Skip to content

docs: update paid-agent evidence claims#264

Merged
abrichr merged 1 commit into
mainfrom
agent/paid-agent-public-claims-20260721
Jul 21, 2026
Merged

docs: update paid-agent evidence claims#264
abrichr merged 1 commit into
mainfrom
agent/paid-agent-public-claims-20260721

Conversation

@abrichr

@abrichr abrichr commented Jul 21, 2026

Copy link
Copy Markdown
Member

What changed

Synchronizes the public workflow catalog and templates with the bounded paid
computer-use-agent aggregates from merged
OpenAdaptAI/openadapt-flow#216
(exact Flow main e740a7e4b68ed5c6461bdcd6fbd086e8ac75c8be).

Vertical Trials Primary outcome Over-halt Silent incorrect Mean list-price cost
Insurance / openIMIS 3 3/3 correct 0/3 0/3 $0.4793/run
Lending / Frappe Lending 6 6/6 correct writes; 5/6 clean 1/6 post-write cost-cap halt 0/6 $0.4240/run
Healthcare / local OpenEMR 6 0/6 correct; 6/6 missing_write 0/6 0/6 $0.8901/run

This also fixes the stale openIMIS policy copy that still said there was no
agent arm while preserving the current Browser/Desktop/RDP/Citrix maturity
boundaries.

Dependency and honest scope

  • The public aggregate source is merged Flow feat(download): real Windows install-flow visuals with provenance #216 at exact main
    e740a7e4b68ed5c6461bdcd6fbd086e8ac75c8be.
  • Paid trials used separately provisioned baselines from the earlier
    compiled/API subsets. They are not matched head-to-head rows or a three-arm
    matrix.
  • N is 3-6 per environment. This is local engineering evidence, not a
    publication, certification, broad computer-use-agent claim, customer result,
    or design-partner result.
  • All paid tasks used the Browser (Playwright) Beta substrate. They are not
    Windows, RDP, Citrix, or VDI evidence.
  • The OpenEMR agent exhausted its action budget without the required effect;
    the oracle classification is missing_write, not over-halt.
  • Public copy retains bounded aggregates and caveats only. Raw per-run rows,
    screenshots, fingerprints, detailed cost ledgers, and application-specific
    driver/oracle recipes remain private.

Docs counterpart: OpenAdaptAI/openadapt-ops#57.

Exact prepared state

  • base: 47a3611548dcb4ab395e237380c3764b6375003c
  • head: ebbb54702289ebf06e00eca1bd5b4261dc9edb31
  • commits: 1
  • changed files: data/templates.js, data/workflowCatalog.js

Validation

  • npm test: 124/124 passed
  • git diff --check: passed
  • repository-wide stale current-claim search: passed

@netlify

netlify Bot commented Jul 21, 2026

Copy link
Copy Markdown

Deploy Preview for cosmic-klepon-3c693c ready!

Name Link
🔨 Latest commit ebbb547
🔍 Latest deploy log https://app.netlify.com/projects/cosmic-klepon-3c693c/deploys/6a5fb49d4caeff0009d89843
😎 Deploy Preview https://deploy-preview-264--cosmic-klepon-3c693c.netlify.app
📱 Preview on mobile
Toggle QR Code...

QR Code

Use your smartphone camera to open QR code link.
🤖 Make changes Run an agent on this branch

To edit notification comments on pull requests, go to your Netlify project configuration.

Signed-off-by: abrichr <richard.abrich@mldsai.com>
@abrichr
abrichr force-pushed the agent/paid-agent-public-claims-20260721 branch from f8dc753 to ebbb547 Compare July 21, 2026 18:04
@abrichr
abrichr marked this pull request as ready for review July 21, 2026 23:33
@abrichr
abrichr merged commit abaf8b3 into main Jul 21, 2026
9 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant