agent · agent skills sharing platform

Agentman

agentman.aievidence retrieved Aug 8, 2026 – Aug 27, 2026view as JSON all agent skills sharing platform entries

Indexed12 or more fields evidenced; not yet scored by a human against the rubric

23 fields evidenced · 32 with no public information. Every value below links to the document it came from and the date we checked it.

15 of those are quoted but not yet interpreted: we hold the source sentence and the date we read it, but nobody has written the answer to the question yet. Those rows show the quote and say so rather than repeating it back as an answer. Why these exist

1 absence has been read back against the source by an editor and confirmed.

16 of the evidenced values quote wording our own later capture of the same page no longer contains. Marked below, awaiting an editor.

Also appears in

AI agents and vendors that state SOC 2 AI agents that support the Model Context Protocol AI agents and vendors that state HIPAA compliance Self-hosted and on-premise AI agents AI agents and vendors that state ISO 27001 AI agents that state a human-in-the-loop control AI agents and vendors that state a tamper-evident audit trail

Trust gap

How this is scored

These scores are automated. A 1 or 2 counts how many fields this entry answers with a citation — not what those answers say. A 0 means every field for that dimension is recorded as undisclosed and none of the pages we captured mentions it. No one has scored this entry against the rubric yet.

Runtime governance

2/3 auto

Are scope, spend, and authority enforced while the agent runs?

Scored from 2 evidenced field(s): runtime_governance, permission_scopes. Automated score; capped at 2 pending review.

Counts Permission scopes and Runtime governance, each cited below.

Audit trail

2/3 auto

Is there a tamper-evident record of what it actually did?

Scored from 2 evidenced field(s): audit_trail, audit_trail_immutable. Automated score; capped at 2 pending review.

Counts Tamper-evident log and Audit trail, each cited below.

Compliance

1/3 auto

Are compliance obligations attached per engagement?

Scored from 1 evidenced field(s): compliance_certs. Automated score; capped at 2 pending review.

Counts Compliance certifications, each cited below.

Outcome settlement

unscored

Does payment depend on a verified result?

Insurance & indemnity

unscored

Can the deployment be insured, and is the customer indemnified?

Assurance

Insurance available: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Insurance carriers: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Coverage limits: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Indemnification: no public information
agentman.ai · checked Aug 8, 2026 · absence verified against this source
Liability cap: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Audit trail: Yes - immutable event trails for every agent decision/action, capturing skill version, citation, timestamp, and operator
“Immutable event trails for every agent decision and action — skill version, citation, timestamp, and operator captured on every step.”
agentman.ai · checked Aug 27, 2026
Tamper-evident log: Event trail described as immutable, covering skill version, citation, timestamp, operator per step
“Immutable event trails for every agent decision and action — skill version, citation, timestamp, and operator captured on every step.”
agentman.ai · checked Aug 27, 2026
Explainability: Every output traces to the skill version, source documents/systems read, decision made, and human approver if applicable
“Every output traces back to its source: which skill version ran, which documents or systems it read, what it decided, and who approved it if a person was in the loop.”
agentman.ai · checked Aug 27, 2026
Runtime governance: not yet interpreted
“Permissioned Control who can view, edit, and publish — scoped by workspace, team, or individual, down to a single skill.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
agentman.ai · checked Aug 8, 2026
Permission scopes: not yet interpreted
“Per-skill access control Grant Read, Edit, or Admin per skill or across the whole workspace — plus Use-only on Business, which lets someone run a skill without reading it.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
agentman.ai · checked Aug 8, 2026
Compliance certifications: HIPAA BAA available now; SOC 2 and ISO 27001 certification audits in progress (not yet certified).
“HIPAA controls are in place with a BAA available; SOC 2 and ISO 27001 audits are underway.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
agentman.ai · checked Aug 26, 2026
Regulatory alignment: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Outcome-based pricing: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Settlement mechanism: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Dispute process: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
SLA terms: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Evaluation coverage: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this

Agency

Autonomy level: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Human oversight: not yet interpreted
“Human in the loop Consequential decisions wait for a person. Always reviewable.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
agentman.ai · checked Aug 8, 2026
Goal complexity: not yet interpreted
“Single loops that execute Review one contract. Verify one claim.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
agentman.ai · checked Aug 8, 2026
Action space: not yet interpreted
“A skill captures how your best people actually do the work — their procedures, judgment, and standards — so every agent runs it the same way, every time.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
agentman.ai · checked Aug 8, 2026
Operating environment: not yet interpreted
“Build once, use everywhere Your best skills, shared with the whole team — in Claude and ChatGPT .”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
agentman.ai · checked Aug 8, 2026
Initiative: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this

Safety

Safety evaluations: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Red teaming: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Safety policy: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Usage restrictions: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Model or system card: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Incident reporting: Breach notification procedures compliant with the HIPAA Breach Notification Rule (45 CFR Part 164, Subpart D)
“Breach notification procedures compliant with HIPAA Breach Notification Rule (45 CFR Part 164, Subpart D)”
agentman.ai · checked Aug 27, 2026
Third-party evaluations: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Data handling: Excluded from secondary use: the vendor states protected health information is not used for marketing, analytics or model training. No encryption standard is named in the cited span.
“PHI is never used for marketing, analytics, or model training”
agentman.ai · checked Aug 27, 2026

Practicality

Pricing model: not yet interpreted
“$0.50 per eligibility check vs. $7.97 CAQH benchmark”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
agentman.ai · checked Aug 8, 2026
Price point: Free tier (3 members, 10 private skills); Team $10/seat (3-seat min); Business $25/seat (5-seat min); Enterprise/Partner custom
“Free: 3 members and 10 private skills. Team: $10 per seat (3-seat minimum) with unlimited members and unlimited private skills, 14-day trial. Business adds per-skill access control, use-only sharing, approvals, and activity visibility at $25 per seat (5-seat minimum).”
agentman.ai · checked Aug 27, 2026
Availability: not yet interpreted
“Start building free”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
agentman.ai · checked Aug 8, 2026
Deployment options: Managed cloud (available now), on-premises (coming soon), air-gapped (on request)
“Deploy the platform your way. Agentman runs in our managed cloud today — and deploys inside your infrastructure for organizations that require it.”
agentman.ai · checked Aug 27, 2026
Integrations: not yet interpreted
“Also works in Claude Code · Cursor · Agentman agents — through one connection.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
agentman.ai · checked Aug 8, 2026
Supported regions: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Support model: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this

Foundation models

Base models: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Model provider: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Model swappable: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Open weights: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Fine-tuning: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Context window: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this

Ecosystem

Protocols supported: not yet interpreted
“Open SKILL.md standard, MCP integrations, and skills you can inspect and customize.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
agentman.ai · checked Aug 8, 2026
Tool use: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Multi-agent: not yet interpreted
“A harness orchestrates hundreds — all drawing from the same library your team owns and improves.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
agentman.ai · checked Aug 8, 2026
API access: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Open source: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this
Marketplace presence: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this

Impact

User base: not yet interpreted
“Trusted by Teams at”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
agentman.ai · checked Aug 8, 2026
Deployment scale: not yet interpreted
“Medman is what this looks like fully built. A complete medical back office running on Agentman skills — a production harness coordinating eligibility, inbox triage, and claims loops across 1,300+ payers”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
agentman.ai · checked Aug 8, 2026
Target sectors: not yet interpreted
“Built for firms that can't get this wrong. Permission management and auditing designed for legal, private equity, and healthcare”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
agentman.ai · checked Aug 8, 2026
High-risk domains: not yet interpreted
“Built for firms that can't get this wrong. Permission management and auditing designed for legal, private equity, and healthcare — where every decision needs a paper trail.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
agentman.ai · checked Aug 8, 2026
Documented incidents: no public information
agentman.ai · checked Aug 8, 2026 · source did not state this