# Alternatives to IrisAgent > Source: https://theagentsindex.com/irisagent/alternatives (current datasheets, evidence-ranked) Candidates share the baseline category or are previously researched peers. Requirements, preserved strengths, explicit trade-offs and research coverage decide the order; paid tier does not. ## Shortlist ### 1. Maven AGI Enterprise AI agent platform for customer support across chat, email, voice and web. **Research coverage:** 33/35 criteria **Where it improves on IrisAgent:** - [Claude: yes — The Master Services Agreement names Anthropic, alongside OpenAI, as one of exactly two LLM providers generating output today, and lists it as a contracted sub-processor rather than an optional integration.](https://www.mavenagi.com/legal/msa) **Trade-offs against IrisAgent:** - [Open models: no — The agreement enumerates its LLM providers as OpenAI and Anthropic and promises written notice if any other is added, a closed list with no open-weight or self-hosted model in it.](https://www.mavenagi.com/legal/msa) - [Self-hosted: no — The vendor's own marketplace listing classes delivery as SaaS and states the software is not deployed in the buyer's AWS account; no on-premise, VPC or single-tenant option is published on any tier.](https://aws.amazon.com/marketplace/pp/prodview-l2djyrnxnfffq) - [Free tier: no — The cheapest entitlement the vendor publishes is a twelve-month contract with a $25,000 floor; mavenagi.com routes /pricing to the demo form and app.mavenagi.com offers sign-in with no self-serve registration.](https://aws.amazon.com/marketplace/pp/prodview-l2djyrnxnfffq) [View Maven AGI](https://theagentsindex.com/maven-agi) ### 2. Zendesk AI agents Customer-service AI agents for messaging, email and voice, billed per automated resolution. **Research coverage:** 35/35 criteria **Where it improves on IrisAgent:** - [Claude: partial — Claude is not what powers the agent; it is reachable as an external action in action flows using your own Anthropic key.](https://support.zendesk.com/hc/en-us/articles/10630133525018-Using-Claude-actions-in-action-flows) - [Seat model: yes — Priced per agent seat per month with no published seat floor; the resolution allowance is also derived per seat (5 ARs/agent/month on Team and Suite Team, 10 on Professional).](https://www.zendesk.com/pricing/) - [Single sign-on: yes — SAML, OIDC and JWT are supported, and the plan comparison shows SSO among user authentication options on every self-serve plan.](https://www.zendesk.com/trust-center/) **Trade-offs against IrisAgent:** - [Open models: no — Every generative path the vendor enumerates is a managed hosted API; no open-weight or customer-supplied model is offered.](https://www.zendesk.com/trust-center/) - [Model choice: no — Zendesk selects the models: generative LLMs plus its own proprietary intent models. No model picker is documented.](https://www.zendesk.com/service/ai/ai-agents/) - [Self-hosted: no — Hosted SaaS on AWS; the only locality control is choosing a Zendesk region.](https://www.zendesk.com/trust-center/) [View Zendesk AI agents](https://theagentsindex.com/zendesk-ai-agents) ### 3. Ada Enterprise AI customer-service agents that resolve inquiries across voice, chat, email and social channels. **Research coverage:** 35/35 criteria **Where it improves on IrisAgent:** - [Claude: yes — Anthropic is named as a model provider for all services, and Ada's docs also cover managing the agent from Claude Desktop and Claude Code; the specific Claude model is not published.](https://www.ada.cx/platform/trust/) - [Audit log: yes — Configuration changes are logged with actor, entity, activity and interface, including changes made over the API or MCP, filterable and exportable to CSV up to 10,000 rows.](https://docs.ada.cx/docs/other/audit-log) - [Single sign-on: yes — SAML 2.0 against any compliant IdP through Ada's Okta service provider; no OIDC is documented, IdP-initiated login is unsupported, and setup needs an Ada representative.](https://docs.ada.cx/docs/other/team-access/sso) **Trade-offs against IrisAgent:** - [Multi-agent: no — One agent per instance on a single reasoning layer; additional Ada Agents are separate instances added as separate connections, and escalation goes to a human.](https://www.ada.cx/platform/) - [Open models: partial — Ada internally hosts open-source LLMs for contextual understanding only; reply generation runs on the commercial providers and the customer selects neither.](https://security.ada.cx/) - [Model choice: no — Ada chooses and rotates the models itself behind one Reasoning Engine, benchmarking candidates before selection; no documented control lets a buyer pin or swap the model.](https://www.ada.cx/platform/trust/) [View Ada](https://theagentsindex.com/ada) ### 