Integration · Analytics and data
AI agents for Optimizely
Run Optimizely experiments: list projects and Web Experimentation experiments, read an experiment and its results per variation and metric, start, pause or resume an experiment.
- Actions
- 9
- Read
- 6
- Write
- 3
Actions
What your agents can do in Optimizely
Run Optimizely experiments: list projects and Web Experimentation experiments, read an experiment and its results per variation and metric, start, pause or resume an experiment, and for Feature Experimentation list flags and rules, turn a flag on or off in an environment, and switch a rule (A/B test or targeted delivery) on or off (Optimizely REST API v2 and Flags API v1).
Read 6
Look things up. Nothing changes.
List projects
Lists the account's projects (in result): each with id, name, platform (web for Web Experimentation, custom for Feature Experimentation), status and account_id.
List experiments
Lists a Web Experimentation project's experiments (in result).
Get an experiment
Reads one Web Experimentation experiment: name, status, type, audience conditions, traffic allocation, variations with their weights and actions, and metrics.
Get experiment results
Reads an experiment's results: per metric (index 0 is the primary metric) the results per variation (value, lift against the baseline, statistical significance) and conclusion.
List feature flags
Lists a Feature Experimentation project's flags: each with key, name, description, archived, variable_definitions and environments.
List flag rules
Lists a Feature Experimentation project's rules (A/B tests, multi-armed bandits and targeted deliveries) in one environment.
Write 3
Create, change or send.
Start, pause or resume an experiment
Changes a Web Experimentation experiment's state: start makes it live.
Turn a flag on or off
Turns a feature flag on or off in one environment (its whole ruleset): off serves every user the default "off" variation straight away.
Start or stop a rule
Switches one rule of a flag (an A/B test or a targeted delivery) on or off in an environment, leaving the flag's other rules as they are.
A person can approve first
Any write action can be set to wait for a person's approval before it runs, so an agent asks before it changes anything.
Connection
How it connects
Connect it once in the console, then give it to the agents and workflows that need it.
Paste an API key from your Optimizely account.
What you enter
- Personal access token
Kept safe
- Credentials are stored encrypted with your organization's own keys.
- They are opened only by the process that makes the call, at the moment it runs, and never go into a prompt or the browser.
- Calls go only to the tool's own servers.
Ideas
Ideas to start with
Starting points made only from the actions above. Mix them with any other tool your agents can use.
- 01
Ask about your Optimizely data
Ask a question in plain words. The agent can list projects, list experiments or get an experiment in Optimizely, then answers with what it found.
- 02
Let an agent update Optimizely
Have the agent start, pause or resume an experiment or turn a flag on or off in Optimizely as part of a larger task. Turn on approval and a person signs off on each change first.
- 03
Share what it finds in Slack
Give one agent Optimizely and Slack: it can list projects in Optimizely and post a summary to a Slack channel in the same run.
Works well with
More Analytics and data tools
- Google Analytics4 actionsRun Google Analytics 4 reports (users, sessions, views, conversions by page, source, country …), see who is on a site right now, and find the properties a person can read, signed in with the person's own Google account.
- Mixpanel4 actionsSend events to a Mixpanel project and query event counts, segmentation and saved Insights reports, in the US, EU or India data residency, with a service account.
- Amplitude14 actionsSend events to an Amplitude project and read its analytics: event counts and segmentation, funnels, retention, active users, saved charts, cohorts and one user's activity, in the US or EU data center.
- PostHog5 actionsQuery product analytics with HogQL, list recent events and persons, check which feature flags a user gets, and add annotations, in a PostHog Cloud project (US or EU) with a personal API key.
- Power BI5 actionsList Power BI workspaces and semantic models, refresh a model, push rows into a push dataset and run DAX queries, as the signed-in person.
- Tableau10 actionsFind workbooks, views and published data sources on Tableau Cloud or Tableau Server, read a view's data as CSV, query a published data source with the VizQL Data Service, search content through the Metadata API.
FAQ
Optimizely and MyDeepAgents
Can MyDeepAgents connect to Optimizely?
Yes. The Optimizely connector has 9 actions: 6 read and 3 make changes. Your agents can call them as tools, and your workflows can run them as steps.
How do I connect Optimizely?
Paste an API key from your Optimizely account. You'll need: Personal access token. Credentials are stored encrypted with your organization's own keys and are opened only at the moment of a call.
Can an agent change data in Optimizely without asking?
Only if you let it. Each of the 3 actions that change data can be set to wait for a person's approval before it runs.
Can I use Optimizely in workflows as well as agents?
Yes. Every Optimizely action also works as a step in a workflow, and the same connection serves your agents and your workflows.
Early access
Put Optimizely to work
Connect it in a few minutes, give an agent the actions it needs, and decide which changes wait for a person.