Skip to content
Talk to Us

Blocks.ai publishes this comparison and sells in this market. Every claim about another product links to a public source.

IBM watsonx Orchestrate vs Kong AI Gateway

IBM watsonx Orchestrate

Agent management platform to build, deploy, orchestrate, and govern AI agents

Kong AI Gateway

Gateway that governs LLM, MCP, and agent-to-agent traffic

Short answer

IBM watsonx Orchestrate is a platform to build, deploy, and govern AI agents; Kong AI Gateway is a gateway for LLM, MCP, and agent-to-agent (A2A) traffic.⁠Source 1, Source 2, Source 3, Source 4, Source 5, Source 6 Orchestrate runs agents built in it and can add outside agents by URL; Kong proxies calls to agents registered as upstream URLs.⁠Source 3, Source 7, Source 8, Source 9

By Blocks.ai teamLast checked

Where each one sits

Six layers of running AI agents at a company, and what each product’s own public sources say it covers.

These aren’t the same kind of product

Where they overlap
Both can apply policy to A2A agents and model traffic: IBM through controls, on SaaS outside AWS GovCloud, and Kong through AI Policies.⁠Source 4, Source 5, Source 6
Where they differ
Teams build agents in Orchestrate in Python or, IBM says, visually, and run them there.⁠Source 1, Source 2, Source 3 Kong proxies to agents registered as upstream URLs; building agents in it isn’t publicly documented.⁠Source 9
Running both
IBM’s docs say Orchestrate exposes its agents through A2A endpoints, and Kong’s say AI Gateway can proxy an upstream A2A agent.⁠Source 9, Source 10 Neither vendor publicly documents using the two together.
Public sources · checked 2 October 2026
  • Offered
  • Preview
  • Not publicly documented

IBM watsonx Orchestrate

  • Build agents: OfferedVisual builder and ADK⁠Source 2
  • Host and run agents: OfferedAgents run on watsonx Orchestrate⁠Source 3
  • Identity and access: PreviewAgent identity⁠Source 11
  • Registry and governance: OfferedAgentic Control Plane⁠Source 12
  • Traffic between agents, tools, and models: OfferedA2A calls to agent endpoints⁠Source 13
  • Agents across organizations: OfferedPartner A2A agents in catalog⁠Source 13

Kong AI Gateway

  • Build agents: Not publicly documented
  • Host and run agents: Not publicly documented
  • Identity and access: OfferedPer-agent allow or deny lists⁠Source 9
  • Registry and governance: PreviewKonnect Catalog agents⁠Source 14
  • Traffic between agents, tools, and models: OfferedGateway for LLM, MCP, A2A⁠Source 5
  • Agents across organizations: Not publicly documented

At a glance

TopicIBM watsonx OrchestrateKong AI Gateway
What it isIBM calls it an agent management platform to build, deploy, orchestrate, manage, and govern AI agents, with a visual builder.⁠Source 1, Source 2A gateway for LLM, MCP, and A2A traffic, with shared authentication, observability, and policy features.⁠Source 5, Source 6
Where governed agents runAgents built with its Agent Development Kit run on watsonx Orchestrate.⁠Source 3 Agents on third-party platforms are reached at a running, accessible endpoint.⁠Source 8At their own upstream URLs, which the gateway proxies to.⁠Source 9 Agents can speak A2A or plain HTTP.⁠Source 9
Who can call an agentOutside systems call its A2A endpoints with a bearer token or client JWT.⁠Source 10 People get user, builder, or administrator roles.⁠Source 15Callers can be required to authenticate by API key or OpenID Connect, then checked against a per-agent allow or deny list.⁠Source 9
Pricing modelMonthly plans sized by active users and messages: Essentials from $530 and Standard from $6,360 USD; Premium on request.⁠Source 16 A 30-day free trial.⁠Source 16AI Management Plus from $25 a month plus usage; control planes are $200 a month hybrid, $500 Dedicated Cloud, or $25 serverless.⁠Source 17 A 30-day free trial.⁠Source 17 Enterprise is custom, billed annually.⁠Source 17
MaturityIBM said the unified release of watsonx Orchestrate was generally available in January 2024; the Agentic Control Plane followed in June 2026.⁠Source 18, Source 19 IBM’s AI Gateway is in preview, and agent identity in private preview.⁠Source 20, Source 21Version 2.0 announced generally available on 1 September 2026.⁠Source 22 The agent inventory in Konnect Catalog is in beta.⁠Source 14

