Talkdesk Autopilot
Spectrum 0.2 beta · Public tier · read 2026-11-10 · not reviewed by its vendor yet
Customer-facing AI agent that resolves requests and completes tasks across voice, digital and email channels, handing over to a human agent when needed.
Standout. Autonomy 4 (Orchestrates): "By integrating with your CRM and ERP, Autopilot executes tasks"
Next unlock. Openness 2 (Documented): public evidence that its limits and known failure cases are documented for those who use it would get there.
Trust. FACT-Ray: 12 facts: 12 π Moderate · found by an agent, captured and hashed, checked by 2 other agents (same model family, shared repository); no human has signed it.
Standards constellation. 47 provisions lit across 8 of 8 instruments.
Evidence: 6 sources, captured and hashed · the card's page has the vault's read key · Not reviewed by its vendor yet · correct or claim this card
The walk down from this card: each dimension, the indicators its level stands on (a link to the indicator's row), the public source of each answer (a link out; dashed means available, not default) the instruments its provisions sit in (a link to the instrument) and each provision itself (a link to its own page). A solid frame is evidenced; a dashed frame is not yet evidenced, which is not a no.
What each level rests on
Autonomy: what does A4 Orchestrates rest on? 2 facts
I10 It works across several domains or systems
I19 The agent has full autonomy within boundaries; the person monitors
Reach: what does R2 Integrated rest on? 2 facts
I10 It works across several domains or systems
I11 It connects to external tools or services across a trust boundary
Control: what does C1 Stated rest on? 1 fact
I47 A limit on it is a rule in prose
Openness: what does O1 Disclosed rest on? 2 facts
I20 Its purpose and permitted tasks are stated in writing
I58 The data it uses is described
Each path has its verbs on the edges; every node is a link, the source opens the page, a dashed box is an open question, not a no.
This card rates a product as its vendor documents it, not anyone's deployment of it. A feature the operator has to turn on counts, and is marked as available. Levels are computed from the evidence below by published rules. A dimension with no evidence reads "not yet evidenced".
Autonomy: level 4, Orchestrates
What does the agent do on its own? Runs multi-step workflows across systems or coordinates other agents; a person sets goals and reviews outcomes. This level holds with: Ops center. As shipped, with nothing turned on, it is level 3, Acts.
I10It works across several domains or systems. Autopilot for email executes tasks such as processing refunds, re-routing shipments and managing appointments through integrations with CRM and ERP systems. "By integrating with your CRM and ERP, Autopilot executes tasks" Source (read, documented, captured 2026-11-10T15:45Z, sha2569b4949c9627ce1ff) · π Moderate · S1·R5·A1 ×3I19The agent has full autonomy within boundaries; the person monitors. Under the page heading Resolve requests autonomously with Talkdesk Autopilot, the page says that with CXA Operations Center people monitor live interactions, inspect execution behavior and enforce guardrails. "Monitor live interactions, inspect execution behavior, and enforce guardrails" Source (read, documented, available, captured 2026-11-10T15:45Z, sha256dfa1cc79d013e60b) · π Moderate · S1·R5·A1 ×3
This evidence touches 7 provisions: Salesforce, Microsoft, EAAMM.
Reach: level 2, Integrated
How connected is it? Documented connectors to common tools.
I10It works across several domains or systems. Autopilot for email executes tasks such as processing refunds, re-routing shipments and managing appointments through integrations with CRM and ERP systems. "By integrating with your CRM and ERP, Autopilot executes tasks" Source (read, documented, captured 2026-11-10T15:45Z, sha2569b4949c9627ce1ff) · π Moderate · S1·R5·A1 ×3I11It connects to external tools or services across a trust boundary. Talkdesk states that its AI agents use MCP to call external tools and services of third parties. "securely discover, invoke, and exchange information with external tools and services" Source (read, documented, captured 2026-11-10T15:45Z, sha25692ef8eab59b76e44) · π Moderate · S1·R5·A1 ×3
This evidence touches 8 provisions: Salesforce, Microsoft, OWASP, NIST AI RMF.
Next unlock: level 4, Ecosystem. Public evidence that agents operate across organisational boundaries or disparate stacks; and that others build on it: third parties publish integrations, skills or agents for it.
