Looking for Information on Credits?
Agents cost credits to run in GovDash. To learn more about how to purchase credits, how to monitor credit spend, or limit usage of credits, please see our support article here.
Working with Dash Agents
Dash Agents let you save a task once so it runs again on its own: on a schedule, when something changes in GovDash, or whenever you start it. This guide explains what an agent is, when it runs, and what it can use, walks through setting one up, and ends with a few examples to start from.
What is an Agent?
Instead of asking Dash to do the same task by hand each time, you can create an agent to do that task for you. The agent then runs on its own, uses the GovDash data you choose, and writes its output back to the right record, so the finished work is waiting for you instead of sitting on your to-do list.
Everything an agent does happens inside GovDash, on data that already lives there, and only with the access you grant it.
Prompt, skill, or agent
GovDash gives you three ways to get work done with Dash, and they build on each other. The right choice depends on whether you are doing something once, reusing a method, or running a whole task on its own.
Approach | What it is | Best when |
|---|---|---|
Prompt: One-off | A single request you type to Dash in the moment. Dash answers once, right there in the conversation. | You need a quick answer and don't plan to repeat it. |
Skill: Reusable Method | A saved set of instructions Dash can follow on demand, so you get a consistent result each time you call it. | You repeat the same method but still kick it off yourself. |
Agent: Runs on its own | A skill plus a trigger and scoped sources. It runs the whole task on a schedule, on an event, or on demand, then writes its output back to the record. | You want the work to happen on its own, again and again. |
The simple way to remember it: a prompt does it once, a skill saves how to do it, and an agent runs it for you on its own.
When an agent runs
You decide when an agent starts, and you can combine these.
On a schedule: Dash runs the agent at a set time, such as every morning, every Monday, or any custom schedule.
When something happens: Dash watches for an update and runs the agent then. Triggers include a new opportunity, an opportunity changing stage, a new proposal, a document uploaded to your Data Library, a document added to an opportunity, proposal, or contract, a contract being awarded, and a new email arriving in your connected Outlook inbox.
Manually: you start the agent when you need it. Another agent can also call it as a step in a larger workflow.
What an agent can use
An agent can only read the sources and take the actions you allow, which keeps every agent scoped to the access you grant. Sources include Discover (Public), Discover (Private), Capture, Proposal, Contract, Pricer, Documents, Staffing Pool, Companies, Tasks, Web Search, and USASpending. Every agent can also let your team know when its work is done, either with an in-app notification or by sending an email from GovDash to a teammate. Agents can also work with other agents: an agent can look up your agents and their past runs, and it can create a new agent or update an existing one. Nothing is created or changed until you approve it.
Most agents finish by writing their output back to the related record, so the result lands exactly where your team will look for it, whether that be a Capture opportunity, a Proposal, or a Custom Document.
How to set up an agent
You don't need any technical setup. Open the Agents tab and select Create an Agent in the top-right corner of the page. The menu brings every way to start an agent together in one place:
Create with Dash: Dash starts by asking what you want to build or automate, then asks only the follow-up questions it needs to build the agent with you.
ProTeam Agent: browse recommended, pre-built agents and add one to your team.
Create from scratch : opens the agent form, which walks you through the steps below.
Suggest for me: Dash looks at your recent work to find repetitive tasks worth automating and sets up an agent for you.
Prefer to type it out? You can still describe the task in plain language using the Dash box on the Agents page.
When you choose Create from scratch, the form walks you through the following steps:
Name it, pick an avatar, and set visibility: give it a clear name and choose Personal so only you see it, or Entire team for everyone. For a team-wide agent, use the Subscribers picker to choose which teammates are notified when the agent finishes a run (see Getting notified when an agent finishes below). Make sure it is Enabled.
Choose when it runs: under When should this run?, pick a schedule, an event, or manual start. For events, you can choose more than one to be the trigger.
Choose what Dash can use: under What can Dash use?
Select the sources and actions the agent is allowed to use.
The Delivery row controls how subscribers hear about finished runs: Email is included by default, and you can remove it if you don't want this agent to send completion emails
Write the instructions: under What should Dash do?, describe what to accomplish, which sources to prioritize, the output format, and any rules (for example, cite external sources, stay under 500 words, or do not modify existing records). This is where you tell the agent what it’s supposed to do, where, and how.
