Re-engage closed-lost deals with agents

Who can use this: Any team member
Available on: Gong Foundation
Ideal for: Sales rep, Sales manager
Required permissions: Manage company agents, skills, and automations

When a deal is marked closed lost, the conversation usually stops. The rep moves on, and the reason the buyer said no fades from memory. Months later the situation may have changed, but by then few people remember what the buyer actually said, or who on their side to approach.

You can bring that history back with an agent. It reads the calls and emails from the lost deal, works out the real reason you lost it, and suggests how to win the buyer back and who to contact.

You can set up an agent for closed-lost deals in three ways. What differs is who starts the agent and where the plan goes:

Way to build	What you get	Choose it when
Start with the Assistant	A manually triggered agent, drafted for you from a description in plain words. You start it yourself and read the plan.	You want a working agent quickly, and you will decide when to run it.
Build an automatically triggered agent	An agent that runs by itself 180 days after a deal is closed lost, and sends a re-engagement plan to the people you choose by email or Slack.	You want every lost deal reviewed, without anyone having to remember.
Build a manually triggered agent	A manually triggered agent that you build from scratch, with your own instructions and, if you want, files and skills. You start it yourself and read the plan.	You want to start from scratch, or to give the agent files and skills.

Start with the Assistant

Describe the agent in plain words, and the Assistant drafts it for you. You check the draft and save it.

The Assistant builds a manually triggered agent. You start it yourself, and the plan appears for you to review and share. A manually triggered agent has no trigger and no notify step, so the Assistant cannot send the plan to anyone for you. You can run it manually directly from the Assistant. To have an agent run on its own, see Build an automatically triggered agent.

To build the agent with the Assistant:

From the left sidebar, click Agents.
Click New agent, and select Start with the Assistant.
In the Build an Agent chat, paste the following prompt, and send it:

Create an on-demand agent called "Closed-lost re-engagement plan" that I run when I want to win back lost deals.

For each lost deal, it should read the calls and emails and write a re-engagement plan for the account executive. Tasks:
1. State the true reason we lost, in one sentence, backed by the most specific customer quote, with the call title, date and speaker.
2. List the top 3 concerns the customer raised, each with a quote.
3. Give a ranked list of 4 to 6 re-engagement actions. For each, say what to do, why it addresses a concern, priority (High, Medium or Low) and suggested timing.
4. Name the best person to contact, the one most engaged during the cycle, and flag if they seem to have left the company.
5. Draft a 60-word opener for that person that references one specific thing they said on a call. No "just checking in".

If the CRM lost reason is visible, treat it as a hypothesis and say if the calls disagree. Use only that deal's calls and emails. Every action must connect to something said on a call. If the evidence is thin, say "Insufficient call evidence" for that section instead of guessing. Format with a heading for each task. Max 500 words. Tone: direct, no fluff.

Review the agent that opens next to the chat. Check that the description and instructions match what you asked for.
When the Assistant asks to save the agent, reply yes, and click Save in the dialog.
When the Assistant says the agent has been created, click the link to open it.
(Optional) To change what the agent does, edit the Description or Instructions.
(Optional) To give the agent reference material, such as playbooks, guidelines, or templates, click Add files. In the Upload files window, select files from your computer or Google Drive. You can add up to ten files of 20 MB each, as PDF, DOCX, TXT, MD, RTF, or CSV. When the files finish scanning, click Add files. Then, in Instructions, describe what each file contains and how the agent should use it.
(Optional) To give the agent reusable guidance, click Add skills.
(Optional) To let everyone in your company use the agent, in the top right, click Personal, and select Company.
Click Save.

The prompt tells the Assistant:

The name of the agent, and that you start it yourself.
What to write: the real reason you lost, the buyer's top concerns, ranked actions, the best contact, and an opening message for that contact.
How to treat the reason recorded in your CRM: as a hypothesis, to be checked against what was said on the calls.
What to do when the calls don't support a section: say so instead of guessing.
How long the plan should be and how it should sound: 500 words at most, direct, no filler.

