HAI Assistant is a conversational AI agent built directly into your Harvestr workspace. It connects to your feedback data — feedback, discoveries, components, customers — and lets you query, analyze, and summarize it through natural language.
Rather than navigating filters and views manually, you can ask HAI Assistant directly and get structured, cited answers grounded in your actual data.
HAI Assistant is currently in beta. Responses are grounded in your Harvestr data, but accuracy may vary — especially on complex multi-step queries. If a response misses the mark, use the 👎 button on the message and share your feedback in the support chat.
HAI Assistant is available on Scale and Elite plans. It is distinct from HAI's automated feedback processing features. Learn more about HAI — AI-powered feedback processing →
Using HAI Assistant
Starting a new conversation
Open HAI Assistant from the left navigation bar. You'll land on the main chat screen with an input field at the bottom.
To start a fresh conversation, click the pencil icon in the top right of the chat panel. Previous conversations are listed in the right-hand sidebar and can be reopened at any time.
Asking a question with context
Before sending your message, you can use the context selector — the dropdown at the bottom right of the input field, labelled "All" by default. This lets you focus HAI Assistant's analysis on a specific discovery or component.
All — HAI Assistant searches across your entire workspace
A specific component — analysis is limited to discoveries and feedback within that component
A specific discovery — HAI Assistant focuses on that discovery and its sub-discoveries
This is especially useful when you want a focused deep-dive on one area.
For example, selecting your "Billing" component before asking "What are the main pain points?" will return a more relevant answer than asking globally.
Viewing sources
After HAI Assistant responds, a Sources button appears in the top right of the chat panel. Click it to open the sources panel, which lists all the feedback items and discoveries referenced to produce the answer — organized into Feedback and Discoveries tabs.
Each source links directly to the original resource in Harvestr, so you can verify any claim or read the full message behind a cited extract.
What HAI Assistant can do
Summarize feedback for a discovery or topic
HAI Assistant pulls together all feedback linked to a discovery and surfaces the key themes, pain points, and patterns — saving you from reading through dozens of individual messages manually.
Example queries:
"Summarize the feedback on the Dashboard performance discovery"
"What are customers saying about our onboarding flow?"
"What are the main pain points mentioned in the Billing component?"
Find feedback from a specific customer
HAI Assistant retrieves all feedback submitted by a given user or company — useful for preparing customer calls, understanding churn risks, or identifying your most vocal accounts.
Example queries:
"Summarize all feedback from Acme Corp"
"What has Acme asked for over the past 6 months?"
"Which customers have mentioned our API integration?"
Identify trends and volume changes over time
HAI Assistant analyzes feedback volume across a time period and surfaces spikes, drops, or seasonal patterns — including a breakdown by discovery to show which topics are growing fastest.
Example queries:
"How has feedback volume evolved over the last quarter?"
"Which discoveries received the most feedback in January?"
"Are there any topics that spiked in the last 30 days?"
Explore your discovery backlog
HAI Assistant can search, filter, and rank discoveries by state, component, or feedback volume.
Example queries:
"What are my top 5 discoveries by number of feedback items?"
"List all discoveries currently in the 'In Progress' state"
"Which discoveries in the Analytics component have no linked feedback?"
Support strategic prioritization
On strategic queries, HAI Assistant synthesizes findings into recommendations grounded in your data. Every suggestion traces back to cited feedback — not generic best practices.
Example queries:
"Based on recent feedback, what should I focus on this quarter?"
"What are the biggest unresolved pain points across all open discoveries?"
Answer operational questions instantly
HAI Assistant handles direct, factual lookups without requiring you to build a view or apply filters.
Example queries:
"How many discoveries are currently in the Backlog state?"
"Which discoveries were shipped last month?"
"How many feedback items did we receive from Zendesk in Q1?"
How to get the best results
Be specific about scope. Include the discovery name, customer, or time period in your query. Broad questions without constraints may return partial results or prompt HAI Assistant to ask for clarification.
Less effective: "What's happening with feedback?"
More effective: "What feedback did we receive on the Reporting component in the last 60 days?"
Use the context selector to pre-scope your question. If you know you want to focus on a specific component or discovery, set the context selector before sending. This reduces noise and improves response quality.
Provide a time range for broad searches. When searching across your entire workspace without a specific filter, HAI Assistant will ask for a date range. Having one ready speeds things up.
Use follow-up questions to drill deeper. HAI Assistant supports multi-turn conversations — you can build on previous answers without starting over. For example:
"Summarize feedback on the Notifications discovery"
"Which customers mentioned email specifically?"
"What are those customers' specific needs?"
Current limitations
HAI Assistant is in beta. The following limitations apply:
Read-only: HAI Assistant cannot create discoveries, update statuses, link feedback, or make any changes to your workspace.
Harvestr data only: HAI Assistant works exclusively with data in your Harvestr workspace. It cannot browse external sources.
No access to customer attributes or revenue data: HAI Assistant cannot read CRM-synced attributes such as ARR, plan tier, or any other customer attributes that exist in Harvestr.
No access to Discovery custom fields: HAI Assistant cannot read discovery custom fields such as priority scores, RICE values, or any other custom scoring fields.
No memory between sessions: Each conversation starts fresh. Context from a previous chat is not carried over automatically.
Text-based feedback only: HAI Assistant cannot analyze attachments or images.
Sharing feedback on HAI Assistant
Your feedback directly shapes how HAI Assistant improves. If a response is incorrect, incomplete, or misses your intent:
Tap the 👎 icon below any response to flag it
Share details in the support chat via the chat bubble in the bottom right of the screen