Guide · By AnyCap Team
Human-in-the-loop AI agents
Human-in-the-loop AI places an explicit review, correction, or approval checkpoint inside an otherwise automated workflow.
The human is not there to repeat work the agent can already do. They intervene where judgment, accountability, or visual context matters, and their response becomes structured state for the next agent step.
Structured visual feedback instead of a vague approval prompt
AnyCap can open a non-blocking annotation session for an image, URL, video, or audio target. The reviewer marks the artifact and clicks Done. The agent polls the session, reads the annotations or recording, applies the requested change, and can open a fresh review round.
Open a review session
anycap annotate hero-banner.png --no-wait -o hero-banner-annotated.pngRead the feedback
anycap annotate poll --session <session_id>URL review uses a narrated screen recording as its primary artifact; image, video, and audio sessions can support collaborative visual review. A simple yes/no decision does not need annotation and should stay a lightweight harness approval.
A review checkpoint should change what the agent does next
The agent creates a reviewable artifact
A design, screenshot, generated image, video, or diagram reaches a point where human judgment matters more than another automatic retry.
The harness opens a review checkpoint
Execution pauses before an irreversible or high-cost action. The checkpoint names what the reviewer must decide, instead of asking for generic feedback.
The human points to the evidence
Rectangles, arrows, points, freehand marks, labels, or a narrated recording tie each comment to the relevant visual region or moment.
The agent receives structured feedback
The returned annotations become workflow state. The agent can revise the artifact, request another review, or continue after explicit approval.
Three different reasons to involve a human
- Approval
- May the workflow continue?Publishing, spending credits, sending an external message, or accepting a final artifact.
- Correction
- What exactly must change?UI review, image revision, video feedback, or any task where spatial context prevents ambiguity.
- Escalation
- Is the agent outside its safe boundary?Conflicting evidence, missing permissions, uncertain policy, repeated failures, or a decision that requires accountable human judgment.
Failure boundaries
- Do not ask for human review after every harmless step. Constant approval destroys the speed benefit of an agentic workflow.
- Do not treat a vague comment such as “make it better” as structured feedback. The checkpoint should collect a decision, a marked region, or a concrete requested change.
- Do not let the model silently infer approval. The harness must preserve an explicit stop condition and record the human response before continuation.
- Do not confuse AnyCap with the whole harness. AnyCap supplies the review and media capability; scheduling, permissions, retries, and continuation policy remain the harness's responsibility.
Continue from here
Run the review workflow →
Install the Human Interaction skill and inspect the exact annotation workflow.
Understand the harness →
See where permissions, stop conditions, retries, and state belong.
Read visual evidence →
Use image understanding when the next step depends on a screenshot or marked artifact.
CLI version and updating · 0.6.5
Current release checked October 21, 2026: 0.6.5. Use the update command for your installation method, then verify the version and login in the same environment that runs your agent.
Direct binary installation
anycap updatenpm installation
npm install -g @anycap/cli@latestanycap --version
anycap statusVersion 0.6.5 retries transient downloads, recovers an expired video link by querying the same task, and saves multiple image outputs to numbered files. After a video download failure, resume the existing task instead of generating again.
anycap video tasks wait <task-id> -o result.mp4Dated examples retain the CLI version, output and charge from the original run. Updating the CLI does not revalidate an old result. Check the live model schema and current pricing before a new billed task.