4. Crescendo AI-native CX platform whose agents resolve customer contacts across voice, chat, email and messaging. **Research coverage:** 29/35 criteria **Where it improves on IrisAgent:** - [Done-for-you service: yes — Crescendo deploys its own CX team alongside the software and takes escalations through a network of human specialists.](https://www.crescendo.ai/) - [Multi-agent: yes — Named specialised agents (Concierge, Quality, Applied Insights, Optimization, Integration, Simulation, Knowledge, Workforce) run one operation together.](https://www.crescendo.ai/news/crescendo-launches-the-ai-native-customer-experience-platform-one-system-that-runs-and-continuously-improves-the-entire-cx-operation) - [Audit log: yes — An access log records who accessed what and when, plus real-time activity tracking; the platform is described as audit-logged.](https://www.crescendo.ai/solutions/features) **Trade-offs against IrisAgent:** - [Model choice: no — Crescendo picks the model per task; no customer-facing model selection is published.](https://www.crescendo.ai/news/crescendo-adds-gpt-5) - [Free tier: no — Every published entry point is a booked demo; no self-serve signup, trial or free tier is offered.](https://www.crescendo.ai/total-outcome-guarantee) [View Crescendo](https://theagentsindex.com/crescendo) ### 5. Botsify White-label platform for prompt-built chat and voice agents, plus a done-for-you agent build service. **Research coverage:** 30/35 criteria **Where it improves on IrisAgent:** - [Done-for-you service: yes — A separate Done-for-You line has Botsify staff scope, build, deploy and iterate the agent for you; the white-label platform is the self-serve half.](https://botsify.com/done-for-you-ai-agents) - [Model choice: yes — You pick the LLM platform and the model yourself in LLM Settings, including custom and third-party models.](https://botsify.zendesk.com/hc/en-us/articles/52954207809305-How-to-Configure-LLM-Settings-in-Botsify) - [Bring your own key: yes — Bring your own LLM key in LLM Settings; the plan rows make BYOK the route to uncapped usage, and resellers can mark up the token cost they pay.](https://botsify.zendesk.com/hc/en-us/articles/52954207809305-How-to-Configure-LLM-Settings-in-Botsify) **Trade-offs against IrisAgent:** - [Self-hosted: no — Hosting and infrastructure are Botsify's; the vendor markets 'no DevOps needed' and reserves self-hosting to the rivals it compares against.](https://botsify.com/alternatives/botsify-vs-crewai) - [Opt out of training: no — The terms grant an irrevocable licence to analyse submissions and to own aggregated and anonymised derivatives; no opt-out is offered.](https://botsify.com/terms-and-conditions) - [Certifications: partial — GDPR compliance is claimed and AES-256 encryption at rest is asserted; no SOC 2 or ISO 27001 certification is published anywhere.](https://botsify.com/privacy-policy) [View Botsify](https://theagentsindex.com/botsify) ### 6. Cresta Contact-centre AI platform for voice and digital AI agents, real-time human agent assist, and conversation analytics. **Research coverage:** 32/35 criteria **Where it improves on IrisAgent:** - [Multi-agent: yes — Agents are built as a decentralised network of specialised subAgents, each with its own prompts, knowledge, tools and guardrails.](https://cresta.com/ai-agent-build) - [Claude: partial — Anthropic is a named sub-processor providing natural-language APIs to Cresta; the vendor does not publish which models serve which task or let a buyer request Claude.](https://trust.cresta.com/) - [Seat model: partial — Agent count is one of the quoted pricing dimensions, but no per-seat rate, floor or ceiling is published; the vendor's stated fit is 100+ care agents or 50+ sales agents.](https://cresta.com/llm-info) **Trade-offs against IrisAgent:** - [GPT: partial — OpenAI and Microsoft are named sub-processors supplying natural-language APIs; model choice per task is not published.](https://trust.cresta.com/?itemUid=e3fae2ca-94a9-416b-b577-5c90e382df57) - [Self-hosted: no — Cresta is delivered only as a hosted subscription; its own security addendum describes third-party cloud hosting, and AWS and Google Cloud are its listed hosting sub-processors. No customer-hosted or VPC option is published.](https://cdn.prod.website-files.com/67fe49bf21b9f9d5b910d3c9/6a4c05733607bb1c43d02b00_Enterprise%20Security%20Addendum.pdf) - [Free tier: no — No self-serve entry at all; every route to the product is a demo request, and evaluation runs as a contracted pilot.](https://cresta.com/llm-info) [View Cresta](https://theagentsindex.com/cresta) ## Method Unknown data is never treated as a benefit or a trade-off. Featured placement is labelled but cannot alter recommendation order.