Control: level 1, Stated
Can people stay in command? Documents say how people approve, override or stop it.
I47A limit on it is a rule in prose. The press release gives a sample natural-language setup prompt for an AI agent that includes a rule to escalate to a live agent on a medical emergency. "Escalate to a live agent if the customer mentions a medical emergency" Source (read, documented, captured 2026-11-10T15:45Z, sha256132281985eaabae7) · π Moderate · S1·R5·A1 ×3
This evidence touches 1 provision: OWASP.
Next unlock: level 2, Configurable. Public evidence that high-impact actions need a person's approval; and that what it can reach is enumerated: scopes, permissions, tools.
Openness: level 1, Disclosed
Does it show its work? Says what it is for, and that it is AI, what its limits are or what data it uses.
I20Its purpose and permitted tasks are stated in writing. The product page states what Autopilot is for: resolving customer requests and completing tasks across channels. "agentic AI that resolves customer requests and completes tasks across voice and digital channels" Source (read, documented, captured 2026-11-10T15:45Z, sha256dfa1cc79d013e60b) · π Moderate · S1·R5·A1 ×3I58The data it uses is described. The product page names Talkdesk Data Cloud as the data AI Agents use to understand interaction history, intent and sentiment. "Leverage the Talkdesk Data Cloud so AI Agents understand history, intent, and sentiment" Source (read, documented, captured 2026-11-10T15:45Z, sha256dfa1cc79d013e60b) · π Moderate · S1·R5·A1 ×3
This evidence touches 9 provisions: NIST AI RMF, EU AI Act, AAGMM, EAAMM, Salesforce.
Next unlock: level 2, Documented. Public evidence that its limits and known failure cases are documented for those who use it.
How far to trust this card
Status: Draft. Draft means the facts were found in public pages and reviewed by agents. The company has not confirmed them and no customer has gone on record. FACT-Ray says how far each fact can be trusted: who says it (Source), how firmly it is recorded (Record) and who stands behind it (Accountability). It never changes a level.
- The facts: 12 facts: 12 π Moderate. Each is written beside its evidence above.
- The chain: found by an agent, captured and hashed, checked by 2 other agents (same model family, shared repository); no human has signed it.
- Who: produced by
gamma.studio@web-summit.dinis; checked bygamma.review@web-summit.dinisandgamma.approve@web-summit.dinis. The actors. - What would raise it: the company's own file at
/.well-known/fact-ray.json(Source 2), a customer's statement of use (Source 3), or a named person signing the card (how).
The standards constellation
One piece of public evidence can speak to several frameworks at once. "Touched" never means "complies". The share is of the provisions that can be read from outside.
| Instrument | Provisions touched | Of those publicly readable |
|---|---|---|
| Salesforce | 13 | 24 |
| EAAMM | 4 | 8 |
| OWASP | 3 | 18 |
| MCP authorization | 2 | 8 |
| AAGMM | 1 | 6 |
| Microsoft | 15 | 23 |
| NIST AI RMF | 8 | 20 |
| EU AI Act | 1 | 6 |
The 47 provisions lit
Each line item, with the facts that reach it. "Evidenced" is a link of the kind same: the fact is what the provision asks. "Partly" is a link of the kind part: the fact is one piece of it. "Its absence" points the other way. Each provision has its own page with its text and its place in the source.
