agent · customer service

PolyAI agent

poly.aievidence retrieved Aug 6, 2026 – Aug 15, 2026view as JSON all customer service entries 55 alternatives

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

19 fields evidenced · 40 with no public information. Every value below links to the document it came from and the date we checked it.

1 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 of the evidenced values quotes 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 and vendors that state GDPR compliance AI agents and vendors that state HIPAA compliance AI agents and vendors that publish a self-reported performance figure

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

1/3 auto

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

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

Counts Runtime governance, each cited below.

Audit trail

1/3 auto

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

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

Counts Audit trail, each cited below.

Compliance

2/3 auto

Are compliance obligations attached per engagement?

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

Counts Compliance certifications and Regulatory alignment, 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
poly.ai · checked Aug 6, 2026 · source did not state this
Own liability cover: no public information
poly.ai · checked Aug 15, 2026 · source did not state this
Insurance carriers: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Coverage limits: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Indemnification: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Liability cap: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Audit trail: yes
“full visibility into every agent decision”
poly.ai · checked Aug 6, 2026
Tamper-evident log: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Explainability: not yet interpreted
“full visibility into every agent decision”
poly.ai · checked Aug 6, 2026
Runtime governance: governed by default
“Guardrails for compliance, brand, and experience Every agent is governed by default”
poly.ai · checked Aug 6, 2026
Permission scopes: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Compliance certifications: SOC 2, HIPAA, GDPR, PCI DSS
“Guardrails for compliance, brand, and experience Every agent is governed by default, with SOC 2, HIPAA, GDPR, PCI DSS as standard.”
poly.ai · checked Aug 6, 2026
Regulatory alignment: GDPR
“Guardrails for compliance, brand, and experience Every agent is governed by default, with SOC 2, HIPAA, GDPR, PCI DSS as standard.”
poly.ai · checked Aug 6, 2026
Outcome-based pricing: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Settlement mechanism: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Asset custody: no public information
poly.ai · checked Aug 15, 2026 · source did not state this
Dispute process: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
SLA terms: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Evaluation coverage: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Self-reported performance: Self-described as its 'most advanced frontier dialog model' (Dialog-RSN-1) with published benchmarks.
“Introducing Dialog-RSN-1, our most advanced frontier dialog model. See the benchmarks”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 14, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
poly.ai · checked Aug 15, 2026

Agency

Autonomy level: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Human oversight: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Goal complexity: multi-step
“Built for complexity. Better with every dialog. Dialog agents proven on the hardest conversations in the world, including fraud, outage, triage, multilingual disputes, and more.”
poly.ai · checked Aug 6, 2026
Action space: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Operating environment: chat, voice
“The Agentic Dialog Platform Build at the speed of thought. The enterprise platform where dialog agents get built, run, adapt, and iterate in real time.”
poly.ai · checked Aug 6, 2026
Initiative: no public information
poly.ai · checked Aug 6, 2026 · source did not state this

Safety

Safety evaluations: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Red teaming: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Safety policy: Guardrails for compliance, brand, and experience
“Guardrails for compliance, brand, and experience Every agent is governed by default, with SOC 2, HIPAA, GDPR, PCI DSS as standard.”
poly.ai · checked Aug 6, 2026
Usage restrictions: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Model or system card: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Incident reporting: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Third-party evaluations: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Data handling: SOC 2, HIPAA, GDPR, PCI DSS compliant
“Guardrails for compliance, brand, and experience Every agent is governed by default, with SOC 2, HIPAA, GDPR, PCI DSS as standard.”
poly.ai · checked Aug 6, 2026

Practicality

Pricing model: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Price point: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Availability: beta
“Now open to enterprise builders. Start building Request demo”
poly.ai · checked Aug 6, 2026
Deployment options: SaaS
“The Agentic Dialog Platform One platform to build, run, adapt, and govern dialog agents at enterprise scale, for every builder.”
poly.ai · checked Aug 6, 2026
Integrations: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Supported regions: multilingual (Croatian, implied global)
“Our customers can now get information quickly in their local language”
poly.ai · checked Aug 6, 2026
Support model: no public information
poly.ai · checked Aug 6, 2026 · source did not state this

Foundation models

Base models: Raven
“powered by our proprietary model trained on 1B+ enterprise conversations, Raven.”
poly.ai · checked Aug 6, 2026
Model provider: PolyAI
“powered by our proprietary model trained on 1B+ enterprise conversations, Raven.”
poly.ai · checked Aug 6, 2026
Model swappable: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Open weights: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Fine-tuning: yes
“The Agentic Dialog Platform Build at the speed of thought. The enterprise platform where dialog agents get built, run, adapt, and iterate in real time.”
poly.ai · checked Aug 6, 2026
Context window: no public information
poly.ai · checked Aug 6, 2026 · source did not state this

Ecosystem

Protocols supported: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Tool use: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Multi-agent: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
API access: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Open source: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Marketplace presence: no public information
poly.ai · checked Aug 6, 2026 · source did not state this

Impact

User base: Health insurance provider, Hotel and casino brand, Retail clothing brand, Global delivery company
“Health insurance provider 0 pt CSAT boost from day one Hotel and casino brand $ 0 .2M revenue from one voice agent Retail clothing brand 0 % reduction in seasonal hiring, saving $1 million+ Global delivery company 0 % of calls resolved without human agents”
poly.ai · checked Aug 6, 2026
Deployment scale: enterprise scale
“The Agentic Dialog Platform One platform to build, run, adapt, and govern dialog agents at enterprise scale, for every builder.”
poly.ai · checked Aug 6, 2026
Target sectors: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
High-risk domains: fraud, outage, triage, multilingual disputes
“Dialog agents proven on the hardest conversations in the world, including fraud, outage, triage, multilingual disputes, and more.”
poly.ai · checked Aug 6, 2026
Documented incidents: no public information
poly.ai · checked Aug 6, 2026 · source did not state this
Market recognition: no public information
poly.ai · checked Aug 15, 2026 · source did not state this