Skip to main content

Biggy Chat

The Biggy Chat module lets you chat with Biggy AI directly in the BigPanda web app. Use it as a workspace for investigation, research, and generating polished artifacts that you can paste into your other tools.

Within the Biggy Chat page, you can:

  • Ask Biggy questions about incidents, changes, and services in your environment.

  • Upload images, CSVs, or Word documents for Biggy to analyze in real time.

  • Ask Biggy to generate diagrams, reports, and drafts.

  • Choose the chat mode and response style that fit the task.

  • Save frequently used prompts as chat presets.

  • Share responses to Slack, Teams, ServiceNow, or email, and share whole conversations with your team.

Biggy Chat is grounded in your organization's own data rather than a generic large language model, so it answers using your environment. Depending on the integrations you have enabled, this can include ServiceNow incidents, problems, changes, knowledge base articles, and configuration management database (CMDB) data; chat history from tools like Slack or Teams where it has been ingested; and live observability data from integrations such as Datadog, alongside your BigPanda incident data.

The Biggy Chat page in Biggy Agent mode, showing the welcome screen and starter prompts.

To open Biggy Chat, select Biggy Chat at the top of the left navigation pane.

Choose a chat mode

At the top of the Chat screen, select the mode that fits what you need. Each mode changes how much context and how many tools Biggy can use to answer.

  •  Basic Chat: A standard chat experience with an ITOps-oriented model. Basic Chat supports file uploads, but no integrations or live organizational context. Conversations are saved to your chat history. Use this mode for general questions, explanations, and drafting.

  •  Biggy Agent: An Ops expert that can use integrations, full organizational context, and action plans to answer your queries. Biggy Agent can access multiple action plans within the same query. Use this mode for investigation, correlation, and artifact generation grounded in your environment.

  •  Custom Agent: An org-specific agent built from your private context, curated tools, integrations, and sub-agents. A custom agent answers from the context it was built with and runs only the tools and integrations its builder enabled. When you select Custom Agent, choose the agent you want from the drop-down menu.

Set the response style

The response style informs how much reasoning Biggy applies and how long a response takes to generate. At the top center of the Chat screen, select a response style from the drop-down menu:

  •  Fast & Capable: Generates a fast, in-depth summary.

  •  Extra Reasoning: Uses more reasoning than Fast & Capable. Takes a little longer to generate.

  •  Max Reasoning: Uses the highest amount of reasoning and takes the longest amount of time to generate.

  •  Long Context: Uses a high amount of reasoning to analyze large documents. 

These response styles are available when using Basic or Biggy Agent chat. Each response is labeled with the style Biggy used to generate it, so you can see at a glance how a given answer was produced.

Start a conversation

When you open a new chat, Biggy greets you and shows a rotating set of topics it can help with, such as your CMDB, troubleshooting, RCAs, and post-mortems. Type your query into the text box, or use the starter prompts and input tools described below. See the Write Effective Prompts section for tips on interacting with Biggy Chat.Write effective prompts

In Biggy Agent mode, the welcome screen shows starter prompts for common tasks, including:

Select a starter to prefill the prompt, then edit it before you send. You can also ignore the starters and type your own query.

Input tools

The text box at the bottom of the screen accepts free text, slash commands, and mentions. Type / to browse commands, or type @ to mention an incident, service, or other entity so Biggy pulls in the right context.

The following tools are available in the input bar:

  • Add (+): Open the menu to apply a chat preset or add other content. See the Chat presets section.

  • Image: Add an image for Biggy to analyze.

  • Attach: Upload a file, such as a CSV or Word document.

  • Microphone: Use the voice-to-text option to dictate your query.

  • Deep Research: Arm Deep Research so your next message starts a background research run. See the Deep Research section.

  • Send: Submit your query.

Deep Research

Deep Research runs a longer, in-depth investigation in the background so you can keep working while Biggy compiles a thorough answer.

To use Deep Research, select the Deep Research icon in the input bar. Biggy confirms that Deep Research is armed and that your next message will start a background run. Type your query and send it to begin. To turn Deep Research off before sending, select Disarm.

Deep Research results are available in the web app at Operate > Reports > Deep Research.

Generate a canvas

A canvas is a working document that Biggy drafts and edits in a Biggy Chat conversation, such as an incident executive summary, a post-incident write-up, or a report.

When Biggy creates a canvas, it opens in the Canvas panel, where you can refine and edit it.

biggy_newwebapp_canvaschat.png

Canvases are available for future reference in the web app at Operate > Reports > Canvases. See the Canvases documentation for more information.