What each one is

IBM watsonx Orchestrate

IBM describes watsonx Orchestrate as an agent management platform to build, deploy, orchestrate, manage, and govern AI agents.⁠Source 1 IBM says its Agentic Control Plane, introduced on AWS and IBM Cloud in June 2026, is a centralized layer to observe and govern agents.⁠Source 12, Source 19

Kong AI Gateway

Kong AI Gateway is a gateway for LLM, MCP, and agent-to-agent (A2A) traffic, all through one data plane with shared authentication, observability, and policy.⁠Source 5, Source 6 In 2.x, an agent is added as an AI Agent entity, exposed at a gateway endpoint.⁠Source 9, Source 23

The differences that matter

  1. Where agents run

    IBM watsonx Orchestrate

    Agents built with the Agent Development Kit run on watsonx Orchestrate; agents on third-party platforms are added by the URL of a running, accessible endpoint.⁠Source 3, Source 8

    Kong AI Gateway

    Kong proxies calls to each agent at its own URL; in 2.x, data plane nodes you run forward the allowed traffic.⁠Source 6, Source 9

    Behind a firewall, you allowlist IBM’s outbound IPs or, on IBM Cloud, set up a Satellite TLS tunnel; Kong’s control plane is never in the path of user data traffic.⁠Source 6, Source 24, Source 25

  2. Keeping track of agents

    IBM watsonx Orchestrate

    IBM says its catalog holds partner agents and its AI Gateway (preview) can find agents in AgentCore, Gemini Enterprise Agent Platform, or Azure AI Foundry.⁠Source 20, Source 26, Source 27, Source 28, Source 29

    Kong AI Gateway

    In 2.x, each AI Agent entity is scoped to one gateway instance; Konnect Catalog’s agent inventory is in beta, not for production use.⁠Source 6, Source 9, Source 14

    Outside systems can list a tenant’s live agents through IBM’s A2A discovery endpoint; Kong rewrites agent-card URLs so A2A clients discover the gateway instead of the agent.⁠Source 9, Source 10

  3. Identity and access

    IBM watsonx Orchestrate

    Existing authentication uses an impersonation model; agent identity, so agents act for users under their own verifiable identities, is in private preview.⁠Source 11, Source 21

    Kong AI Gateway

    Kong can identify the caller, by API key or OAuth, and check it against a per-agent allow or deny list before traffic reaches the agent.⁠Source 9, Source 30

    For people signing in to each platform, both support SSO over OIDC or SAML; Kong offers Konnect SSO only on its Enterprise plan.⁠Source 17, Source 31, Source 32

For security teams

What a security review asks, answered from each vendor’s public documentation.

TopicIBM watsonx OrchestrateKong AI Gateway
Network exposureExternal agents need accessible endpoints.⁠Source 8 On IBM Cloud: a Satellite TLS tunnel, private endpoints, and network controls.⁠Source 4, Source 25, Source 33, Source 34In 2.x, data plane nodes you run proxy to agents’ upstream URLs and authenticate to the control plane over mTLS.⁠Source 6, Source 9
IdentityPlatform SSO over OIDC or SAML.⁠Source 31 Agent identity through IBM Verify or Microsoft Entra is in private preview.⁠Source 21Can require an API key, or OpenID Connect through Okta, Azure AD, Google, or another OIDC provider, before routing.⁠Source 9, Source 35
Access changes and revocationOn IBM Cloud, undeploying a released agent version is logged.⁠Source 36 Agents removed from IBM’s AI Gateway directory (preview) can’t collaborate.⁠Source 37Each agent has an enabled switch; Request Termination or deny lists block callers.⁠Source 9, Source 38, Source 39 Nodes keep their last config without Konnect.⁠Source 6
Audit trailAudit events can be routed where you choose on IBM Cloud, or sent to your S3 and CloudWatch on AWS.⁠Source 40, Source 41A2A audit logs: task IDs, method calls, latencies, errors.⁠Source 42 Konnect audit logs (Enterprise): webhook delivery, kept 7 days in Konnect.⁠Source 17, Source 43
ComplianceIBM says watsonx Orchestrate is FedRAMP authorized on AWS GovCloud (US) and the company holds ISO/IEC 27001:2022 certification.⁠Source 44, Source 452.2+ FIPS mode: FIPS 140-3 algorithms only, not NIST-validated.⁠Source 46 Kong Inc. lists ISO 27001 and SOC 2 (report under NDA).⁠Source 47

Full comparison

18 criteria in five groups. Every cell links to its source, or says no public source answers it.

