# Ada — AI Agents & Assistants

Ada by Ada Support Inc. holds a panel rating of 2/5 from 6 AI judges (category median 2.5/5), as of 2026-11-03. Provenance: provenance unknown; sovereignty: not determined.

- Vendor: Ada Support Inc. (https://ada.cx)
- Category: [AI Agents & Assistants](https://whats-best.ai/software/ai-agents.md)
- Provenance (editorial classification): provenance unknown
- Canonical page: https://whats-best.ai/software/ai-agents/ada
- Alternatives: https://whats-best.ai/software/ai-agents/ada/alternatives ([markdown](https://whats-best.ai/software/ai-agents/ada/alternatives.md))
- Data as of: 2026-11-04 · evaluated 2026-11-03 · oldest source captured 2026-11-03

**AI-generated.** Every score, rationale and verdict here is written by a panel of AI judges from public evidence — an analysis, not a hands-on test. Every fact quotes the vendor page it was read from. No score can be bought. How scores are made: https://whats-best.ai/methodology

## At a glance

- Vendor: Ada Support Inc.
- Headquarters: Not stated on the vendor’s pages as of 3 Nov 2026
- Data hosting: Not stated on the vendor’s pages as of 3 Nov 2026
- Free plan: Not stated on the vendor’s pages as of 3 Nov 2026

## The panel's verdict

Ada is an AI agent platform whose documentation is strongest on connections and controls. Integrations and knowledge scored 6 to 7, built on eight knowledge-source connectors — Zendesk, Salesforce, ServiceNow and Microsoft Dynamics among them — syncing as fast as every 15 minutes; admin and access also scored 6 to 7, on SAML 2.0 single sign-on and a filterable, CSV-exportable audit log; agent capabilities holds at 6. The weakness sits underneath. Processing and models scored 1 to 2: no captured page names the models behind the product, who runs them or where inference happens. Sovereignty scored 1 to 2 — we found no public information on the contracting entity's jurisdiction, data residency, hosting or subprocessors; the only regional signal is US, EU and CA (Maple) agent endpoints. Data use and training holds at 4: retention is concrete — attachments after 7 days, end-user data after 2 years — but we found no public information on whether data trains models or on a data processing agreement. Judges' scores sit close together, with no criterion spanning more than one point; no prices appear on any captured page.

**Speaks for it:**
- Retention documented in concrete figures — attachments deleted after 7 days, end-user data after 2 years — with a bulk deletion API, GDPR erasure on demand and export before expiry
- Eight knowledge-source connectors documented, including Zendesk, Salesforce, ServiceNow and Microsoft Dynamics, syncing as fast as every 15 minutes
- SAML 2.0 single sign-on with any identity provider, plus an audit log filterable by actor, activity, entity and interface and exportable as CSV
- Every Action run logs the request data, response data and whether it succeeded, with sample-value testing plus test conversations, test cases and simulations
- Playbooks combine conditions, actions and responses into multi-step workflows built without code

**Held against it:**
- No captured page names the models behind the product, who runs them or where inference happens — processing and models scored 1 to 2
- Sovereignty scored 1 to 2 — we found no public information on the contracting entity's jurisdiction, data residency, hosting or subprocessors, and the only regional signal is US, EU and CA (Maple) agent endpoints
- We found no public information on whether prompts, transcripts or knowledge train a model, or on a data processing agreement
- Provisioning is manual — accounts are deleted and re-added to move users onto single sign-on, and initial setup requires an Ada representative
- We found no public information on configurable human approval before consequential agent actions, or on triggers and schedules

**Best for:**
- You run customer support on Zendesk, Salesforce, ServiceNow or Microsoft Dynamics and want your existing knowledge base to drive the agent
- Your IT team needs SAML 2.0 single sign-on and a searchable audit trail of who changed what, when and through which interface
- You need published retention schedules backed by deletion tooling — bulk deletion API, GDPR erasure on demand, export before expiry
- You want multi-step workflows built without code, with each run's request and response data logged

**Avoid if:**
- You must know which models run your conversations and where inference happens before procurement — processing and models scored 1 to 2
- You cannot sign without a data processing agreement and subprocessor disclosure — sovereignty scored 1 to 2 and we found no public information on either
- You expect automated user provisioning — moving accounts onto single sign-on is documented as a manual delete-and-re-add, and initial setup runs through an Ada representative
- Your knowledge lives in file stores or mailboxes rather than help centres — the documented connectors cover knowledge bases and service desks