Chat presets

Create chat presets for queries that you use frequently with Biggy Chat. Use private presets for personal workflows, or public presets to share with your organization.

For example, if you ask for a report on a weekly basis, you can create a preset for that query so that you don't need to retype it each time.

The Chat presets menu, showing a public preset and the Create and New buttons.

To apply a preset, select the Add (+) button in the input bar and choose a preset from the list. The preset text appears in the text box, where you can edit it before you send the query. Private presets are only visible to you. Public presets are shared across your organization.

Create a preset

To create a new preset:

  1. In the input bar, select the Add (+) icon.

  2. In the Chat presets menu, select Create or New.

  3. In the Create Chat Presets window, complete the following fields:

    Field

    Description

    Preset name

    A descriptive name for the chat preset.

    Visibility

    Select who can see the preset. Select Private to make it visible only to you, or Public to make it visible to everyone in your organization.

    Preset Instructions

    The query used in the preset. Use the Generation Mode button to let Biggy generate a prompt based on your input.

  4. Select Save Preset.

Manage presets

To edit a preset, hover over it and select the Pencil icon. Adjust the fields in the Edit Chat Preset window, and select Save Changes.

To permanently delete a preset, hover over it and select the Trash can icon.

Work with responses

Hover over any response in the conversation to reveal its action icons.

A Biggy Chat conversation with a response labeled Quick and its action icons.

Copy or download a message

You can copy any message, or download it as a Word document. Hover over a message and select the Copy icon or the Download icon.

If Biggy generates a table as part of the response, select Download as CSV to export the table.

Share a message

You can send an individual Biggy Chat message to systems outside of the web app. Hover over the message, select the Share icon, and choose a destination:

  •  Email: Enter one or more recipient addresses separated by commas, add a subject, and send.

  •  Slack: Send the message as a direct message to yourself, or to one or more channels.

  •  Teams: Send the message as a direct message to yourself, to one or more channels, or to specific conversations.

  •  ServiceNow: Enter the ticket number and choose whether to add the message as a work note or a comment.

For any destination, use the optional additional instructions field to adjust the tone, focus, or layout of the message, or to emphasize next steps or remove sections. In the preview section, select Regenerate to refresh the message, and select Send when you are satisfied with it.

Share a chat with your team

You can share a whole conversation with teammates in your organization. They can view it, or collaborate on its canvas.

The Share chat window, showing the list of people to add and their reachable platforms.

To share a chat:

  1. At the top of the Chat screen, select the Share icon.

  2. In the Share chat window, find the people you want to add. Use the Search by name or email box to narrow the list, then select the checkbox next to each person. Icons next to each name show where that person can be reached, such as Slack or Teams.

  3. For each selected person, choose a permission level from the drop-down menu. Select Can view to let them view the conversation. Select Can Collaborate to allow them to collaborate on the conversation.

  4. Under Notify recipients, choose how to notify the people you added. Select any combination of In-app, Email, Slack, and Teams.

  5. Select Share with to share the conversation. 

  6. Select Done to close the window.

The Share chat window with a recipient selected, a permission drop-down, and the Notify recipients options.

Chat history

To view your recent and favorited conversations with Biggy, select Chat History at the top of the Chat screen.

The Chat History panel, showing the All, Favorites, Folders, and Shared tabs.

The Chat History panel opens on the All tab, which lists your conversations grouped by time period. Select any chat to open the full conversation. Use the Search by title box to find a specific conversation, and use the All, Basic Chat, and Biggy Agent filters to narrow the list by mode.

The Chat History panel organizes your conversations across the following tabs:

  •  All: Every conversation you have with Biggy AI.

  •  Favorites: Conversations you have starred for quick access. To favorite a conversation, select the Star icon.

  •  Folders: Conversations you have organized into folders. 

  •  Shared: Conversations that you have shared or that have been shared with you.

Biggy automatically saves conversations and generates a title for each one. To rename a conversation, select the three dots icon and select Rename, enter a new title, and select the green check mark to save. To permanently delete a conversation, select the three dots icon and select Delete.

Write effective prompts

Biggy Chat is a workspace for investigation, research, and generating polished artifacts that you can paste into other tools. Whether you're a responder building situational awareness, an engineer doing deeper triage, or a manager preparing a review, the quality of what you get back depends on how you ask.