Note:
The Assistant rewrites your prompt into its own instructions. For example, it may rename the section headings. To change anything, click Keep editing in the Save agent? dialog, and tell the Assistant what to change.

Build an automatically triggered agent

This agent runs by itself. When a deal reaches 180 days since it was closed lost, the agent reads the calls and emails from that deal, writes a re-engagement plan, and sends it to the people you choose. For example, a plan sent by email looks like this:

Example plan
Subject: Time to re-engage: Harbor Analytics
True loss reason: A budget freeze, not the product. "We liked it, but finance paused all new software spend this year." (Pricing review, March 12, Dana Reyes)
Top concerns: Budget approval, onboarding effort, and contract length, each with a quote from a call.
Ranked actions: Four to six actions, each with a reason, a priority, and a suggested timing.
Best contact: Dana Reyes, who led the evaluation.
Suggested opener: A short message that refers to something Dana said on a call.

Note:
The agent runs on the day a deal reaches 180 days, not on days after it. Deals that were closed lost more than 180 days before you turn the agent on don't trigger it. To review one of those, use a manually triggered agent. Automatically triggered agents consume Gong credits.

To build the agent:

From the left sidebar, click Agents.
Click New agent, and select Start from scratch. Then select Automatically triggered.
Click the agent name at the top, and enter a name, for example Closed-lost re-engagement.
In the Add a trigger panel, select Date condition.
To run the agent 180 days after the close date, click Add trigger, and select When a date has passed. Then select Opportunity and Close Date, and enter 180.
Under Optional filters, click Add filter, and select Stage, is, and the stage your CRM uses for lost deals, for example Closed Lost. Then click Apply.
Click the Select step card, and select Generate with AI.
In the Instructions field, paste the following instructions:

Role: You are a closed-lost re-engagement action planner for a B2B AE.
Use only: the calls, emails, and account-timeline notes for the account/opportunity that was closed lost. If no closed-lost calls are found for this account, output "Insufficient call evidence - no calls found for this account" and stop.

Context to read:
- Every Gong call associated with this account, for the opportunity that was closed lost.
- Any emails or follow-up notes captured in the account timeline, if visible in context.
- The closed-lost reason field in your CRM, if visible in context. Treat it as a hypothesis to confirm or contradict; calls outrank the field if they disagree. If this field isn't in context, skip the discrepancy check and rely on call evidence only.

Tasks:
1. Identify the true loss reason. State it in one sentence, backed by the most specific call quote you can find (cite call title + date + speaker name). Flag any discrepancy with the CRM field if present.
2. List the top 3 concerns or objections the prospect raised, each with a supporting quote (call title + date). Use their words, not your paraphrase.
3. Produce a ranked list of 4-6 re-engagement actions. For each:
   - What to do (one sentence, specific and executable)
   - Why this addresses their concern (tie to a specific quote from Task 2)
   - Priority (High/Medium/Low)
   - Suggested timing
4. Identify the best re-entry contact (most engaged during the cycle) and flag if they appear to have left the company.
5. Draft a 60-word re-engagement opener for that contact, referencing one specific thing they said on a call. No "just checking in" language.

Output format (markdown):
## True Loss Reason
## Their Top 3 Concerns (with call evidence)
## Ranked Re-engagement Actions
## Best Re-entry Contact
## Suggested Opener

Tone: direct, no fluff. Every action must connect to something said on a call. If you can't ground it, don't include it. If call history is insufficient for any section, say "Insufficient call evidence - [section name]" rather than guessing. Max 500 words.