## Scores by judge and criterion

Scores out of 5, each judge scoring independently against the published rubric (v1). "n/r" = not rated: the vendor publishes no price, or the judge found no public information on that criterion.

| Criterion | The Head of IT | The Data Protection Officer | The Automation Lead | The Customer-Service Director | The Works Council Member | The Skeptic |
| --- | --- | --- | --- | --- | --- | --- |
| Data use, training & retention | 2/5 | 2/5 | 2/5 | 2/5 | 2/5 | 2/5 |
| Models & processing location | 0.5/5 | 1/5 | 1/5 | 1/5 | 1/5 | 0.5/5 |
| Admin, identity & access controls | 3/5 | 3/5 | 3.5/5 | 3/5 | 3/5 | 3/5 |
| Integrations, connectors & knowledge | 3/5 | 3.5/5 | 3.5/5 | 3.5/5 | 3.5/5 | 3/5 |
| Agent capabilities & guardrails | 3/5 | 3/5 | 3/5 | 3/5 | 3/5 | 3/5 |
| European sovereignty | 1/5 | 0.5/5 | 1/5 | 1/5 | 1/5 | 1/5 |
| Pricing transparency | n/r | n/r | n/r | n/r | n/r | n/r |
| **Weighted verdict** | **2/5** | **2/5** | **2.5/5** | **2.5/5** | **2/5** | **2/5** |

### The judges

- **The Head of IT** (v1.0): Has to roll an AI assistant out to eight hundred staff without a second shadow-IT wave. Wants SSO and SCIM, groups that decide who gets which model, agent and connector, answers that respect SharePoint permissions, audit logs for the SIEM, and a deployment option that is not "trust us".
- **The Data Protection Officer** (v1.0): Signs the DPA and gets asked where a prompt goes. Wants every model provider named as a subprocessor with its region, training excluded for all of them, retention the company controls, and an EU-only switch that also covers agents and connectors — not just the chat window.
- **The Automation Lead** (v1.0): Builds the agents that file tickets, draft offers and chase approvals across the ERP, CRM and wiki. Wants tools and actions with scoped permissions, MCP and an API, approval steps before anything is sent, run logs, and a way to test an agent before the whole company uses it.
- **The Customer-Service Director** (v1.0): Runs a contact centre with forty agents and wants half the routine calls and chats answered by an AI agent. Wants handover to a human with the full context, actions in the order and ticket systems, evaluation before go-live, and a price per conversation the CFO can forecast.
- **The Works Council Member** (v1.0): Has a co-determination right the moment a tool can monitor staff, and an AI assistant logs every prompt. Wants usage reports that can be aggregated or pseudonymised, prompt logging rules set out in writing, a human approving what agents do to colleagues, and no training on staff input.
- **The Skeptic** (v1.0): Has read "European AI" on a wrapper that sends every prompt to a US model, "agents" that are saved prompts, and "we never train on your data" with no word on the model provider behind it. Asks which model answers, where it runs, what it may do unsupervised, and what a thousand seats cost.

## European sovereignty — proven facts

Built only from facts on the vendor's own pages; a dimension we could not prove is left open, never scored as zero. Headline: not determined.

| Dimension | Finding | Points | Source |
|---|---|---|---|
| Legal entity | Not determined | — | — |
| Hosting location | Not determined | — | — |
| Hosting options | Not determined | — | — |
| Open source | Not determined | — | — |
| Data processing agreement | Not determined | — | — |
| Transfer impact assessment | Not determined | — | — |

## Key facts

Each fact is the vendor's own statement, cited to the source page it was read from ([S*n*] → Sources).

**Compliance**
- Retention policy reference: Trust Center: Customer Data Retention Policy [S1]

**Data**
- Attachment retention: 7 [S1]
- Bulk deletion API: yes [S1]
- Conversation retention: yes · 6 · 2 [S2]
- End user retention: 2 [S1]
- Export before deletion: yes [S1]
- GDPR erasure support: yes [S1]
- Llm zero retention: yes [S1]
- Redaction: yes [S1]
- Sunshine image not stored: yes [S1]
- Transcripts with personal data: no [S1]