Biggy is most useful when you give it three things: context (which incident, change, or system, and what timeframe), an explicit action (what you want done), and a format (what you want back). Vague prompts get vague answers. Specific prompts get useful responses and artifacts you can paste directly into your tools.

The pattern is context, action, format. The following table shows the difference:

Weak prompt

Strong prompt (context + action + format)

What's going on with <incident_ID>?

Summarize <incident_ID> in five bullets covering scope, affected sites, suspected cause, on-call engaged, and current status. Audience: responder.

Was this a change?

List ServiceNow changes in the last 24 hours that touched the same CIs, technologies, or sites as <incident_ID>. Include the change number, change owner, start and end time, and any AI Incident Prevention risk score.

Draft comms

Draft a status update for <incident_ID> per <your_severity_SOP>, audience: leadership. Include services impacted, scope, suspected cause, and next update time (30 minutes). Plain text, under 120 words. I will paste it into Slack.

Tell me about this change.

Show the AI Incident Prevention assessment for <change_ID>: risk score, top risk factors, and the prioritized mitigation steps. Format it as a one-page pre-CAB brief.

Prompting do's and don'ts

Follow these practices to get consistent, pasteable results:

  •  Anchor every prompt to a service. Reference a specific incident ID, change ID, or named service. Once you give Biggy the service context, it can pull all the related information.

  •  Ask for the format you want. For example, as a table, as five bullets, as a status update under 120 words, or as a pre-CAB brief.

  •  Tell Biggy where the output is going. For example, I'll paste this into Slack, this is for a leadership deck, or this is for ServiceNow work notes. Tone and length adjust accordingly.

  •  Iterate in the same chat. Biggy keeps context within a single chat. Refine with follow-ups like make it shorter, more technical, add the change ID, or redraft for an executive audience.

  •  Don't ask Biggy to invent data. If a source is missing, tell Biggy where to look, or accept "unknown" as an answer.

  •  Don't skip the action. Tell me about <incident_ID> is open-ended. Summarize <incident_ID> for leadership is actionable.

  • Don't paste sensitive data in chat. Don't paste sensitive or regulated data, such as personally identifiable information (PII), into the chat. Reference incidents by their ID and let Biggy resolve details from the source system without surfacing them back to you.

Prompt library

Use the following prompts as starting points. Copy a prompt, substitute the placeholder values in <angle brackets>, and iterate in the same chat to refine the result.

Prompts by purpose

Purpose

Try this prompt

Quick situational awareness

Summarize <incident_ID> in five bullets for a technical or executive audience: scope, affected services, suspected cause, on-call engaged, and current status.

Severity guidance

Based on the data you have, what severity should <incident_ID> be per <your_severity_SOP>? Cite the rule and the evidence you used.

Change-incident correlation

List ServiceNow changes in the last 24, 48, or 72 hours that touched the same CIs as <incident_ID>. Rank them by likelihood of being the root cause.

Similar past incidents

Find historical incidents with symptoms similar to <incident_ID> in the last 12 months. Show the incident number, date, duration, resolver group, and the resolution step that worked. Table format.

On-call lookup

Who is on-call right now for <team> per ServiceNow rotations? Return names and contact details.

Status update draft

Draft a status update for <incident_ID> per <your_severity_SOP>, audience: leadership or responders. Plain text, under 120 words. Include services impacted, scope, suspected cause, and next update time.

Vendor escalation packet

Generate a copy/paste-ready vendor escalation packet for <incident_ID>. Include affected components and sites, timestamps, symptoms, reproduction steps, scope, and the specific trace requests to make.

Pre-CAB change brief

Generate a pre-CAB risk brief for <change_ID>: AI Incident Prevention risk score, top risk factors, prioritized mitigation steps, and similar prior changes and their outcomes.

After-action review draft

Generate the after-action review for <incident_ID>: timeline, what went well, what didn't, and prioritized action items with proposed owners.

RCA draft

Draft the RCA for <incident_ID>: root cause, contributing factors, detection gap, and recommended preventive actions. Mark anything you're inferring versus citing.

Executive summary

Generate a one-page executive summary of <incident_ID> for leadership: business impact, scope, duration, root cause, and the three actions you are taking next.

Problem theme analysis

Cluster incidents from the last 90 days into themes. Show the top five themes by incident count, a root cause summary, and proposed remediation.

Knowledge base or runbook lookup

Find any knowledge base articles, SOPs, or runbooks relevant to <symptom or system>. Summarize each in one line and give the link or location.