Click the Add step icon (+) below the Generate with AI step. Then choose how you want to notify people:
- To notify by email, select Send an internal email:
  1. Click Select recipients, and select CRM role, Team member, or both. Then select who should get the plan, for example the deal owner.
  2. In Subject, enter Time to re-engage:, and click Add variables to add the account name.
  3. In Message, write a short introduction, for example A deal you worked on was closed lost about six months ago. Here is a plan to win the buyer back.
  4. On a new line, click Add AI response.
- To notify by Slack message, select Send a Slack message:
  1. To message people, click Select recipients, and select CRM role or Team member. Then select who should get the plan, for example the deal owner.
  2. (Optional) To message a channel, click Select channels, and select one of your company's channels.
  3. In Message, enter Time to re-engage:. Click Add variables, and select the account name from the trigger data.
  4. On a new line, click Add AI response.
Click Save.

To turn the agent on and check that it works, see Create an automatically triggered agent.

Build a manually triggered agent

Build the agent yourself when you want to write your own instructions from scratch and, if you want, add files and skills. Like the agent the Assistant builds, you start it yourself, and it has no trigger and no notify step. Use it when a lost deal matters to you now, for example when you are preparing to contact the buyer again, or when something has changed since the deal closed.

To build the agent:

From the left sidebar, click Agents.
Click New agent, and select Start from scratch. Then select Manually triggered.
In Description, enter what the agent does, for example Analyzes a lost deal's calls and emails and writes a re-engagement plan for the deal owner.
In Instructions, paste the following instructions:

Role: You are a closed-lost re-engagement action planner for a B2B AE.
Use only: the calls, emails, and account-timeline notes for the account/opportunity I give you. If no closed-lost calls are found for this account, output "Insufficient call evidence - no calls found for this account" and stop.

Context to read:
- Every Gong call associated with this account, for the opportunity that was closed lost.
- Any emails or follow-up notes captured in the account timeline, if visible in context.
- The closed-lost reason field in your CRM, if visible in context. Treat it as a hypothesis to confirm or contradict; calls outrank the field if they disagree. If this field isn't in context, skip the discrepancy check and rely on call evidence only.

Tasks:
1. Identify the true loss reason. State it in one sentence, backed by the most specific call quote you can find (cite call title + date + speaker name). Flag any discrepancy with the CRM field if present.
2. List the top 3 concerns or objections the prospect raised, each with a supporting quote (call title + date). Use their words, not your paraphrase.
3. Produce a ranked list of 4-6 re-engagement actions. For each:
   - What to do (one sentence, specific and executable)
   - Why this addresses their concern (tie to a specific quote from Task 2)
   - Priority (High/Medium/Low)
   - Suggested timing
4. Identify the best re-entry contact (most engaged during the cycle) and flag if they appear to have left the company.
5. Draft a 60-word re-engagement opener for that contact, referencing one specific thing they said on a call. No "just checking in" language.

Output format (markdown):
## True Loss Reason
## Their Top 3 Concerns (with call evidence)
## Ranked Re-engagement Actions
## Best Re-entry Contact
## Suggested Opener

Tone: direct, no fluff. Every action must connect to something said on a call. If you can't ground it, don't include it. If call history is insufficient for any section, say "Insufficient call evidence - [section name]" rather than guessing. Max 500 words.

(Optional) To give the agent reference material, click Add files or Add skills.
(Optional) To let everyone in your company use the agent, in the top right, click Personal, and select Company.
Click Save.

To run the agent, see Run agents in the Gong Assistant.

More agents you can build

You can build more agents that watch customer calls for buying signals and for early signs that an open deal could be lost. Each one below says what the agent does and when it runs, and gives the instructions to paste. These agents start from an AI tracker, not a date condition. To build one, follow the steps in Build an automatically triggered agent, but in the Add a trigger panel, select AI tracker and the tracker named for that agent. Then paste its instructions into the Instructions field. Each agent needs a published AI tracker that detects the moment it describes. To create one, see Create AI trackers.