IBM watsonx Orchestrate and Kong AI Gateway compared on 18 criteria
IBM watsonx OrchestrateKong AI Gateway
What it is
What it is and who it’s forIBM describes it as an agent management platform to build, deploy, orchestrate, manage, and govern agents, for IT, security, and AI leaders.⁠Source 1A gateway that governs LLM, MCP, and A2A traffic.⁠Source 5, Source 6 All three run through one data plane, with shared authentication, observability, and policy features.⁠Source 6
MaturityIBM said its unified release was GA in January 2024; the Agentic Control Plane followed in June 2026.⁠Source 18, Source 19 IBM’s AI Gateway and some dashboards are in preview.⁠Source 20, Source 48Version 2.0 announced generally available on 1 September 2026; 2.2.0 released 30 September 2026.⁠Source 22, Source 49 Konnect Catalog’s agent inventory is in beta.⁠Source 14
Control
Agent registry and discoveryIBM says its searchable catalog holds prebuilt and custom agents and tools.⁠Source 26 IBM’s AI Gateway directory (preview) holds agents imported from other platforms.⁠Source 20, Source 37In 2.x, each AI Agent entity, A2A or plain HTTP, is scoped to one gateway instance.⁠Source 6, Source 9 Konnect Catalog’s agent inventory is in beta.⁠Source 14
Identity and access controlPlatform SSO over OIDC or SAML, with user, builder, and admin roles.⁠Source 15, Source 31 Existing authentication uses impersonation; agent identity is in private preview.⁠Source 11, Source 21Can require an API key or an OpenID Connect login, through Okta, Azure AD, or another provider, then check a per-agent allow or deny list.⁠Source 9, Source 35
Ownership, policy, and revocationOn SaaS outside AWS GovCloud, controls can block unsafe content, protect data, govern model traffic, and limit network access.⁠Source 4 Agent owners: private preview.⁠Source 21Agent policies include input validation, logging, and rate limits.⁠Source 9 Kong’s AI PII Sanitizer scrubs requests to AI models: a Plus add-on, included on Enterprise.⁠Source 17, Source 50
Audit log and observabilityTraces give a high-level view of a request; registered outside agents can export theirs.⁠Source 51, Source 52 Audit events can go to IBM Cloud targets, or S3 and CloudWatch on AWS.⁠Source 40, Source 41A2A audit logs record task IDs, method calls, latencies, and errors.⁠Source 42 A2A telemetry can go to Konnect and OpenTelemetry.⁠Source 9 Bodies go to Konnect only if you opt in.⁠Source 6
Connection
How agents connectAgents hosted elsewhere need an accessible endpoint.⁠Source 8 IBM publishes outbound IPs to allowlist; on IBM Cloud, a Satellite TLS tunnel and private endpoints.⁠Source 24, Source 25, Source 33Each agent is an upstream URL the gateway proxies to.⁠Source 9 In 2.x, data plane nodes you run forward allowed traffic and stay connected to Konnect.⁠Source 6
Agents across organizationsExcept on premises, partner A2A agents from IBM’s catalog can be collaborators.⁠Source 13 A connection sets how Orchestrate authenticates to an external A2A agent.⁠Source 53Not publicly documented (checked 2 October 2026)
Protocol supportCalls external A2A agents over JSON-RPC 2.0 only, and exposes its own through A2A endpoints.⁠Source 10, Source 54 Imports MCP server tools; OAuth 2.1 and DCR aren’t supported.⁠Source 55A2A over JSON-RPC and REST bindings, with agent cards rewritten to the gateway.⁠Source 9 MCP: proxies or combines servers; four revisions, the newest from 2.1.⁠Source 6, Source 56
Frameworks, models, and clouds supportedIBM says it supports native, Langflow, LangGraph, and A2A agents.⁠Source 57 Agents with an OpenAI-style chat completions endpoint and Copilot Studio agents can be added.⁠Source 54Proxies A2A and plain HTTP agents, including ones on AgentCore Runtime via SigV4.⁠Source 9 Kong says it doesn’t change how agents are built.⁠Source 58
Operations
Deployment options and data residencyManaged SaaS in AWS and IBM Cloud regions, or on premises on IBM Cloud Pak for Data or IBM Software Hub.⁠Source 24, Source 59 Agentic Control Plane: not in AWS GovCloud (US).⁠Source 482.x: a Konnect-managed control plane in a region you choose, data plane nodes you run.⁠Source 6, Source 60 Kong also sells Kong-managed Dedicated Cloud and serverless gateways.⁠Source 17, Source 61, Source 62
Compliance attestationsIBM says the product is FedRAMP authorized on AWS GovCloud (US), and the company holds ISO/IEC 27001:2022 certification.⁠Source 44, Source 45 Premium lists a HIPAA-ready option.⁠Source 16From 2.2, FIPS mode uses only FIPS 140-3 approved algorithms; not submitted for NIST validation.⁠Source 46 Kong lists ISO 27001, SOC 2, and PCI DSS for Kong Inc.⁠Source 47
Support and SLAOn AWS, IBM states a 99.9% availability SLA.⁠Source 63 On IBM Cloud, it points to the base IBM Cloud Service Description.⁠Source 64 Support cases can be opened.⁠Source 65Konnect targets 99.9% availability; Dedicated Cloud Gateways list a 99.99% SLA, serverless gateways none.⁠Source 17 Enterprise support SLAs: 30 min to 2 hours.⁠Source 17
Time and effort to get runningIBM’s administrator guide covers environment setup and user access.⁠Source 66 Platform SSO is set up with IBM.⁠Source 31 The Agentic Control Plane needs the Admin or Builder role.⁠Source 48A quickstart script creates a Konnect control plane and a local Docker data plane; you then add each agent as an AI Agent entity and attach policies.⁠Source 23, Source 67
Pricing model and public pricesEssentials from $530 and Standard from $6,360 USD a month, sized by active users and messages; Premium on request.⁠Source 16 A 30-day free trial.⁠Source 16Plus: from $25 a month plus usage; per control plane, $200 hybrid, $500 Dedicated Cloud, $25 serverless.⁠Source 17 Enterprise: custom, billed annually.⁠Source 17
Building
Agent building toolsIBM says agents can be built in a drag-and-drop visual builder, and Langflow workflows deployed as tools.⁠Source 2 The Agent Development Kit is a Python library and CLI.⁠Source 3Kong says it can generate MCP tools and servers from Kong-managed APIs.⁠Source 5 Tools for building agents in Kong AI Gateway are not publicly documented.
Model accessIBM-hosted and third-party models, varying by cloud and region.⁠Source 68 Most regions default to GPT-OSS 120B via Groq.⁠Source 68 Other providers’ models can be registered.⁠Source 69One API to providers including OpenAI, Anthropic, Amazon Bedrock, Gemini, Azure AI, Mistral, and Ollama, with credentials you supply.⁠Source 6, Source 67, Source 70
Integrations and ecosystemIBM says its catalog shows how IBM and partner agents connect to systems such as Microsoft 365 and SAP.⁠Source 26 Partners can integrate through IBM Agent Connect.⁠Source 71A Policies Hub of policies and integrations.⁠Source 38 AI Vault works with AWS, GCP, Azure, and HashiCorp Vault secrets backends.⁠Source 6

Which to choose

Choose IBM watsonx Orchestrate if

  • You want to build agents as well as govern them, using the Agent Development Kit or, IBM says, a visual builder.⁠Source 1, Source 2, Source 3
  • You need an on-premises install (IBM Cloud Pak for Data or Software Hub), where some agent controls aren’t available, or SaaS.⁠Source 24, Source 59, Source 72
  • You want a catalog that, IBM says, shows how each IBM and partner agent connects to systems like Microsoft 365 and SAP.⁠Source 26
  • You want a central place, outside AWS GovCloud, to monitor and manage agents’ operational health, adoption, and quality.⁠Source 48

Choose Kong AI Gateway if

  • You want one gateway for LLM, MCP, and A2A traffic, with shared authentication, observability, and policy features.⁠Source 5, Source 6
  • You’d rather run the data plane yourself: Kong’s control plane is never in the data path; nodes keep proxying if it’s unreachable.⁠Source 6
  • You want to turn existing REST APIs into MCP tools, or combine tools from several MCP servers into one endpoint.⁠Source 6
  • You want one API to model providers such as OpenAI, Anthropic, Gemini, and Mistral, switching or combining them without rewriting integrations.⁠Source 67, Source 70

Questions buyers ask

Is IBM’s AI Gateway the same as Kong AI Gateway?

IBM uses the name for a preview feature of watsonx Orchestrate that can discover agents on other platforms, keep a directory of imported ones, and connect remote MCP servers.⁠Source 20, Source 37 Kong AI Gateway is Kong’s own gateway for LLM, MCP, and A2A traffic.⁠Source 5, Source 6

Do they support MCP and A2A?

Orchestrate calls external A2A agents, exposes its own through A2A endpoints, and imports tools from MCP servers, though not with OAuth 2.1.⁠Source 10, Source 54, Source 55 Kong AI Gateway detects A2A over JSON-RPC and REST bindings, proxies MCP servers or combines their tools, and accepts four MCP revisions.⁠Source 6, Source 9, Source 56

Can either one reach agents at other organizations?

Except on premises, watsonx Orchestrate can add partner A2A agents from IBM’s catalog as collaborators.⁠Source 13 Kong AI Gateway proxies to agents registered as upstream URLs.⁠Source 9 For both, how another organization keeps control of its own agents, beyond issuing credentials, is not publicly documented.

Can either one be self-hosted?

IBM watsonx Orchestrate can be installed on premises, on IBM Cloud Pak for Data or IBM Software Hub.⁠Source 24, Source 59 Fully self-hosted Kong AI gateways are part of Kong’s separate Gateway Enterprise offering; the 2.x AI entities run hybrid, with a Konnect-managed control plane.⁠Source 6, Source 17

How we compare

Read the full method

Every claim on this page links to a public source. Where none answers a question, the page says so.

We re-check every fact at least every 90 days. This page was last checked .

Something wrong or out of date? Tell us and we’ll correct it.

Sources

79 public sources, each with the date we checked it. Every one opens in a new tab.

  1. Source 1: IBM watsonx Orchestrate IBM · checked Back:abcdef

  2. Source 2: AI Agent Builder | IBM watsonx Orchestrate IBM · checked Back:abcdef

  3. Source 3: Welcome to IBM watsonx Orchestrate Agent Development Kit IBM · checked Back:abcdefgh

  4. Source 4: Protecting assets with controls IBM · checked Back:abcd

  5. Source 5: Kong AI Gateway product page Kong · checked Back:abcdefghi

  6. Source 6: AI Gateway architecture - Kong Docs Kong · checked Back:abcdefghijklmnopqrstuvwx

  7. Source 7: Overview - Agents (watsonx Orchestrate ADK docs) IBM · checked Back to text

  8. Source 8: Adding agents from third-party platforms IBM · checked Back:abcde

  9. Source 9: AI Agents - Kong AI Gateway docs Kong · checked Back:abcdefghijklmnopqrstuvwx

  10. Source 10: Agent-to-Agent (A2A) Protocol endpoints IBM · checked Back:abcde

  11. Source 11: Agent identity overview IBM · checked Back:abc

  12. Source 12: AI Agent Control Plane | IBM watsonx Orchestrate IBM · checked Back:ab

  13. Source 13: Partner A2A (Agent2Agent) agents IBM · checked Back:abcd

  14. Source 14: Agents in Catalog - Kong Docs Kong · checked Back:abcde

  15. Source 15: Roles on IBM watsonx Orchestrate IBM · checked Back:ab

  16. Source 16: IBM watsonx Orchestrate Pricing IBM · checked Back:abcde

  17. Source 17: Kong Pricing & Plans Kong · checked Back:abcdefghijkl

  18. Source 18: The AI Assistant for everyone: watsonx Orchestrate combines generative AI and automation to boost productivity | IBM IBM · checked Back:ab

  19. Source 19: Agentic Control Plane in IBM watsonx Orchestrate: One place to control every AI agent IBM · checked Back:abc

  20. Source 20: Governing assets with AI Gateway IBM · checked Back:abcde

  21. Source 21: Prerequisites for configuring agent identity IBM · checked Back:abcde

  22. Source 22: Kong AI Gateway 2.0 Is Now GA - And It's Already Moving Faster Kong · checked Back:ab

  23. Source 23: Route A2A agent traffic through AI Gateway - Kong Docs Kong · checked Back:ab

  24. Source 24: Regional availability and outbound IP addresses IBM · checked Back:abcde

  25. Source 25: Configuring TLS tunnel IBM · checked Back:abc

  26. Source 26: IBM watsonx Orchestrate Agent Catalog IBM · checked Back:abcd

  27. Source 27: Connecting and configuring Amazon Bedrock IBM · checked Back to text

  28. Source 28: Connecting and configuring Gemini Enterprise Agent Platform IBM · checked Back to text

  29. Source 29: Connecting and configuring Microsoft Azure AI Foundry IBM · checked Back to text

  30. Source 30: AI Consumers - Kong AI Gateway docs Kong · checked Back to text

  31. Source 31: Configuring SSO for platform access IBM · checked Back:abcd

  32. Source 32: Konnect SSO - Kong Docs Kong · checked Back to text

  33. Source 33: Using private network endpoints IBM · checked Back:ab

  34. Source 34: Configuring network controls IBM · checked Back to text

  35. Source 35: AI Auth Strategies - Kong AI Gateway docs Kong · checked Back:ab

  36. Source 36: List of events for activity tracking IBM · checked Back to text

  37. Source 37: Managing the agent directory IBM · checked Back:abc

  38. Source 38: Kong AI Gateway Policies - Kong Docs Kong · checked Back:ab

  39. Source 39: Request Termination - Configuration Reference - Policy | Kong Docs Kong · checked Back to text

  40. Source 40: Activity tracking events on IBM Cloud IBM · checked Back:ab

  41. Source 41: Enabling external logging for AWS IBM · checked Back:ab

  42. Source 42: Route A2A traffic through AI Gateway - Kong Docs Kong · checked Back:ab

  43. Source 43: Konnect and Dev Portal audit logs - Kong Docs Kong · checked Back to text

  44. Source 44: IBM Expands FedRAMP Portfolio with Authorization of 11 Software Solutions, Including watsonx IBM · checked Back:ab

  45. Source 45: ISO 27001 - IBM Corporation Certificate (Bureau Veritas, ISO/IEC 27001:2022) IBM · checked Back:ab

  46. Source 46: FIPS 140-3 compliance in AI Gateway - Kong Docs Kong · checked Back:ab

  47. Source 47: Trust Center - Kong Inc. Kong · checked Back:ab

  48. Source 48: Agentic Control Plane IBM · checked Back:abcd

  49. Source 49: Kong AI Gateway changelog - Kong Docs Kong · checked Back to text

  50. Source 50: AI PII Sanitizer - Policy | Kong Docs Kong · checked Back to text

  51. Source 51: Overview - Traces (watsonx Orchestrate ADK docs) IBM · checked Back to text

  52. Source 52: Exporting observability traces with OpenTelemetry (watsonx Orchestrate ADK docs) IBM · checked Back to text

  53. Source 53: Adding an agent-to-agent connection IBM · checked Back to text

  54. Source 54: Connect to external agents (watsonx Orchestrate ADK docs) IBM · checked Back:abc

  55. Source 55: MCP servers IBM · checked Back:ab

  56. Source 56: MCP version support - Kong AI Gateway docs Kong · checked Back:ab

  57. Source 57: Manage all your AI agents in one place with watsonx Orchestrate IBM · checked Back to text

  58. Source 58: The Agent Gateway for Secure, Observable Agent-to-Agent Communication (Kong) Kong · checked Back to text

  59. Source 59: Installing on IBM watsonx Orchestrate On-premises IBM · checked Back:abc

  60. Source 60: Geographic regions - Kong Docs Kong · checked Back to text

  61. Source 61: Dedicated Cloud Gateways - Kong Docs Kong · checked Back to text

  62. Source 62: Serverless Gateways - Kong Docs Kong · checked Back to text

  63. Source 63: High availability, business continuity, backups and disaster recovery on AWS IBM · checked Back to text

  64. Source 64: Licenses and entitlements for watsonx Orchestrate on IBM Cloud IBM · checked Back to text

  65. Source 65: Getting help and support IBM · checked Back to text

  66. Source 66: Getting started as an administrator IBM · checked Back to text

  67. Source 67: Kong AI Gateway | Kong Docs Kong · checked Back:abc

  68. Source 68: Available AI models IBM · checked Back:ab

  69. Source 69: Choosing your LLM (watsonx Orchestrate ADK docs) IBM · checked Back to text

  70. Source 70: AI Gateway providers - Kong Docs Kong · checked Back:ab

  71. Source 71: IBM Agent Connect (watsonx Orchestrate ADK docs) IBM · checked Back to text

  72. Source 72: Managing asset controls IBM · checked Back to text

  73. Source 73: Why Blocks? Blocks.ai · checked Back to text

  74. Source 74: What is Blocks? Blocks.ai · checked Back to text

  75. Source 75: Your company's private network Blocks.ai · checked Back to text

  76. Source 76: Network requirements Blocks.ai · checked Back to text

  77. Source 77: Solutions: Agent sprawl Blocks.ai · checked Back to text

  78. Source 78: Solutions: Partner networks Blocks.ai · checked Back to text

  79. Source 79: Pricing Blocks.ai · checked Back to text