Challenge the hypothesis

What is the strongest argument that <incident_ID> is NOT caused by <hypothesis>? What evidence would change my mind?

Investigation scenarios

Each scenario starts with a deep-context seed prompt to set up the chat, followed by prompts to refine the result. Substitute the placeholder values for your own.

Vendor-suspected service outage

Seed prompt: I'm investigating a service outage with a suspected vendor cause. Incident: <incident_ID>. Affected components: <list>. Start time: <HH:MM>. Summarize what BigPanda knows about it, list any related vendor signals or external status events from the last hour, and any related changes in the last 24 to 72 hours. 

Follow-ups:

  • Generate the vendor escalation packet I should send for this. Plain text, copy/paste ready.

  • Find prior outages of this type from the last 12 months that were resolved by rerouting. Give me the runbook reference and the typical time to mitigate.

  • Draft a status update for leadership, under 120 words, that I can paste into Slack.

Suspected change-induced incident

Seed prompt: Cross-reference <incident_ID> against ServiceNow changes in the last 72 hours that touched the same CIs, sites, or technology. Rank them by likelihood of root cause. For the top candidate, show me the AI Incident Prevention risk score and any mitigations it flagged. 

Follow-ups:

  • For <change_ID>, what mitigations did AI Incident Prevention propose, and which were actually performed per the change record?

  • Find historical incidents from similar-scope changes. Did they cause incidents? What was the typical mitigation?

  • Draft a rollback decision brief for the bridge: current state, what a rollback restores, blast radius, and the go or no-go criteria.

Multi-site outage analysis

Seed prompt: I'm looking at <incident_ID>. Identify which sites are impacted, what infrastructure they share, and the timeline of the first event per site from BigPanda. Are the failures simultaneous or staggered? 

Follow-ups:

  • Assess business impact: which sites have critical operations running right now, and what is the risk if this lasts another 30 or 60 minutes?

  • Find similar multi-site outages from the last 12 months and the mitigation step that worked.

  • Draft an impact statement I can hand to the affected site owners.

Capacity or saturation investigation

Seed prompt: Show me everything you have on the capacity problem theme for <system>: the BigPanda problem report, recent saturation events from the last 30 days, a root cause summary, and the proposed solutions with effort estimates. 

Follow-ups:

  • What downstream applications are likely impacted by this saturation per CMDB?

  • Draft an executive summary explaining why this is recurring and what is different about the proposed fix this time. One page.

  • Generate a project brief I can hand to engineering: problem, evidence, the proposed solutions, and recommended sequencing.

Pre-CAB change risk research

Seed prompt: I'm reviewing <change_ID> before CAB. Pull the AI Incident Prevention risk score, the top risk factors, prioritized mitigation steps, and any prior changes of similar scope that caused incidents. Format it as a one-page pre-CAB brief. 

Follow-ups:

  • What questions should I make the change owner answer before approval?

  • If this change does cause an incident, what is the most likely failure mode based on similar history?

  • Draft proposed rollback criteria and the validation steps the change record is missing.

Post-incident artifact generation

Seed prompt: For <incident_ID>: generate the after-action review (timeline, what went well, what didn't, action items with owners), the RCA (root cause, contributing factors, detection gap, preventive actions), and a one-page executive summary for leadership. Mark anything inferred versus cited. 

Follow-ups:

  • Make the executive summary 50% shorter and lead with the business outcome.

  • From the action items, identify which are detection gaps, process gaps, or capability gaps, and group them.

  • Find prior incidents that produced similar action items but were never closed. Are we about to repeat ourselves?

Tips for getting the most out of Biggy Chat

  • Treat each chat like a workspace. Use one chat per incident or per investigation. Biggy keeps context within it, and switching chats resets that context.

  • Generate artifacts here, and act elsewhere. Biggy Chat is strongest for drafting comms, packets, and briefs. Use the sharing options to send them to Slack, Teams, ServiceNow, or email, where you can act on them. See the Share a Chat Message section for details.

  • Ask Biggy to challenge itself. Before committing to a hypothesis, try a prompt like What's the strongest argument that the change isn't related?

  • Always say where the output is going. A status update for Slack, a work note for ServiceNow, and a brief for leadership each call for a different tone, length, and level of detail.

  • Give feedback when Biggy gets it right or wrong. Reactions and thumbs feedback feed the model. The accuracy you see in a few months depends on the feedback you give it now.

In this section: