Knowledge Gap Finder Agent

1. 01

   Find gaps

   Group closed cases without articles into topics with counts.

2. 02

   Draft articles

   Draft a Knowledge article for each gap that meets the threshold.

3. 03

   Request review

   Send each draft for approval and report the week's results.

• The agent creates Draft articles only. It never publishes.
• Only create an article for a cluster with 5 or more cases.
• Remove customer names, emails, phone numbers and account names from every draft.
• Use only facts present in the case resolutions. If the resolution steps are unclear, write the article as Needs expert input and list the open question.
• Maximum of 10 drafts per weekly run.
• Never delete or edit existing articles.

Runs on Service Cloud, Salesforce Knowledge, Agentforce. Confirm editions and licenses with your Salesforce account team.

Salesforce products

Service CloudSalesforce KnowledgeAgentforce

Editions and licenses

Agentforce must be enabled in your org. Confirm editions and licenses with your Salesforce account team; we check them in the first workshop.

Agent type

Autonomous agent

From you

Service Cloud with Salesforce Knowledge enabled and a Knowledge manager user. · At least 3 months of closed cases with resolution comments. · Your approver and the article template fields.

Language

English. The agent writes in your locale and follows your wording settings.

Where it runs

Inside your Salesforce org. Records are read and written through the agent’s approved actions only.

Not included

Publishing or retiring articles. · Editing or merging existing articles. · Translating articles. · Real time suggestions to agents while they work a case.

Designed in full before a line is built, with 8 scripted test conversations. The numbers become verified results when the agent is delivered.

• Deployable sourceThe agent, its actions, objects and screens as Salesforce metadata, in your repository.
• Solution designA Solution Design Document with UML: architecture, data model, sequence and security.
• Test suiteApex tests on every action, plus scripted conversations replayed before every release.
• Least-privilege accessIts own permission sets, so the agent and your staff see only what the job needs.
• Runbook and handoverHow to run it, change its rules and roll back, with a walkthrough for your team.

• Least-privilege access

  It runs as its own user with a permission set written for this agent, so it can reach only what the job needs.

• Changes only through approved actions

  The agent cannot edit records freely. Every change goes through one of its 7 actions, each with one job.

• People make the big calls

  The agent creates Draft articles only. It never publishes.

• Runs inside Salesforce

  Agentforce runs on the Salesforce platform and its Einstein Trust Layer. Confirm which Trust Layer features apply to agents in your org with your Salesforce account team.

• Every change is on the record

  What the agent does lands as normal Salesforce records with their full history, so you can see who changed what and when.

• The review is free

  A 60-minute call with an architect about the Knowledge Gap Finder Agent and your org, with a written plan you keep.

• A fixed-scope proposal first

  Before any work starts you get a written proposal with milestones. You approve it, or you do not.

• Timing follows scope

  How long it takes depends on your setup and your rules. The proposal states the milestones up front.

• Or inside a monthly plan

  Agents can be built and run through one of our monthly delivery plans, alongside your other Salesforce work.

Salesforce licenses, including Agentforce, are bought from Salesforce and are not part of our fee. See our plans and pricing →

• One-page brief (PDF)

  What it does, the rules it follows and what you need, on one page you can forward.

  Get the brief →

• Slide deck (PDF, 6 slides)

  For your team or steering group: the problem, what it does, the rules it follows and how we deliver it.

  Get the slides →

• Talk to an architect

  A free 60-minute session on how it would work in your org, with your processes, your data and your rules.

  Book a session →

• The whole library

  Every agent we offer, by business area.

  Browse agents →

Further reading from our architects

• The grounding checklist we run before an agent talks to a customerTwelve pre-flight checks we run before an AI agent is allowed near a real customer, each with the failure it catches and the fix. A go or no-go list, not a readiness score.
• Deflection that does not cost you the customerHow to measure service automation honestly, why deflection alone is a vanity metric, and an escalation design framework covering triggers, routing and carried context.
• Agentforce and Service Cloud: what actually connects to whatA reference architecture for Agentforce on Service Cloud: how channels reach the agent, what it can read at each hop, where the case object sits, and how escalation carries context to a human.

• What does the Knowledge Gap Finder Agent do?

  The Knowledge Gap Finder Agent reviews the last 30 days of closed cases every Monday, finds topics that were solved without a Knowledge article, groups them, and drafts new articles for a Knowledge manager to approve. A Knowledge base that grows from real case history instead of guesswork, and fewer repeat cases.

• Which Salesforce products does it run on?

  Service Cloud, Salesforce Knowledge, Agentforce. Confirm editions and licenses with your Salesforce account team.

• Where do people use it?

  Background. Approval request by Salesforce approval and an optional Slack post.

• What does it not do?

  Publishing or retiring articles; Editing or merging existing articles; Translating articles; Real time suggestions to agents while they work a case.

• Is there a demo?

  Not yet. This agent is in our build program and is coming soon. We can scope it for your org now, and show you the agents that are already live.