Procore AI Go

# Fix list: Procore AI Go

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/procore-ai-go, the October 2026 research run, assessed 21 October 2026. Grade F, 24.4 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Procore AI Go: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Agent ergonomics, 5 out of 100, up to 15.4 more on the total

Why it scored 5: These lines measure an interface an agent calls, and Procore AI Go has none. The app's source cards, chat search, push-to-talk and stated session limits help the person using it (5). Nothing else applies. Total 5.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 2. Schema & documentation, 9 out of 100, up to 14.8 more on the total

Why it scored 9: No API, OpenAPI file, webhook event or MCP tool for Procore AI Go (0). No llms.txt; www.procore.com/llms.txt returns 404 and the support site's returns an HTML page (0). The support articles explain for a person what the app does, what it can't do (no creates or updates, no custom agents) and that broad questions spanning many records are less reliable (6 of 20). No typed inputs an agent could call (0). Step-by-step examples for people and the access-denied screen documented, with no error responses (3 of 15). No changelog for the app (0). Total 9.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 3. Payments & pricing, 0 out of 100, up to 12.5 more on the total

Why it scored 0: No x402, MPP or L402 (0 of 40). No published price; Procore quotes by Annual Construction Volume and the Digital Coworker packages have no public price (0 of 20). No free tier or trial found (0). Access comes with a Procore contract and a person on an iPhone (0). Total 0.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 4. Reliability, 40 out of 100, up to 12 more on the total

Why it scored 40: Read with the hosted lines, for an app only people use. status.procore.com (Atlassian Statuspage) has component history and an RSS feed, with mobile, API and tool components and none for Procore AI or Procore AI Go (20). In the 90 days to 21 October, the feed lists short incidents, among them intermittent access errors in US01 and US02 on 24 July traced to a network provider, Datagrid unavailable for about 20 minutes on 7 August, a Daily Log blank page on 1 September and platform-wide intermittent errors for about 25 minutes on 9 October. No outage of an hour or more of a core service was found, so minor only (20). No rate limits apply, since there is no API (0). No retry guidance (0). No SLA found; the subscription terms weren't readable (0). Open beta, not generally available (0). Total 40.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 5. Security & auth, 39 out of 100, up to 10.7 more on the total

Why it scored 39: No credential an outside agent could hold (0). The app follows each user's existing Procore permissions, needs a Procore AI role on each project and a company-level opt-in by a Company Administrator, and is read-only in the beta (12 of 20). Answers draw on project records and user photos that can carry third-party text, with no guidance on prompt injection found (5 of 15). Company Administrators get credit usage reports and itemised transaction logs in Datagrid's Control Tower, with no per-question log documented for the app (8 of 15). The trust page states ISO 27001:2013 and SSAE18 SOC 2 and there is a vulnerability reporting page; the reports weren't seen and there is no security.txt (14 of 20). Total 39.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 6. Maintenance & community, 35 out of 100, up to 5.7 more on the total

Why it scored 35: Read for a closed service. Launched on 21 October 2026, within 30 days (30). No earlier dated releases of the app in 90 days were found (0). Help centre articles, in-app beta feedback through TestFlight and a community site, with no changelog for the app (5 of 15). No SDK or registry entry for the app (0). No package (0). Total 35.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 7. Transparency & trust, 48 out of 100, up to 4.6 more on the total

Made of editorial 16, provenance 80.

Why it scored 48: Closed service. Procore publishes User Terms, Online Subscription Terms and AI Terms for its generative AI tools, but each page draws its text by script and none was read, so only their existence is scored (5 of 30). The support articles say photos aren't saved to the project and are used only in their conversation, and the press release says session history is kept on the device. The Privacy Notice and DPA weren't readable, and no statement on which AI models process voice questions was found (8 of 30). No deprecation policy for a beta (0 of 20). The trust page says data is stored with Amazon Web Services or another provider, without naming AI subprocessors (3 of 20). Total 16.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- unchecked: the text of the User Terms, Online Subscription Terms, AI Terms, Privacy Notice and DPA. Each page loads its text by script and the served HTML holds only navigation, so dates, training on customer data and any SLA weren't read.
- unchecked: whether Procore's developer portal documents an MCP server or any endpoint for Procore AI. developers.procore.com draws its pages by script. The Digital Coworker FAQ mentions Procore AI using "API calls via the MCP" for recent data, which describes its own back end, not an outside interface.
- unchecked: the TestFlight listing. The download link is shared only by a customer's administrator, so no dated store listing exists to read.
- unchecked: v2.support.procore.com/release-notes, disallowed by robots.txt.
- The About article counts a Datagrid standalone account with a linked teamspace as qualifying, while the Set Up article and the press release name only the Digital Coworker packages. Recorded as a difference between the vendor's pages, not deducted.
- No earlier first-hand date than 21 October 2026 was found. The support articles carry no date, and the 23 July 2026 Digital Coworker release doesn't mention the app.
- Not one of our own products. Procore AI Go answers questions from Procore records and doesn't do the job of LocalGhost or letme.
- Vendor claims not checked: "the leading global provider of construction management software", over three million projects across 150 countries, and two to six hours a week recovered per person from the Procore and Dodge report.

## Weaknesses

- No API, webhook or MCP tool an outside agent can use to ask Procore AI Go anything
- Open beta on iOS through TestFlight only, with no App Store or Android version
- Needs a Digital Coworker package sold by custom quote, and every question uses Procore Credits
- It can't create or update Procore items yet; write actions and agents are announced for later
- The status page has no component for Procore AI or Procore AI Go

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Don't plan to call Procore AI Go. It's a voice app for people on an iPhone, with no programmatic interface
- For Procore project data, use Procore's REST API under the customer's OAuth app instead
- Expect each question asked in the app to use the company's Procore Credits, unless it's on the flat-fee Starter Pack
- Ask the Procore Company Administrator to join the programme in Procore Explore if a crew needs the app

## What the review panel asked for

- publish readable AI terms and model providers
- Publish credit rates
- documented API for the app
- a dated changelog for the app
- a status component for Procore AI

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.