Trellis Overview and Best Practices
Table of Contents
Trellis, Sprout's AI Agent, is designed to help your team work faster, smarter and with deeper insights. It empowers your team to leverage social intelligence to enhance the quality of your brand’s processes, products and services.
You can ask questions to Trellis directly and receive direct, contextual answers rooted in social data. It can also surface insights without the need to sift through reports and configurations.
Curious how AI can save you time? Take AI & Automation in Sprout: Work Smarter, Not Harder in Sprout Academy, a quick 32-minute course on Sprout's built-in AI tools.
Capabilities
Here's a quick overview of the ways Trellis can contribute to your workflows and processing social data
- Publishing pipeline: Review drafts, scheduled posts, and queued posts; filter by network, date, profile, or tag/campaign.
- Published-post performance: Review post metrics and permalinks; compare results by network, post type, content category, profile, or day of week; find top or bottom posts by a metric. Post metrics available for analysis with Trellis would include: Impressions, Engagement Rate, Total Engagement, Link Clicks, Comments, Shares, and Reactions.
- Listening: Review topics’ public and, where available, owned conversation; summarize messages; examine sentiment, volume, engagement, impressions, and network activity; view trends and breakdowns; and build or refine topic queries.
- Inbox and care: Find inbound messages using filters such as text, date, profile, network, sentiment, intent, and reply or completion status; review ingested conversations and replies.
- Cases: Find and filter cases by status, priority, assignee, queue, type, text, and dates.
- Account references: Look up connected profiles, users, and tags or campaigns to support those workflows.
Trellis Resources
Feature Overviews
- How to Use Trellis in Sprout Social Listening
- What is Trellis Studio?
- Trellis Studio Skills Deep Dive
Maximizing Credits, Prompts and Trellis Plus
- Pro Tips for Writing Great Prompts for Trellis
- Understanding and Maximizing Your Trellis Credits
- Trellis Plus: Extended Access to AI Features
- Trellis Plus: Shared Credits
- Trellis Fair Use Cap
Getting started with Trellis
It’s easy to get started using the Trellis in Sprout. To begin:
-
Navigate to the global toolbar on the left side of the screen, and then click the Ask Trellis icon:
- Trellis will appear on the right hand side of your session.
- Enter your conversation prompt into the input box.
- Press Enter.
Trellis Chat History
Trellis automatically stores your chat history and allows you to re-engage a previous conversation. This is useful when you want to use the same line of questioning with new data over time. Additionally, you can keep a thread open and come back after a meeting with new information to dig deeper.
To switch between chats, click the history button:
Click Manage at the bottom of your list to rename or delete any chats as needed:
To start a new chat, click the pencil icon in the upper right hand corner of your current chat window:
From here you can start a new conversation. Conversation names are dynamically created but can be changed.
How to write a good prompt with Trellis
Writing a good prompt is key to extracting the insights that matter most to your brand. Use the following tips to craft the best prompts: Pro-Tips for Writing Great Trellis Prompts
Using Trellis Studio
Trellis Studio allows teams to set up recurring conversation starters, called skills, for repetitive analysis. Choose from a number of pre-built skill templates and schedule those templates to run at a cadence that works best for you! You can customize select fields (profiles, tags, et ) to narrow your analysis to what’s most relevant to your brand.
Check out this article for more information on getting started in Trellis Studio!
Providing feedback
You make Trellis better. Providing feedback is a great way to ensure it gets it right.
Use the 👍 / 👎 reactions on agent responses.
Thumbs down is most valuable. If Trellis falls short, click 👎 and tell us why using the checkboxes and free-text input to provide suggestions. The “why” is critical to improving Trellis.
FAQs
Is my data secure when using Sprout’s AI features, and does it train external AI models like OpenAI’s?
Yes, your data is secure. Sprout’s AI features, including those that leverage OpenAI, such as Trellis, are configured to ensure your data is never used to train external AI models. Your proprietary information remains private at all times. If you’ve already approved Sprout’s security protocols during onboarding, enabling AI features does not introduce any additional security risk beyond what was previously approved.
What is the smallest time period I can analyze or view data for?
The agent is designed to work with time periods no smaller than one full day. You can’t analyze data at an hourly or minute level.
How can I use Trellis to analyze product or event feedback?
You can prompt Trellis with a query like, "Are there recurring concerns about [product/event] over the past three months? What themes show up most in negative feedback, if so?"
What are the key elements for writing an effective prompt for the Sprout AI Agent?
Good prompts should (1) be clear and specific about the goal, (2) provide the right context (timeframe and topic), (3) ask for actionable insights, (4) guide Trellis with framing (using 'what,' 'why,' 'how'), and (5) break down complex tasks.
What performance data can I analyze and access with Trellis?
At this time, the Trellis is able to source data from published posts. This published post data would include: Impressions, Engagement Rate, Total Engagement, Link Clicks, Comments, Shares, and Reactions. This allows Trellis to provide feedback on general trends and patterns with publishing performance over time, based specifically on these metrics.
Was this article helpful?