**Integrations**
- Article size limit: 100 [S5]
- Contentful regions: US · EU · CA (Maple) [S5]
- Contentful webhook: POST · yes [S5]
- Custom setup available: Additional integrations and customizations available via Ada representative [S7]
- Dixa sync frequency: 6 [S5]
- Dynamics language default: English - United States [S5]
- Dynamics sync frequency: 15 [S5]
- Gladly answer limit: alphabetical · 1000 [S5]
- Gladly sync frequency: 6 [S5]
- Handoff options: Zendesk Messaging · Zendesk Chat · Salesforce Chat · Salesforce Messaging · custom solution by Ada Solutions team [S7]
- Helpjuice private internal articles: yes · yes [S5]
- Helpjuice sync frequency: 2 [S5]
- Knowledge API: yes [S5]
- Knowledge API source management: rename · availability_rules · delete [S5]
- New language ingestion delay: 15 [S5]
- Public knowledge required: public-facing [S5]
- Salesforce channel visibilities: Public Knowledge Base · Customer Portal · Partner Portal · Internal App [S5]
- Salesforce data categories as tags: yes [S5]
- Salesforce knowledge categories as tags: yes [S6]
- Salesforce knowledge external client apps: Client Credentials OAuth flow via External Client Apps [S6]
- Salesforce knowledge legacy support: 2026-03-17 [S6]
- Salesforce knowledge multiple connections: yes [S6]
- Salesforce knowledge sync filters: /data category · /locale [S6]
- Salesforce oauth flow: Client Credentials OAuth [S5]
- Salesforce sync frequency: 15 [S5]
- Servicenow sync frequency: 15 [S5]
- Supported sources: Zendesk · Salesforce · Contentful · Dixa · Gladly · ServiceNow Knowledge Management · Helpjuice · Microsoft Dynamics [S5]
- Sync frequency general: 15 [S5]
- Zendesk labels limit: 25 [S5]
- Zendesk multiple help centers: yes [S5]
- Zendesk private articles: yes [S5]

**Product**
- Action block configuration: Action blocks are configured by mapping variables to the Action's inputs and outputs [S8]
- Action block output autocommunication: yes [S8]
- Action blocks overview: Every Action in an AI Agent gets a block in the block drawer that can be dragged into a Process, regardless of whether the Action is active [S8]
- Action import json: JSON · yes [S7]
- Action logging: yes · yes · yes [S2]
- Action testing: Actions can be tested with sample values to verify API functionality [S7]
- Actions definition: Actions are tasks the AI Agent can perform, e.g. retrieving data from external systems or completing workflows [S7]
- Archival limitation: no [S2]
- Article management: yes [S5]
- Audit log activities: Created · Updated · Deleted · Activated · Deactivated · Invited · Executed [S3]
- Audit log autorefresh pagination: yes · yes [S3]
- Audit log default range: 30 [S3]
- Audit log entities: Playbooks · Articles · Knowledge sources · API tools · Code tools · Processes · Greetings · Handoffs · Proactives · Variables · Glossary terms · Coaching · Test Cases · Simulations · Topics · Intents · API keys · Team Access · SSO configur… [S3]
- Audit log entry columns: Timestamp (UTC) · Activity · Entity · Actor · Interface [S3]
- Audit log export: csv · 10000 · yes [S3]
- Audit log filters: Is · Is not · Interface · Actor · Activity · Entity · yes [S3]
- Audit log interfaces: Ada Dashboard · API · MCP · Import · Export [S3]
- Audit log purpose: Audit log records configuration changes to the AI Agent as a chronological, searchable history of actor, activity, entity and interface [S3]
- Audit log search: Search box finds entries by entity name [S3]
- Automatic sync: yes [S5]
- Availability rules: yes [S5]
- Channels voice social separate: Voice and Social channels may need to be enabled separately for billing reasons [S7]
- Conversation view: Conversation View provides a library of end-user conversations with the AI Agent for review and fine-tuning [S2]
- Default date range: 180 · yes [S2]
- Details pane: yes · yes · yes · yes · yes [S2]
- Filter types: include_test_user · ar_classification · coaching · csat · nps · article_source · article · action · playbook · conversation_topic · engaged · handoff · live_agent · language · channel · browser · device · variable · moderation [S2]
- Greeting customization: Greeting text can be customized with optional variations [S7]
- Moderation filter categories: Self-harm · Violence · Hate speech · Harassment · Sexual content [S2]
- Multilingual behavior translation: English only [S5]
- Multilingual content: yes [S5]
- Multilingual language match: language-matched retrieval [S5]
- Playbook AI generation: Playbooks can be generated via AI from a product area and use case, or a custom description [S7]
- Playbooks definition: Playbooks combine conditions, actions, and responses to create tailored conversational paths for multi-step workflows [S7]
- Reasoning log: yes · yes [S2]
- Related article creation: yes [S5]
- Related session timeout: yes [S4]
- Related web import: yes [S5]
- Resolution classification history: statistical sample only · 2024-07-31 [S2]
- Search syntax: plain words · quotation phrases · wildcard * · yes · - · \| · ~ · parentheses [S2]
- Setup permissions: Automation setup requires a role with edit permissions, Agent or higher [S7]
- SSO available: yes [S4]
- SSO multiple instances: yes [S4]
- SSO name id format: email [S4]
- SSO no direct idp login: no [S4]
- SSO requires representative: yes [S4]
- SSO saml2: yes [S4]
- SSO single login method: yes [S4]
- SSO sp okta: Okta [S4]
- SSO user attributes: email · firstName · lastName [S4]
- SSO user provisioning: delete and re-add user accounts with SSO login type; assign Ada Support app in IDP [S4]
- Summary language coverage: yes [S2]
- Summary rules: 3 [S2]
- Test capability: AI Agent can be tested via the Test navigation option to start a conversation [S7]
- Tokens required for actions: Tokens must be set up before creating Actions; tokens provide secure authentication to external systems [S7]
- Transcript update latency: 10 [S2]
- Voice interruption annotations: Voice conversation view shows inline [Interrupted by end user] annotations for barge-in [S6]
- Voice interruption coverage: Covers interruptions during speech, short utterances, and before the agent begins speaking [S6]

