Statsig connector for AI agents

Tools your experimentation agent reaches for on Statsig, scoped per user.

CALL ANY TOOL

96 tools for feature flags and experiments in Statsig: create, update, enable, disable, and launch gates, start, ship, and abandon experiments, manage dynamic configs, segments, layers, and holdouts, and read Pulse results, metrics, and audit logs.

statsig_abandon_experiment

Abandon experiment

Abandon an experiment, stopping it without shipping any group. Returns a confirmation message. Use statsig_abandon_experiment to stop a failed or invalid test. Use statsig_ship_experiment to launch a winning group.

Parameters

Name

Type

Required

Description

decision_reason

string

Required

Reason for abandoning, recorded on the experiment. Example: Logging bug invalidated the results.

experiment_id

string

Required

ID of the experiment, as returned by statsig_list_experiments. Example: checkout_button_color_test.

statsig_add_gate_overrides

Add gate overrides

statsig_archive_dynamic_config

Archive dynamic config

statsig_create_dynamic_config

Create dynamic config

Create a new dynamic config that serves JSON values to users, optionally with targeting rules. Returns the created dynamic config, including its generated id. Use statsig_create_dynamic_config for a new config. Use statsig_update_dynamic_config to change an existing one.

Parameters

Name

Type

Required

Description

name

string

Required

Display name of the dynamic config. Statsig derives the ID from it in snake_case. Example: Pricing Page Config.

default_value

object

Optional

JSON object served when no rule matches. Example: {"currency": "USD", "show_banner": false}.

description

string

Optional

Short summary of what this is used for. Example: Rolls out the redesigned checkout to web users.

id_type

string

Optional

Unit ID type the entity evaluates on, such as userID, stableID, or a custom unit ID type from statsig_list_unit_id_types. Example: userID.

is_enabled

boolean

Optional

Whether the config is enabled. A disabled config serves its default value to everyone. Example: true.

rules

array

Optional

Targeting rules as a JSON array. Each rule needs a name, a conditions array (same shape as gate conditions) and a returnValue JSON object served to users who match. passPercentage (0-100) is optional. Example: [{"name": "EU users", "passPercentage": 100, "conditions": [{"type": "country", "operator": "any", "targetValue": ["DE", "FR"]}], "returnValue": {"currency": "EUR"}}]

schema

string

Optional

Optional JSON Schema (Draft 2020-12), as a string, that every return value must satisfy. Example: {"type": "object", "properties": {"currency": {"type": "string"}}}.

tags

array

Optional

Tag names to attach, as a JSON array of strings. Tags must already exist (see statsig_list_tags). Example: ["checkout", "web"].

target_apps

array

Optional

Target app names to scope evaluation to, as a JSON array of strings (see statsig_list_target_apps). Example: ["web_app"].

team

string

Optional

Name of the owning team (Enterprise only). Example: Growth.

team_id

string

Optional

ID of the owning team (Enterprise only), as returned by statsig_list_teams. Example: 2bC4dE6fG8hI0jK2lM4nO6.

type

string

Optional

Lifecycle type: PERMANENT to mark the config long-lived, TEMPORARY to unmark it. Allowed values: PERMANENT, TEMPORARY. Example: PERMANENT. One of: `PERMANENT`, `TEMPORARY`.

statsig_update_experiment_overrides

Update experiment overrides

statsig_update_holdout

Update holdout

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Statsig tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["statsig"], toolNames: [
    "statsig_list_gates",
    "statsig_get_experiment_pulse_results",
    "statsig_disable_gate"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Show Pulse results for the new-checkout experiment" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["statsig"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Show Pulse results for the new-checkout experiment" }],
  tools,
});

// Execute the tool call with the user's vaulted Statsig API key
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["statsig"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Show Pulse results for the new-checkout experiment" }],
  tools,
});

// Tool call runs with the user's vaulted Statsig API key
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["statsig"] }, pageSize: 100,
});

const agent = new Agent({
  name: "experimentation_agent",
  model: "gemini-2.5-pro",
  instruction: "Statsig tools scoped to this user",
  tools,
});

await agent.run("Show Pulse results for the new-checkout experiment");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Statsig tool. Click to copy, paste into your agent, done.

Feature gates

Copy the prompt

Copied

Create a feature gate called new_onboarding for 10% of users.

Copy the prompt

Copied

Disable the checkout_v2 gate now.

Copy the prompt

Copied

Has the legacy_search gate been checked in production in the last 7 days?

Experiments

Copy the prompt

Copied

Show Pulse results for the new-checkout experiment.

Copy the prompt

Copied

Ship the test group of the pricing-page experiment.

Copy the prompt

Copied

List experiments that are currently active.

Configs and audit

Copy the prompt

Copied

Update the default value of the rate_limits dynamic config.

Copy the prompt

Copied

Add these 20 user IDs to the beta-testers segment.

Copy the prompt

Copied

Show audit log entries for gate changes made yesterday.

SEE HOW AUTH WORKS

Each user connects their own Statsig API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Statsig

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Statsig

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Statsig

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Statsig

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other developer tools and analytics connectors.

Engineering Teams

DevOps assistant agent

Polls GitHub for failing checks and stale PRs, opens Linear issues for the ones that need work, and posts a daily digest to Slack. It acts as the engineer, not a shared service account.

Engineering Teams

Engineering standup agent

Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Statsig API key looks fine in a demo. In production every gate change looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Statsig today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Statsig as the user or through a shared API key?

As the user. Each user connects their own Statsig API key once, and Scalekit sends it with every call. Gate changes, experiment launches, and config edits the agent makes are attributed to that user in your audit trail, not a shared service account.

Where is the Statsig API key stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Statsig?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example read and Pulse tools without statsig_delete_gate and statsig_delete_experiment, which permanently remove a gate or experiment. Archive tools retire them while keeping history. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Statsig access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Which Statsig project does the agent work in?

The project the user's Statsig API key belongs to. statsig_get_project returns that project's ID and name, and gate, experiment, config, and metric tools act inside it. Team tools such as statsig_list_teams need Statsig Enterprise.