Hand off work (optional): Open Advanced and, under Agents it can use, choose other agents this one can call to accomplish a task. For example, if you have a well defined agent that kicks off new opportunities added to your Pipeline, you can utilize that in an agent that helps source those opportunities instead of redefining the process in a second agent.
Create the agent: select Create agent. Your agent is ready to run, test, or adjust at any time.
After you create it
GovDash gives you a short summary of what the agent does and a couple of next steps. We recommend you start here.
Test it first: run the agent manually using the Start button from the Agents dashboard on an existing opportunity or record to see how it performs before you rely on it.
Configure it as needed: adjust the instructions, triggers, or allowed sources any time from the agent's Configure screen.
Track its work: every run is logged. On the Agents page you can see saved workflows, work in progress, and work completed, so you always know what your agents have done.
Get notified when it finishes: subscribe to the agent and turn on the Agent Run Completion notification so GovDash tells you, in the app or by email, as soon as a run is ready to review.
Tip
Test an agent on a couple of records first, then make small changes based on the results you see. This is the fastest way to get an agent you trust with your process.
Letting Dash suggest an agent
Not sure what to automate first? Let Dash find it for you. Suggest for me looks back over your past conversations with Dash for the tasks and prompts you keep repeating, then turns the best one into an agent.
Open the Agents tab and select Create an Agent in the top-right corner.
Select Suggest for me at the bottom of the menu. Hover over the info icon next to it to see a quick reminder of what it does. The Dash panel opens with a new conversation.
Dash searches your past conversations for repetitive work and picks the single recurring workflow best suited to an agent, prioritizing the time it will save you and its ongoing value.
Dash checks your existing agents so it doesn't suggest something you already have.
Dash prepares the agent with a clear name, a focused goal, the sources it needs, and a schedule only if your conversation history shows you do the task on a regular cadence. It then briefly explains what it found and what it set up.
Review the agent card Dash proposes and select Create agent to save it.
Want a different suggestion? Tell Dash in the same conversation, for example, "Suggest something for proposal work instead," or refine the proposed agent before you create it. Once it's created, you can test and adjust it like any other agent
Tip
Suggestions are based on how you've used Dash, so the more you work with Dash in chat, the better Suggest for me gets at spotting work worth automating.
Running an agent when a new email arrives
Want an agent to jump on new mail as soon as it lands? Connect your Outlook inbox and the agent runs each time a new email arrives. It can read the email's subject, sender, and message, so it can triage an RFI notice, summarize a teaming request for your capture lead, or create a task for anything that needs a reply.
Open the Agents page and select Create an Agent → Create from scratch, or open an existing agent and select Configure.
Under When should this run?, select When something happens. Outlook Email Received is listed first.
Select Connect Outlook. If your team uses a GCC High tenant, select Connect Outlook GCC High instead.
Read the notice in the Connect your Outlook inbox window and select I agree, connect Outlook. Sign in with your Microsoft account and approve access to read your mail. If Microsoft asks for admin approval, go back to the agent form and use the Blocked on admin approval? line under the buttons: open the approval link, or copy it and send it to your Microsoft admin.
Back in GovDash, you'll see an Outlook inbox connected message and your inbox listed under Outlook Email Received. If you've connected more than one inbox, choose the one this agent should watch.
Turn on the Outlook Email Received switch and save your agent (select Create agent for a new agent, or Save for an existing one).
Runs started this way show Outlook Email as their trigger in the agent's run history.
Good to know
New mail only: The agent picks up emails that arrive after you connect your inbox, not older mail.
Your inbox, your agent: Only the person who created the agent can turn on this trigger, and only with an inbox they connected themselves. Each agent watches one inbox.
Keep CUI out of commercial inboxes: Results from a commercial Outlook inbox can reach teammates and delivery channels, so don't connect an inbox that receives CUI. A GCC High inbox is treated as CUI, so some sources are blocked for that agent.
Disconnect any time: Select Disconnect next to the inbox in the agent form to stop sharing new mail with your agents.
Giving your agent an avatar
Every agent has its own avatar, so you can tell your agents apart at a glance. The avatar appears next to the agent's name in the Agents list and at the top of the agent's page, and wherever the agent's work shows up, such as the comments it leaves, the tasks it creates, and a record's activity history.
GovDash picks a random avatar for every new agent, including agents you add from PROteam Agents. To choose a different one:
Open the Agents tab and find your agent in the list, or select it to open its page.
Hover over the agent's avatar next to its name (a pencil icon appears) and select it. The avatar picker opens with an animated preview of your avatar.
Choose one of the six characters.
Choose a color. The preview updates as you go.
Select Use avatar to save it, or Cancel to keep the current one.
You can also pick the avatar while you set the agent up. When you create one from scratch, select the avatar above the agent's name. When Dash builds the agent with you, use the Avatar field on the agent card Dash proposes, before you select Create agent.
Chatting with an agent about a run
Every agent run is a conversation. Once a run has finished, you can talk to the agent about what it did, ask for another pass at the output, give it the information it was waiting on, or have it update its own setup, all without leaving the run.
Opening the chat
Select your agent from the list, and then choose a run from the agent's run history. The run's transcript opens, with Started by at the top so you can see who or what kicked it off.
Type your message in the Chat with <agent name>… box at the bottom of the run and send it. The agent replies in the same conversation, in character as your agent, using the same sources and actions you granted it.
Started a run and want to chat now? The chat box appears as soon as the run has finished. While a run is still Queued or Running, follow along in the transcript and chat with the agent once it wraps up.
Team-Agent Runs
Runs of an Entire team agent can be opened by anyone on your team. Only the person who started the run can send messages in that conversation; everyone else can read along. Runs of a Personal agent stay private to you.
Refine the output
If a run didn't land the way you hoped, say so in the chat: tell the agent what to change, what to prioritize, or what to leave alone, for example, "Focus on the incumbent's recent awards and keep the summary under 300 words." The agent keeps the context of the run it just completed, and it has the same sources and actions as that run, so it can pick up the work and revise it rather than starting from scratch.
Your agent also remembers what it learns. When you correct it or share a preference, such as a format you like or a source to skip, it saves a short private note and reads its notes at the start of every future run. That way it gets better at repeated tasks over time, and you don't have to repeat yourself.
Unblock a run that needs attention
When an agent needs a decision or more information to keep going, it ends the run as Needs Attention and explains what it needs. You have two ways to clear it:
Answer it in the chat: approve the approach, choose between options, or supply the missing detail, and the agent continues the task from there. Once the follow-up completes the work, the run updates to Succeeded.
Mark it resolved: if you've already handled the agent's question elsewhere, or you don't need it to keep going, select Mark resolved in the run header (next to the run's status badge). The run updates to Succeeded right away and nothing is sent to the agent.
Don't see Mark resolved? The button only appears while a run is in Needs Attention, and it needs the same Run permission on Agents that starting a run does. If it's grayed out, ask your admin to grant you that permission (see Roles & Permissions).
Ask the agent to update itself
You can also ask the agent to change its own configuration, its name, its instructions and goal, when it runs, and the sources and actions it may use. Describe the change in the chat, and the agent will propose it and ask for your approval first: "I'd like to update my configuration. Would you like to apply those changes now?" Select Update Agent to apply the change, or decline to leave the agent exactly as it is.
Getting notified when an agent finishes
You don't have to keep checking the Agents page to find out whether a run is done. Subscribe to an agent and GovDash will notify you as soon as one of its runs finishes, with a link that takes you straight to that run so you can review the output or chat with the agent about it.
Three things control who hears about a run:
The agent's subscribers: the people who should be told when this agent finishes.
Your notification preference: whether you want agent completion alerts at all, and whether they arrive in the app, by email, or both.
The agent's delivery setting: whether this agent sends completion emails at all. Email is on for every agent unless you turn it off.
Choosing who subscribes to an agent
Every agent keeps its own list of subscribers.
Personal agents notify their owner. You are subscribed automatically to agents you own, and there is nothing else to set up.
Entire team agents let you choose which teammates are notified. When you create or configure a team-wide agent, use the Subscribers picker next to the visibility setting and select the people who should be notified. The picker shows how many people are selected (for example, 2 selected) and reads Receive a notification when this agent finishes.
Turning on the notification
Subscribing tells GovDash which agents you care about; the Agent Run Completion notification controls whether and how you're alerted. It is off by default, so turn it on once:
Navigate to Settings in the bottom left of GovDash and select Notifications.