## Questions

### Is Ada European?

Not determined: the vendor’s pages as captured do not say where Ada is based.

### Where does Ada store data?

Not stated on the vendor’s pages as of 3 Nov 2026.

### Does Ada have a free plan?

Not stated on the vendor’s pages as of 3 Nov 2026.

### What are the best alternatives to Ada?

As of 4 Nov 2026, the panel rates [Langdock (4/5)](https://whats-best.ai/software/ai-agents/langdock), [Dust (3.5/5)](https://whats-best.ai/software/ai-agents/dust) and [Unique AI (3.5/5)](https://whats-best.ai/software/ai-agents/unique-ai) highest among the other 18 AI Agents & Assistants products evaluated. Ratings that look equal are rounded to half stars; the order uses the unrounded rating, then the name. The highest-rated European alternative is [Langdock](https://whats-best.ai/software/ai-agents/langdock) (EU-Made). Ratings are the AI panel’s opinion, formed from public evidence: [how scores are made](https://whats-best.ai/methodology#ordering). The full list, with European products first: [Ada alternatives](https://whats-best.ai/software/ai-agents/ada/alternatives).

## What this page leaves out

- We found no public information on pricing on the pages we read (docs.ada.cx/docs/other/data-retention, docs.ada.cx/docs/optimization/conversations/response-training, docs.ada.cx/docs/other/audit-log, docs.ada.cx/docs/other/team-access/sso, docs.ada.cx/docs/knowledge/content-ingestion/knowledge-integration, docs.ada.cx/2026-03-18-salesforce-knowledge-v2 and 2 more). If the vendor publishes it somewhere else, send us the page.
- 1 product fact could not be confirmed on the vendor’s page as captured and was left out of this page and of the panel’s material.

## Sources

- [S1] Data use, training & retention — found from sitemap: https://docs.ada.cx/docs/other/data-retention (checked 2026-11-03)
- [S2] Data use, training & retention — found from sitemap: https://docs.ada.cx/docs/optimization/conversations/response-training (checked 2026-11-03)
- [S3] Admin, identity & access controls — found from sitemap: https://docs.ada.cx/docs/other/audit-log (checked 2026-11-03)
- [S4] Admin, identity & access controls — found from sitemap: https://docs.ada.cx/docs/other/team-access/sso (checked 2026-11-03)
- [S5] Integrations, connectors & knowledge — found from sitemap: https://docs.ada.cx/docs/knowledge/content-ingestion/knowledge-integration (checked 2026-11-03)
- [S6] Integrations, connectors & knowledge — found from sitemap: https://docs.ada.cx/2026-03-18-salesforce-knowledge-v2 (checked 2026-11-03)
- [S7] Agent capabilities & guardrails — found from sitemap: https://docs.ada.cx/docs/welcome/getting-started/enhance-your-ai-agent-with-automation (checked 2026-11-03)
- [S8] Agent capabilities & guardrails — found from sitemap: https://docs.ada.cx/docs/automation/processes/blocks/action-blocks (checked 2026-11-03)

---

Cite as: whats-best.ai, "Ada — AI Agents & Assistants", AI panel analysis, as of 2026-11-04. https://whats-best.ai/software/ai-agents/ada

Corrections: https://whats-best.ai/correct/1364?target=page