L
LMS / Performance

Lattice AI Integration

Connect Lattice to BeforeQuery for grounded AI answers and agent actions across LMS / Performance.

What is it?

About Lattice

Lattice is one of the LMS / Performance platforms BeforeQuery connects to. Once linked, the platform's data becomes a first-class source for grounded AI answers and a target for policy-gated agent actions — the same identity, approval, and audit-log guarantees every other integration ships with.

Setup

How to connect Lattice

  1. Step 01

    In the BeforeQuery dashboard, go to Integrations → LMS / Performance and select Lattice.

  2. Step 02

    Sign in to Lattice with an account that has permissions to grant BeforeQuery the LMS / Performance scopes required.

  3. Step 03

    Confirm the connection. Lattice is now available as a source and action target for every playbook in your workspace.

How BeforeQuery uses Lattice

What the agent does with your Lattice connection

  • 01

    Read Lattice learning progress and performance records to power personalized learning and coaching moments.

  • 02

    Assign, remind, and track mandatory training completion — with escalation when deadlines slip.

  • 03

    Draft performance review inputs grounded in Lattice feedback, 1:1 notes, and OKR progress.

  • 04

    Deliver micro-learning "just in time" — when someone asks a question, surface the relevant training module alongside the answer.

Use cases

What teams actually do with the Lattice integration

Mandatory training completion cascade

New employees + annual re-certifications get auto-assigned in Lattice. BeforeQuery nudges at 7, 3, and 1 day before deadline; escalates to manager at overdue; sends completion certificates when done.

Just-in-time learning

When someone asks a question that has a Lattice training module attached, BeforeQuery answers the question AND surfaces the training as optional deeper learning. Higher engagement, less "you should take a course" cold-selling.

Performance review prep

Before a review cycle, BeforeQuery drafts a prep packet per employee: OKR progress, Lattice training completion, 360 feedback themes, prior-cycle goals. Reviewers open a ready-made template instead of starting blank.

Answer questions grounded in Lattice

Employees and customers ask Lattice-related questions in Slack, Teams, or the widget — BeforeQuery answers with the exact Lattice record shown alongside the response. No context switching, no "log into LMS / Performance to check" round-trips.

Lattice — Frequently Asked Questions

Common questions about connecting BeforeQuery to Lattice.

Only when explicitly scoped to a playbook that needs it — e.g., review-prep. Feedback text stays in Lattice; BeforeQuery surfaces summaries, themes, and status without duplicating the raw records into the KB.
Standard OAuth 2.0 where Lattice supports it, otherwise API-key or bearer-token auth. Credentials are stored encrypted at rest (AES-256-GCM) per workspace, never shared across customers, and rotated on request. The connection is scoped to the least-privilege set of scopes each playbook needs — you approve the scope list on install.
No. Your Lattice data feeds only your workspace's own agents and answers. Nothing is used to train a shared model, and nothing crosses workspace boundaries. Bring-your-own-model is available on Enterprise if you want to pin inference to your own OpenAI / Anthropic / self-hosted deployment.
Yes. Every Lattice integration is scoped at install time — you pick which resources, users, or record types are visible. You can further restrict per-playbook: a single playbook only touches the specific Lattice objects it needs. Scope changes take effect on the next sync.
Every write is logged with the acting user, the playbook that fired it, the exact operation, the target entity IDs, and the timestamp — all in the immutable audit log. Writes are rehearsable in simulation mode against a copy of live data before they touch Lattice for real.

Ready to connect Lattice?

Start free. No credit card required. Connect your first integration in under 5 minutes.