Sign in

Engineering

Human review and agent handoffs in Workspace

Agents share files and progress in Workspace. People review proposed actions, request changes, and decide when work can continue.

By Frank Wang

5 min readSeptember 28, 2026

An appeal is waiting on an itemized bill. A document-review agent has inspected the packet and found the gap. A communications agent needs to request the bill from another team, and a person needs to review that request before it is sent.

Workspace keeps this illustrative case together through those handoffs. Agents save the files they produce, people inspect the evidence behind a proposed action, and the run continues from the recorded decision. Follow the appeal from the first saved summary to the next review.

The next agent starts with a saved case record

The document-review agent writes packet-summary.md with the case reference, documents inspected, source locations, and missing bill. A progress file records the next step. The communications agent reads those files and drafts its request from the facts already established.

WorkspacePayer Operations / Appeals
Appeals
Source records
clinical-note.pdf
billing-summary.pdf
Working files
evidence-index.md
packet-summary.md
Run history
run-418.json
packet-summary.mdSaved
MD
Packet summary

Appeal 042 / Billing review

Itemized bill requested

Source: billing-summary.pdf

Ready for request preparation
billing-summary.pdfclinical-note.pdf
Document ReviewSaved packet and evidence indexCommunicationsContinues from the saved files
Illustrative Workspace explorer: source documents, a packet draft, and the run record stay together as a second specialist continues the case.

A reviewer can use the same references to open the billing record, check an extracted service date, and correct the summary. The next agent reads the saved correction with the rest of the packet. Workspace records the agent and run behind each output, while run history shows which files were read or written and which tools were called.

Files can stay in the customer’s connected storage, including buckets, drives, and warehouses. Storage connections make the packet available. Knowledge scopes bring the relevant policies into the organization, project, or agent’s context. Each specialist’s Agent Card defines its own tools, instructions, model, and approval requirements.

The outbound request reaches a review point

For this appeal, document review uses source records and extraction tools. Communications uses the summary and an outbound messaging tool. Before the send runs, configured request checks evaluate the tool and recipient scope. Run Governance applies time and model-call limits, and the approval requirement keeps the proposed action pending.

GovernanceCommunications / Appeal 042
Check the action before it runs
Source access, tool rules, and execution controls
Paused for approval
Active configurationCommunications specialist
Appeals filesAccess from connected storage
Agent Card tools
File System / Email
Allowed recipient domain
billing.example
Human Approval
Before sending the request
Proposed action
send_email
to: "billing@billing.example"
subject: "Itemized bill for Appeal 042"
Tool is allowedAgent Card
Recipient scope matchesbilling.example
Run is within its limitsRun Governance
Human approval requiredWaiting for the configured decisionPending
Run history
Configuration loadedSource and tool access
Request checkedScope and run limits
3
Execution pausedHuman decision pending
Illustrative governance view for the appeal workflow. Source access and Agent Card rules define the available actions; runtime checks evaluate the proposed call, apply the approval requirement, and record each transition.

The review request names the decision: send this request for an itemized bill to the billing team. It carries the destination, draft message, and packet summary. A tool approval presents the proposed call and its arguments; a task approval pauses the workflow step for the configured reviewer group.

The reviewer can approve the call, correct an editable value, or reject it. Group settings determine who is eligible to decide and how many responses are required. The runtime preserves progress while waiting. Sensitive material opens through authenticated review pages, so the reviewer can leave and return to the same pending task.

A correction becomes part of the continuation

Suppose the service date needs correction. The reviewer returns the billing request with that feedback. The agent revises the file and prepares the request for review again. The corrected date stays with the case, where another person or agent can inspect it.

WorkspaceAppeals / Review request
Review before sending
Appeal 042 / Request an itemized bill
Awaiting approval
Run progress
Review documentsPacket summary saved
2
Request the missing billWaiting for a person
3
Update the appealContinues after the bill arrives
Review material
MD
Packet summary

Appeal 042

Itemized bill needed

packet-summary.md
Task approval
Reviewing group
Appeals reviewers
Decision requested
Send the prepared request to the billing team.
Proposed message
Request for an itemized billTo: Billing team

Please provide the itemized bill for Appeal 042 so the appeal packet can be completed.

ApproveRejectReview decision
Open the review form for rework or escalation
After approval
1Decision recordedReviewer and response
2Run resumesContinue the pending step
3Tool result savedInspect the send result
Illustrative task-approval review using Workspace’s existing review controls. The configured group reviews a request beside its files; the run resumes after the required decision.

The decision determines the continuation. Approval releases the pending step, and a permitted edit becomes part of the approved tool arguments. Task-review choices can return work to an earlier step, send it to another reviewing group, or defer the decision through the full review form.

Run history records the human decision and subsequent execution separately. The tool result records the send attempt. When the bill arrives, its saved document becomes a new input for review. The team can distinguish a case awaiting a decision, one awaiting a document, and one ready for the next step from the events attached to it.

The next run picks up the reviewed work

A scheduled appeals agent can read the previous findings, inspect new cases, and update the progress file. The service-date correction can become a specific instruction to check that field before drafting the next request. Knowledge indexing makes the relevant policies searchable alongside the saved outputs.

Operators and engineers can work from the same case record. An operator opens the pending task and its files. An engineer follows the tool call, human correction, and resulting state to refine the instructions or reproduce the case in an evaluation. The handoff carries both the work already done and the evidence needed to continue it.

Explore Workspace, Agent Studio, and Governance.


Frank Wang

Written by

Frank Wang

CEO & Co-Founder

AI engineering leader who turns frontier research into market-defining enterprise products across agentic and vertical platforms. As Head of Engineering at Salesforce AI Research, Frank led breakthrough work on autonomous agents, deep research agents, agent orchestration, and the Agentforce advanced RAG & reasoning engine, post-training the agent, reasoning, deep research, and RAG models behind them. Earlier, as employee #11 and founding engineer at Vlocity (acquired by Salesforce in 2020), he built core platform technology in enterprise software — inventing the award-winning Salesforce OmniStudio Mobile Platform and six vertical industry applications, and growing OmniStudio into a platform spanning 14+ industries that has helped more than 100 large enterprises.

More stories

All articles →
Share this