Open the Dash tab and turn on Agent Run Completion (Get notified when an agent finishes running.).
Select Configure to choose your Methods of Delivery: App for an in-app notification, Email for an email, or both. If you belong to more than one team, use the Teams tab to choose which teams' agents can notify you.
Once both are set, each time a subscribed agent finishes a run you'll receive an Agent run complete notification that reads <agent name> finished running. Select it to open the run and review the output, or chat with the agent to refine it.
Turning off completion emails for one agent
Some agents run often enough that an email for every run is more than you need. You can stop a single agent from sending completion emails without changing your notification preferences for any other agent:
Open the Agents tab, select the agent, and select Configure.
Under What can Dash use?, find the Delivery row. Email is listed there when the agent emails its subscribers.
Select Remove next to Email. Your change saves automatically.
To turn emails back on, select Add destination in the Delivery row and switch on Email.
Emailing your team from an agent
Agents don't have to wait for you to check GovDash. Any agent (and Dash itself, in a regular chat) can send an email from GovDash to a member of your team: a recap of what it found, an alert that something needs a decision, or a reminder that a deadline is coming up.
To use it, simply say so in the agent's instructions under What should Dash do?, for example: "When you finish, email the summary to Jordan Lee with a link to the opportunity." Dash looks up the teammate by name, composes the email, and sends it. No email connector is required.
Here's what your teammate receives:
The email comes from GovDash and opens with a line such as Dash is sending you a message or <Agent name> is sending you a message, so it's always clear who sent it.
A title and a short, formatted body written by the agent. Headings, paragraphs, and lists are all supported.
A single button (for example, Open opportunity) that takes them straight to the related page in GovDash. The button always opens a page inside GovDash, never an outside website.
A few guardrails to know about:
Team members only. Agents can only email active members of your GovDash team. They cannot email outside contacts, agency points of contact, or anyone who has been removed from your team.
Classified work stays in GovDash. If the run involved classified (CUI) information, the recipient receives a generic notice, Something is waiting for you in GovDash, with an Open GovDash button instead of the details. Nothing classified is ever included in an email.
Your own mailbox isn't used. Emails sent this way come from GovDash, not from your Gmail or Outlook account. If you'd rather Dash send from your own mailbox, connect Gmail or Outlook as described in our Using Dash Connectors article.
Prefer an in-app notification? Agents can also notify teammates inside GovDash instead of by email. Just ask for a notification in the instructions, and it appears in the recipient's notification bell.
Examples to start from
These are agents teams set up most often, grouped by lifecycle stage. Each lists when it runs and what it uses, build any of them from scratch, or look for a template under PROteam Agents. If your team doesn’t have any agents set up, GovDash will show you a recommended list from this pool.
Here are some examples of what Dash Agents can accomplish:
Teaming Partner Recommendations: Who to Approach and Why: Translates gaps and pursuit posture into a concrete partner profile, checks existing relationships first, researches new candidates with a strict evidence standard, and delivers a ranked shortlist with cautions.
Prime/Sub Strategy Recommendation: How We Should Pursue: Weighs eligibility, position strength, and capacity to deliver a direct recommendation on pursuing as prime or positioning as a subcontractor, with conditions for success.
Consolidated Gap Report: What We Lack and How to Close It: Synthesizes prior analysis and company data into a consolidated gap assessment across capability, past performance, compliance, key personnel, and scale, with severity ratings and mitigation paths. Feeds the bid/no-bid discussion.
Past Performance Relevancy Analysis: Best References and Coverage Map: Reviews all documents in the contract inventory (contracts active in the last five years), ranks past performance by size, scope, and complexity relevance, and maps task area coverage with links to each record.
Competitive Landscape Analysis: Incumbent and Likely Bidder Identification: Mines the opportunity record for competitive intelligence, then researches the web to identify the incumbent and likely bidders with a strict evidence standard.
Pipeline Intake Screen: Bid Stoppers and Risk Flags: Scans any opportunity entering the pipeline for showstoppers, incumbent or wired-bid signals, and past performance constraints, then posts a flag report to the record.