| Provision | Instrument | Reached by | How far |
|---|---|---|---|
sf.a02 Level 0, how companies can advance from Level 0 to Level 1 | Salesforce | I67 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
sf.a04 Level 0, how companies can advance from Level 0 to Level 1 | Salesforce | I58 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
sf.a06 Level 0, how companies can advance from Level 0 to Level 1 | Salesforce | I67 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
sf.a07 Level 1, how to advance from Level 1 to Level 2 | Salesforce | I08 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
sf.a08 Level 1, how to advance from Level 1 to Level 2 | Salesforce | I58 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
sf.a12 Level 1, how to advance from Level 1 to Level 2 | Salesforce | I67 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
sf.L2 Level 2: Simple Orchestration, Single Domain | Salesforce | I08 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
sf.a16 Level 2, how to advance from Level 2 to Level 3 | Salesforce | I10 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
sf.L3 Level 3: Complex Orchestration, Multiple Domain | Salesforce | I10 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
sf.a17 Level 3, how to advance from Level 3 to Level 4 | Salesforce | I10 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
sf.a24 Level 3, how to advance from Level 3 to Level 4 | Salesforce | I67 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
sf.a27 Level 4, how to maximize value | Salesforce | I67 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
sf.a29 Level 4, how to maximize value | Salesforce | I67 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
eaamm.L3 L3 Consultative (survey item Q9) | EAAMM | I17 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
eaamm.L5 L5 Autonomous (survey item Q9) | EAAMM | I19 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
eaamm.D1 Readiness dimension 1 | EAAMM | I65 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
eaamm.D2 Readiness dimension 2 | EAAMM | I58 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
owasp.AT3 AT3 Citizen Developer Agent | OWASP | I03 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
owasp.AT6 AT6 Externally Extended Agent | OWASP | I11 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
owasp.k04 Maturity Level 0 Unaware and Ad Hoc, key enterprise action | OWASP | I47 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
mcp.01 Authorization (draft) | MCP authorization | S3 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
mcp.02 Authorization (draft) | MCP authorization | S3 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
aagmm.GD-05 GD-05 | AAGMM | I58 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
ms.100.1.1 100: Initial, AI strategy and experience | Microsoft | I65 (its absence) | its absence · π Moderate · S1·R5·A1 ×3 |
ms.100.5.3 100: Initial, Organization and culture | Microsoft | I67 (its absence) | its absence · π Moderate · S1·R5·A1 ×3 |
ms.200.1.1 200: Repeatable, AI strategy and experience | Microsoft | I65 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
ms.200.1.3 200: Repeatable, AI strategy and experience | Microsoft | I65 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
ms.200.2.1 200: Repeatable, Business strategy | Microsoft | I08 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
ms.200.2.5 200: Repeatable, Business strategy | Microsoft | I67 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
ms.200.4.2 200: Repeatable, Technology and data | Microsoft | I10 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
ms.300.1.1 300: Defined, AI strategy and experience | Microsoft | I65 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
ms.300.1.4 300: Defined, AI strategy and experience | Microsoft | I67 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
ms.300.2.2 300: Defined, Business strategy | Microsoft | I67 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
ms.400.1.1 400: Capable, AI strategy and experience | Microsoft | I65 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
ms.400.1.3 400: Capable, AI strategy and experience | Microsoft | I67 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
ms.400.2.1 400: Capable, Business strategy | Microsoft | I10 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
ms.400.2.3 400: Capable, Business strategy | Microsoft | I67 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
ms.500.2.1 500: Efficient, Business strategy | Microsoft | I19 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
nist.GOVERN-6.1 GOVERN 6.1 | NIST AI RMF | I11 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
nist.MAP-1.1 MAP 1.1 | NIST AI RMF | I20 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
nist.MAP-1.3 MAP 1.3 | NIST AI RMF | I20 (partly), I65 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
nist.MAP-1.4 MAP 1.4 | NIST AI RMF | I67 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
nist.MAP-2.1 MAP 2.1 | NIST AI RMF | I20 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
nist.MAP-3.1 MAP 3.1 | NIST AI RMF | I67 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
nist.MAP-3.3 MAP 3.3 | NIST AI RMF | I20 (evidenced) | evidenced · π Moderate · S1·R5·A1 ×3 |
nist.MAP-4.1 MAP 4.1 | NIST AI RMF | I11 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
aiact.art-13 Article 13 | EU AI Act | I20 (partly), S3 (partly) | partly · π Moderate · S1·R5·A1 ×3 |
Upper layers
The public card is the front door. The same evidence, read with the governance rules, is this agent's GAMMA-Ray rating: freedom, governance, the level held, the grant and a work order. That layer is written for an operator.
The vault
Every source behind this card was captured and hashed into a public sgit vault (2y7brc8i): captures.json lists each URL with the SHA-256 of what was fetched and when. Read key:
sgit_public_read_3d0b44fafd298169b107547dca711422049fe47f11a1f3d00f99b74f7377f6e7:2y7brc8i
With sgit: sgit clone sgit_public_read_3d0b44fafd298169b107547dca711422049fe47f11a1f3d00f99b74f7377f6e7:2y7brc8i.