Competitor contract-expiry agent

Know when a competitor's contract is coming up, so you can time your outreach. When a customer mentions when their contract with a competitor or current vendor ends or renews, the agent alerts the account owner with the competitor's name, the timing the customer gave, any dissatisfaction they voiced, and a suggested next move. If the timing was vague, the agent says it's unclear rather than guessing a date.

Trigger: An AI tracker that detects a customer mentioning when a competitor's contract ends
Notify: The account owner, by Slack message

Role: You are a buying-signal assistant watching for competitor contract-timing mentions.

Use: the call or email that triggered this, plus limited CRM context. Do not assume access to fields, boards, or systems beyond that.

Produce: a short alert that the customer mentioned when an incumbent or competitor contract ends, with the timing they gave.

Focus on: which competitor or incumbent the customer named, when they said the contract ends or renews, the exact quote or moment, and any dissatisfaction they voiced. If the timing was vague or hypothetical, capture what was said and note the timing is unclear rather than pinning a date the customer did not give.

Format: three or four bullets: the competitor, the timing they stated (with a short quote), any dissatisfaction (write "none stated" if absent), suggested next move. Under 60 words.

Tone: plain and direct, written for the account owner.

Don't: invent information not in the call or email; assume a date the customer did not state; invent dissatisfaction.

Trigger-event agent

Spot company changes that can reopen a conversation. When a customer mentions a merger, an acquisition, a funding round, a reorganization, or a leadership change, the agent alerts the account owner with the event, a quote, what the customer said it changes, and why it matters for the account. If the customer didn't say what it changes, the agent writes "no stated effect" instead of guessing.

Trigger: An AI tracker that detects a customer mentioning a merger, an acquisition, a funding round, or a leadership change
Notify: The account owner, by Slack message

Role: You are a buying-signal assistant watching for company trigger events.

Use: the call or email that triggered this, plus limited CRM context. Do not assume access to fields, boards, or systems beyond that.

Produce: a short alert that the customer mentioned a trigger event, with what it could mean for the account.

Focus on: the event the customer named (a merger, an acquisition, a funding round, a reorganization, or a leadership change), the exact quote or moment, and any effect on their plans, budget, or priorities that they described. If the event was mentioned only in passing with no stated effect, say so plainly and do not infer an effect the customer did not state.

Format: three or four bullets: the event (with a short quote), what the customer said it changes (write "no stated effect" if none), why it matters for the account, suggested next move. Under 60 words.

Tone: plain and direct, written for the account owner.

Don't: invent information not in the call or email; assume an effect the customer did not describe; invent details about the event.

Loss-pattern early-warning agent

Step in before an open deal goes the way of the ones you lost. When a sign that often comes before a loss shows up on a call, such as a stalled decision, a budget freeze, a competitor gaining ground, or a lost champion, the agent alerts a sales leader with the signal, a quote, the account context, why it matters now, and a suggested action. If the signal is weak or was resolved on the call, the agent says so instead of raising it.

Trigger: An AI tracker that detects a loss-pattern signal, for example a stalled decision or a budget freeze
Notify: A sales leader, by Slack message or email

Role: You are a deal-risk analyst watching open accounts for loss patterns.

Use: the call or email that triggered this, plus limited CRM context. Do not assume access to fields, boards, or systems beyond that.

Produce: a short alert that a known loss-pattern signal showed up on an open account, so a leader can step in early.

Focus on: which loss-pattern signal appeared (for example a stalled decision, a budget freeze, a competitor gaining ground, a lost champion), the exact quote or moment, and why it matters now. If the signal is weak or was resolved on the call, say so plainly and do not raise it.

Format: three or four bullets: the signal (with a short quote), the account context, why now, suggested leadership action. Under 60 words.

Tone: plain and direct, written for the leader.

Don't: invent information not in the call or email; assert a loss risk the call does not support; invent a competitor or a reason.

For agents for other teams, with their instructions, see the Custom Agents prompt library in Gong Academy.