Managing advertising performance often means jumping between dashboards, comparing metrics, reviewing automation rules, and manually looking for optimization opportunities.
Birch AI helps you do all of that with simple questions. Whether you need to understand why ROAS dropped, find your best-performing campaigns, audit automation rules – including drafts and rule logs – or generate new automations, Birch AI turns your workspace data into actionable recommendations in seconds – and with Meta MCP connected, it can act on your Meta account directly, not just analyze it.
Unlike general-purpose AI tools, Birch AI is built specifically for performance marketers and understands advertising platforms, marketing metrics, and automation workflows out of the box.
Accessing Birch AI
To open Birch AI:
Click Birch AI in the top-right corner of the platform.
The chat window will open with suggested prompts to help you get started.
Ask a question about your advertising performance, automation setup, or workspace data.
Want more room to work? Click Full screen to expand the chat view:
This takes you to the Home tab, where all your past chats are stored and accessible from the left sidebar:
What can Birch AI do?
Performance analysis
Birch AI can analyze performance data across:
Meta Ads
TikTok Ads
Google Ads
Snapchat Ads
Facebook Pages
Google Analytics
It can help you:
Understand performance trends and changes
Compare results across platforms
Analyze ROAS, CPA, CPC, CPM, CTR, and revenue
Identify optimization and scaling opportunities
Generate automated rules in drafts
Automation analysis
Birch AI can review your Meta and TikTok automation rules – both active rules and rule drafts – and help you:
Identify overlapping or conflicting rules
Audit your automation strategy
Recommend improvements
Suggest additional automations
Explain existing rule logic, including logic still sitting in a draft you haven't published yet
Analyze rule activity logs to explain what a rule actually did, and when
Rule generation
Describe your goal, and Birch AI can generate Meta/TikTok Ads automation rules directly in Birch. For example, you can ask Birch AI to:
Create a scaling rule
Generate a CPA protection rule
Suggest a starter automation strategy for a new account
Build a creative testing workflow
What Birch AI can set up in a rule
Custom timeframes – use any of your saved timeframes, or have Birch AI create a new one (e.g., "last 3 days excluding today").
Metric-to-metric comparisons – compare one metric against another instead of a fixed value (e.g., "CTR today is lower than CTR over the last 7 days").
Metric level – check a condition at the current item, parent, or ad account level (e.g., "pause an ad if its ad set's CPA is above $30").
Ad account–level Notify rules – get alerted based on account-wide performance (e.g., "notify me if account spend today exceeds $5,000").
Specific items – apply a rule only to selected campaigns, ad sets, or ads (e.g., "only campaigns containing 'Prospecting' in the name").
Generated rules are created as drafts, allowing you to review and edit them before publishing.
Custom metrics
Birch AI can also help you work with Custom Metrics – calculated performance values that go beyond standard platform metrics.
With Birch AI, you can ask it to:
Analyze an existing custom metric and flag whether it needs fixes or improvements (all platforms)
Analyze a custom metric used inside an automation rule's condition logic (Meta only)
Create a custom metric using a formula or based on a Google Sheet, at the workspace or ad-account level (all platforms)
Once created, a custom metric can be used in reports and as a condition inside automation rules.
👉 See the Birch AI Prompting Guide for ready-to-use prompts.
Get the most out of Birch AI
Birch AI works out of the box, but two optional connections provide significantly more context, leading to sharper, more relevant insights.
Connect Meta Ads MCP
Meta MCP is Meta's official connector that gives Birch AI deeper access to your Meta ad account – from live performance data to industry benchmarks, and the ability to pause/start and edit campaigns, ad sets, and ads.
👉 See Meta MCP Tools for what it adds and how to connect it.
Add Business Context
Business Context lets you save reusable information about your business - your goals, funnel, KPIs, or anything Birch AI should always know - so you don't have to repeat it in every conversation. It doesn't count toward your usage limits.
Best practices
To get the most accurate results:
Be specific about what you want to analyze.
Mention ad account names when working with multiple accounts.
Ask focused questions instead of combining many requests into one prompt.
Use rule names instead of rule URLs when analyzing automations — this now applies to both active rules and drafts.
When creating a rule, describe the condition, timeframe, and which campaigns, ad sets, or ads it should apply to.
Ask follow-up questions to build on previous responses.
Current limitations
While Birch AI supports a wide range of performance and automation analysis tasks, there are a few limitations to keep in mind.
Large accounts
In accounts with very large numbers of campaigns, ad sets, or ads, Birch AI may ask you to narrow the scope of your request to ensure accurate results.
Automation analysis
Currently, Birch AI can analyze Meta and TikTok automation rules only. Rule analysis is limited to active rules connected to ad accounts and does not include rule activity logs or folder information.
The following features are not currently supported:
Automation rule analysis and generation for Google Ads, or Snapchat
Cohort analysis
Custom Metrics based on the Attribution platform data
Top/Bottom ranking requests
Simultaneous conversations across multiple browser tabs
Privacy & Security
Birch AI uses data available within your Birch workspace, including advertising performance data and automation rule configurations. Your data is processed only to answer your requests and is never used to train external AI models. For more information, please refer to our Privacy Policy.
FAQ
Which large language model (LLM) does Birch AI use?
Which large language model (LLM) does Birch AI use?
Birch AI is powered by Open AI GPT 6 Luna model, chosen for its speed and efficiency in processing complex campaign data and delivering precise, actionable insights. The Birch team is continuously evaluating additional state-of-the-art models to expand capabilities and ensure you always get the best possible experience.
What kind of data does Birch use to power its AI?
What kind of data does Birch use to power its AI?
Birch AI is powered by your connected ad account data – including campaign performance metrics, spend breakdowns, automated rule configurations, rule drafts, and rule activity logs – all organized to deliver fast, accurate insights and smarter decision-making for your paid media strategy.
Does Birch share my data with LLM providers?
Does Birch share my data with LLM providers?
Birch AI is built with your data privacy and security as a top priority. LLMs are engaged solely to process your queries and never use your data for model training or service improvement. All data handling fully complies with our Privacy Policy and strict enterprise privacy standards.
How is it different from Meta Ads MCP?
How is it different from Meta Ads MCP?
Birch AI and Meta MCP work together. Birch AI is a purpose-built assistant inside the Bïrch app, with access to your business context, rules, and performance history. Meta MCP is an official connector you use from the same Birch AI interface – it adds Meta-specific capabilities like plain-language ads library search, performance vs. industry benchmarks, and now the ability to pause and edit campaigns, ad sets, and ads. See Meta MCP Tools for details.
Can I use Birch AI outside of Birch?
Can I use Birch AI outside of Birch?
No, Birch AI is exclusively available within the Birch platform. It is deeply integrated with your connected ad accounts and workspace data, which means it can only operate within the Birch environment to deliver accurate insights and rule suggestions.