Can an AI agent view our signal data?

Yes. With the Read permission, an agent can list the cleaned, customer-facing signal activity for a specific lead or account, newest first, or pull a quick rollup of activity by type. It sees the same mapped signals you see in the app, not raw payloads, and always scoped to your one workspace.

Can an agent find accounts that recently turned hot?

Yes. With the Read permission, an agent can filter and sort accounts by propensity and find ones whose propensity recently changed — for example, accounts that turned hot this week — the same information available in Browsing Accounts.

Can an agent see why an account or lead was scored the way it was?

Yes. With the Read permission, an agent can read the AI Assessment Reasoning behind a score, not just the score itself, along with the score's history over time.

Can an agent check whether an evaluation was pushed to our CRM?

Yes. With the Read permission, an agent can check whether an account's latest evaluation has reached your connected destinations and when — read-only visibility, not a trigger to push.

Can an agent tell me how much of our monthly scoring allowance is used, or why some accounts aren't scored yet?

Yes. With the Read permission, an agent can check your Evaluated Accounts and Signals usage for the current billing period, and will flag when scoring is paused because the monthly Evaluated Accounts allotment has been used — the likely reason some accounts look unscored or stale until the next billing period, or until overages are turned on.

Can an agent build or change our ICPs?

Yes, with the Configure permission. An agent can create and edit ICPs, adjust eligibility and scoring rules, and manage buying-group roles — the same things you can do in the ICP builder.

Can an agent connect our CRM?

An agent with the Configure permission can start a CRM connection, but a person still has to complete the provider's sign-in and approval. The agent hands you off to the CRM's own login rather than connecting silently.

What can an agent do with only the Read permission?

Look, but not touch — browse leads and accounts, filter by propensity and recent changes, read evaluations, scores and reasoning, check destination push status, review cleaned signal activity, and inspect your ICPs, signal mappings, and integration status. It can't change anything or correct data without additional permissions.

What Agents Can Do - TrailSpark Docs

Overview

An agent connected through Agent Access can do much of what you do in the app — as long as you've granted the matching permission. This page walks through the most common use cases and shows which of the three permissions — Read, Configure, Data corrections — each one needs.

Everything below is scoped to the single workspace the agent was granted access to, and account re-evaluation stays off unless you've explicitly allowed it (and set a daily limit).

Review accounts, leads, and evaluations

Needs Read

An agent can find and read your scored accounts and the people in them:

Search leads and open a single lead's full profile, or list the leads that belong to one account
Browse target accounts and open a single account, including firmographics and connected-CRM details
Filter and sort accounts by propensity (High / Medium / Low), and find accounts whose propensity recently changed — for example, "which accounts turned hot this week"
Read evaluation results and history — the score, the AI Assessment Reasoning behind it, and how it's changed over time
Pull a workspace-wide rollup of how many accounts are hot, warm, and cold right now, and how that mix is trending

This is the foundation for reporting, triage, and questions like "what's happening with account X" or "what changed this week." See Browsing Accounts for the same information in the app.

Propensity filtering and the workspace rollup show scores, not the reasoning behind them. For "why is this account scored high (or medium, or low)?", ask about that one account — the agent pulls its AI Assessment Reasoning.

Check your monthly scoring usage

Needs Read

An agent can check how much of your monthly Evaluated Accounts allotment has been used — the same count shown on Settings > Usage — along with your Signals usage, and whether scoring is currently paused. Ask things like "how much of this month's scoring allowance is left" or "why isn't this account scored yet."

When your workspace has used its monthly Evaluated Accounts allotment and overages are off, an agent's account lists (browsing accounts, the hot/warm/cold rollup) add a note that scoring is paused. Some accounts may look unscored or stale simply because they're waiting for the next billing period, not because anything is wrong. See Usage Tracking for the full picture, including overages and upgrading.

Review cleaned signal activity

Needs Read

An agent can list the cleaned, customer-facing signal activity for a specific lead or a specific account, newest first, or pull a quick rollup of how much activity of each type an account has had. These are the same mapped signals you see in the app — page views, form submissions, product usage, and so on — not raw webhook payloads.

Activity is always anchored to one lead or one account at a time, so an agent reviews a specific entity's timeline rather than pulling a workspace-wide firehose. A typical flow is: search for a lead or account, then read that entity's recent signal activity (or its rollup) to explain why it's scoring the way it is.

Check destination push status

Needs Read

An agent can check whether an account's latest evaluation has been pushed to your connected destinations (CRM or other platforms) yet, and when. This is read-only visibility into delivery status — it doesn't trigger a push or change any destination configuration. See Destinations Overview for what gets pushed and where.

Build and refine ICPs

Needs Configure

An agent can do the same ICP work you'd do in the ICP builder:

Create a new ICP or update an existing one
Adjust eligibility rules (which accounts match the ICP) and scoring filters (what's worth scoring)
Manage buying-group roles and their point weightings
Preview the impact of a change before committing, and — if you've allowed re-evaluation — re-score affected accounts

See ICP Creation for how these pieces fit together.

Re-scoring accounts is billable, so it only happens when you've turned on re-evaluation for that key or connected agent, and it stays within the daily limit you set.

Connect a CRM or other integration

Needs Configure

An agent can check the status of your integrations and start a CRM connection — but a person still finishes it. Rather than connecting silently, the agent hands you off to the provider's own sign-in and approval screen (for example, HubSpot or Salesforce), so the connection is always completed by someone who can authorize it.

See CRM Integration for the connections TrailSpark supports.

Map incoming signals

Needs Configure

An agent can manage how raw incoming events become the cleaned signals you score on:

List and read your signal-mapping rules
Create or update a rule, and activate or deactivate it
Preview what a rule would match, and check the impact before turning it on

This is the same signal-mapping work described in Signals Overview — useful for keeping mappings tidy as your sources change.

Correct data and give feedback

Needs Data corrections

When an agent spots something wrong, it can help fix it:

Correct a person's buying-group role on an account
Submit feedback on an evaluation to help improve future scoring

These corrections feed the same learning loop as corrections you make by hand in the app.

Permissions at a glance

Use case	Permission
Review accounts, leads, evaluations	Read
Filter/sort accounts by propensity, find recent propensity changes	Read
Review cleaned signal activity (and its rollup by type)	Read
Check destination push status	Read
Check monthly scoring usage, and whether scoring is paused	Read
Inspect ICPs, mappings, integration status	Read
Build and refine ICPs	Configure
Connect a CRM (start the flow)	Configure
Map incoming signals	Configure
Manage destinations	Configure
Correct roles and give evaluation feedback	Data corrections

Grant only the permissions an agent actually needs — see Agent Access Overview for the full permission model, and Managing Agent Keys or Connecting an AI Agent to set one up.