Yield demo video
Screen recording of Yield, 3:45, file dated 2026-11-08. The voice is AI-generated (ElevenLabs) and the data on screen is made up.
Recorded 2026-11-08. This video shows one journey: a real run on Claude, the Needs-you approval clicked by the recording script (as its caption says), the spending cap, and the length-limit warning on a staged reply from a stand-in model (as its caption says). It does not show every page; the full-product video is in production. The scorecard in the video reads 76; the site shows 70/100 on our own rubric (2026-11-08). Re-recorded 2026-11-08 against agentorchestration-autonomous-aigov-platform main dfaae6c; caption at 1:04-1:17 now reads $0.25, $1.00 or $5.00; added the Needs-you length-limit warning (#9), shown on a staged reply from a stand-in model; the card text and date are updated. Encoded CRF 16, -16.3 LUFS.
This button opens your email app with the subject "Waitlist: Yield". There is no sign-up database yet; your email comes to support@shipitworks.com and we keep it only to tell you when Yield is ready. To be removed, send an email with the subject "Remove me". Privacy notice.
Transcript
Every word spoken in the video, in 16 parts, each with the time it starts. Taken from the captions file.
0:03 Yield gives small jobs to an AI helper and keeps you in charge. This time it is a real run, on Claude, through the Anthropic API.
0:17 You pick a job, paste the notes, and set the most it may ever spend. One dollar.
0:25 The task starts. The Stage follows the real task. It thinks, it writes, and then it stops and asks.
0:35 Here is the whole text it wants to save. Nothing is saved yet. Show proof gives the fingerprint of those exact bytes.
0:46 In this recording, the script clicks Approve. In real use, a person does.
0:53 Finished. The page names the model, Claude Sonnet five point five, and what it cost, about one cent. The record checks out.
1:05 Now a task with a cap of almost nothing. The cap is checked before any call is made. It stops, says why, and nothing is spent.
1:18 One more case, staged for this recording. A stand-in model, not Claude, sends an answer that stops at its length limit. The Needs you card warns you to read the end before you save it.
1:35 Results adds up the spend from the task records. Only the one real run cost anything.
1:43 Eighteen runs, before and after the fixes. Before, Haiku missed items in the reply task, once finding none, and some answers were cut off at the length limit.
1:57 After the fix, no Haiku answer was cut off. Sonnet found every planted item both times. Times and costs come from the app. We make no claim about how long the work takes by hand.
2:29 Recorded on 2026-11-08, US Eastern time, against Yield main at commit dfaae6c. A real run on Claude Sonnet 5.5, about one cent. The script clicked Approve; in real use a person does. The cap test was started through the API. The length-limit scene used a stand-in model, not Claude.
2:53 Runs on Claude through the Anthropic API. ShipItWorks is not affiliated with Anthropic.
3:00 Yield 0.5.0, Beta. Our audit scored it 76 out of 100. Changes made since that audit were tested, but not re-audited.
3:10 Not done yet. No manual comparison was made. Approval time was not measured. A refused step is labelled price not known. The length-limit warning was shown on a staged reply, not on a real cut-off from Claude. The installer is older than the code.
3:29 The voice you just heard is AI-generated, using ElevenLabs. This walkthrough was recorded on the eighth of November, twenty twenty-six, US Eastern time.