Proposal Template Formatting Requirements: Extracts proposal submission and formatting requirements (fonts, margins, spacing, file naming, packaging, deadlines) from solicitation documents, records them as a checklist note on the pursuit, recommends the most compliant cover letter template, and creates a task for any requirements the template does not cover.
Weekly Pipeline Recap: Emailed to Your Capture Lead: Every Monday, summarizes the opportunities that were added, advanced a stage, or are due this week, then emails the recap from GovDash to your capture lead with a button that opens the Pipeline.
Try It Yourself: Opportunity First-Look Example
To show how an example becomes an agent, here is New opportunity first-look as you'd type it under What should Dash do?
AGENT INSTRUCTION
When a new opportunity is added to the pipeline, research the issuing agency, the likely incumbent, and recent related awards. Use Web Search for external context, and use the Contract and Data Library sources for our relevant past performance. Summarize how the opportunity fits our experience, list three reasons to pursue and three risks, and give an initial go / no-go lean. Save the findings to the opportunity record. Cite all external sources and stay under 600 words.
Set its trigger to Opportunity Created and turn on Capture, Contract, Documents, and Web Search. Once you add a new opportunity to your Pipeline, this will start the process and save the results to the Activity tab in your opportunity.
FAQ
Do I need to know how to code to build an agent?
No. You describe the task in plain language and choose a few options. Dash builds the agent with you.
Can an agent see data I don't have access to?
No. An agent only uses the sources and actions you allow when you set it up. It works within the access you grant.
Can my whole team use the same agent?
Yes. Set the agent to Entire team and it becomes available to everyone on your team, and its runs can be read by everyone on the team too. Set it to Personal to keep it to yourself.
How do I know what an agent did?
Every run is logged and every output is written back to the right record. You can review the full history of any agent at any time from the Agents page and selecting your agent from the list.
Can an agent email me when it finishes?
Yes. Tell the agent in its instructions to email you (or another active member of your team) when it is done. The email is sent from GovDash, shows the agent's name as the sender, and includes a button that opens the related page in GovDash. Agents can only email members of your team, and if the run involved classified information you receive a generic notice asking you to log in instead of the details.
Can I get notified when an agent finishes?
Yes. Subscribe to the agent (personal agents subscribe their owner automatically) and turn on Agent Run Completion under Settings → Notifications → Dash. You'll get an in-app or email notification with a link straight to the finished run.
Can I stop an agent from emailing me every time it finishes?
Yes. Open the agent, select Configure, and select Remove next to Email in the Delivery row under What can Dash use?. The agent stops sending completion emails to all of its subscribers, while anyone with App notifications turned on still gets an in-app alert. To stop emails just for yourself instead, unsubscribe from the agent or change your Methods of Delivery under Settings → Notifications → Dash.
Can I change an agent after I create it?
Yes. Open the agent and select Configure to change its instructions, triggers, or sources whenever you need to.
Can an agent create or change other agents?
Yes. Ask for it in the agent's instructions under What should Dash do?. An agent never creates or changes an agent without your approval, so when a run gets to that step, it ends as Needs Attention and explains what it wants to set up. Reply in the chat on that run to go ahead. The agent shows you the details, and nothing changes until you select Create Agent or Update Agent.
Does my agent remember anything between runs?
Yes. Each agent keeps its own private notes about your preferences and the corrections you've given it, and it reads them at the start of every run and every chat about a run. These notes belong to the agent and are separate from your personal Dash memories on the Memories page. To change what an agent remembers, tell it in the chat on any run, for example, "From now on, always include the NAICS code in your summary."
Why can't I create, run, or change an agent?
Your role may not include the matching Agents permission. Agents have separate Read, Run, Create, Edit, and Delete permissions. Ask an Admin to update your role under Settings > Access & Permissions > Roles. Learn more in our Roles & Permissions article.
My agent used to be able to update companies. Why did it stop?
Company actions moved from the Documents source to the new Companies source. Open the agent, select Configure, and turn on Companies under What can Dash use? to restore them.
Why can't I turn on Outlook Email Received?
The switch stays off until you connect an Outlook inbox. If Connect Outlook is grayed out, your team hasn't linked a Microsoft tenant yet: select Link a Microsoft tenant below the buttons, or ask your admin to set it up (see our Microsoft SharePoint Integration Setup article). Only the person who created the agent can turn on this trigger, using an inbox they connected themselves.