration

Tool	Typical use
`get-brand`	Brand configuration: identity, timezone, business hours, compliance, skills, activity statuses, teams, communication sources, and more.

2.13 Data analysis

Available only when observability metrics are enabled for your brand.

Tool	Typical use
`list-metrics`	Return the catalog of available observability metrics (cubes, measures, dimensions). Call this first.
`query-metric`	Query one metric from the catalog — measures, dimensions to group by, time range or date range, granularity, filters.

2.14 Phone number management

Tool	Typical use
`list-business-profiles`	List your business profile(s).
`list-active-phone-numbers`	Lists your Regal provisioned phone numbers.
`list-branded-phone-numbers`	Lists your phone numbers that were uploaded for branded caller id and/or spam remediation.
`create-branded-phone-number`	Adds a phone number for branded caller id and/or spam remediation.
`update-branded-phone-number`	Updates a phone number for branded caller id and/or spam remediation, including registering/unregistering numbers for carriers.
`delete-branded-phone-number`	Deletes a phone number from branded caller id and/or spam remediation.

2.15 Copilot session UI

These render or load content in the Copilot session; they do not change Regal configuration.

Tool	Typical use
`send-thinking`	UI: collapsible “thinking” markdown.
`step-summary`	UI: short step progress markdown.
`publish-workflow-summary`	UI: publish a workflow summary card at the end of a major workflow.
`publish-agent-builder-trigger`	UI: surface the agent builder entry point.
`canvas`	UI: render a rich panel (table, chart, KPI cards, tabs). Available where enabled.
`read-attachment`	Load a CSV / PDF / image uploaded earlier in the session. Available where enabled.

2.16 Skills

Skills are guided workflows Copilot loads on demand; names are stable skill ids:

Skill	Use for
`build-agent-workflow`	Build a new single-state voice or SMS agent.
`build-multi-state-agent`	Build a new multi-state / branching agent.
`iterate-agent`	Change, fix, or improve an agent that already exists.
`generate-test-case-prompt`	Generate test cases for an agent.
`run-simulations-workflow`	Run simulations / test cases against an agent.
`post-simulation-analysis-workflow`	Analyze results of a completed test run.
`analyze-transcript`	Analyze a single call recording.
`analyze-transcripts`	Analyze multiple recordings — patterns, themes, filter batches.
`analyze-metrics`	Investigate measured agent performance metrics, trends, regressions.
`profile-investigation`	Investigate contact / profile data, versions, and field changes.
`troubleshoot-journey`	Investigate or diff a single journey.
`audit-journeys`	Cross-journey audit or inventory spanning all journeys.
`troubleshoot-ivr`	Investigate, explain, or compare IVRs.
`troubleshoot-task-routing`	Investigate task routing, queues, and rule changes.

3. Copilot write capabilities

Copilot creates new AI agents and saves draft updates to existing agents. Copilot can also publish an agent live, but only when you explicitly confirm that publish step—it never switches production traffic on its own.

Copilot creates, edits, and deletes test cases for simulations. Large creates happen in batches of 10; deletes need explicit confirmation.

Copilot can start simulation runs. That exercises your tests against the agent; it does not change live call traffic.

Copilot can create, edit, and delete custom analysis data points and create / edit dispositions.

Copilot can add, update, delete carrier registrations for your branded/spam phone numbers. You still wait on carrier approval timelines.

All other actions are read-only. For the exact MCP operations behind each bullet, see section 2.

4. Use cases and good-to-knows

Use case	Example asks	Strong when	Good to know
New agent (single flow)	“Build an inbound…”, “Walk me through billing.”	End-to-end draft; uses queues that already exist in your account.	Saved as a draft. Going live is a separate, explicitly confirmed step.
New agent (branching / multi-step)	“Triage then schedule”, “Graph with qualification.”	Plans branches before filling in details.	Transfers and actions work differently than in a simple single-flow agent—expect Copilot to follow Regal’s product rules, not copy settings blindly across styles.
Improve existing agent	“Review my script”, “Fix the transfer.”	Recommendations tied to your current configuration.	Saves as a draft by default. Knowledge libraries stay managed in the Regal app.
Test cases	“Generate 15 tests”, “Import this CSV.”	Mix of happy paths, objections, and edge cases.	Large imports are created in batches of 10. Deletes need a clear yes from you.
Simulations	“Run all tests”, “What happened on the last run?”	Clear pass/fail and links back to transcripts.	Long runs may pause—you can ask Copilot to keep checking. If one scenario never finishes, the test wording or end condition may need tightening.
Real calls & transcripts	“What happened on this call?”, “Find calls where…” "Where did customers drop off in these AI agent calls?"	One-call diagnosis; OR trends across a bounded set of calls (<100)	For many calls at once, start with a shorter time range or tighter filters—Copilot works in chunks and will ask you to continue or narrow as it goes. Stay within 100 calls for good analysis results - we are actively improving the bulk capabilities here. Stay tuned! Paste recording links directly to Copilot and ask questions.
Agent performance metrics	“How are my agents doing this week?”, “Did latency get worse?”, “Which actions are failing?”	Bounded metric questions with a clear timeframe; comparing agents or versions.	Requires metrics to be enabled for your brand. Copilot answers from the metrics catalog—if a measure is not in the catalog, it cannot be queried.
Task routing	“Why didn’t [email protected] get this taskID W123?”, “Was this scheduled callback task snoozed?”	Explains routing, eligibility, and recent rule history. Explain "what happened" for a particular task.	Use the same Task id wording Regal shows in the UI to debug.
Journeys	“Where are all the conditional nodes with {{contact.age}} filter in this Journey?” "What is the difference between Journey 123 and Journey 345?	Scan across large Journey definitions to find gaps or hard-to-identify issues.	Single Journey questions perform best. For a contact's run through a journey, Copilot can pull the execution history and per-node detail (branches taken, webhook responses, task IDs).
IVRs	"Walk me through what IVR 20 does", "Where is {{contactPhone}} referenced?", "What changed between these two IVRs?"	End-to-end flow explanation and node-level detail.	Reference the IVR by friendly ID or name; Copilot resolves it to the full node definition.
Contact Profiles	"What is the value for {{contact.product_type}} for this contact last Thursday?" "What were the values for this event on the profile? Should it have triggered Journey 123?"	Find profile attributes at a point in time; find events for a contact	Copilot can load historical profile snapshots by version, not just the current record.
Capabilities	“What can you do?” — answer with categories (agents, tests, calls, routing, journeys), not a long internal feature list.

5. Gaps and what’s coming

Topic	Today	What’s coming / how to set expectations
Large datasets & analytics	Copilot is not a SQL, spreadsheet, or warehouse front end. Where enabled, it reads Regal's own metrics catalog (`list-metrics` / `query-metric`)—it cannot answer “query every call we’ve ever made” in one step.	Treat cross-system analytics as work in progress—use Regal Intelligence, metrics, recordings, and simulations inside Copilot, and Looker / Snowflake / BI outside it for now.
Call & transcript analysis at scale	Searches and deep reads are staged; Copilot asks you to confirm between waves; rough caps (~25 transcripts per deep pass, ~100 per focused investigation unless you narrow or continue; ~200 calls listed per search wave when only metadata is needed).	Customers should narrow time ranges or filters for “all calls” style questions, or work in multiple Copilot sessions.
Scheduled workflows	Allow users to schedule automated sessions to automate repeatable review workflows, or automatically make improvements.	Richer agentic runs that need fewer explicit “click to continue” checkpoints—while still respecting guardrails—are planned; expectations will be communicated as those modes ship.