Platform extensibility
Which AI agent platforms let you choose or bring your own model?
This is the largest documentation gap in the index. Of 984 vendors, only 198 document full model flexibility: working across several foundation models, routing tasks between models, or letting the buyer bring their own model and their own provider keys. 196 document partial coverage and 590, three in five, document none at all.
Every vendor in the index is assessed against the same 14 point taxonomy from public documentation, and no vendor pays for placement. Counts on this page were measured across all 984 public vendors on August 10, 2026.
How the 984 vendors split
No public evidence means the reviewed sources did not document the capability. On this index that is a statement about the evidence, not proof that the capability is absent. See methodology.
What counts as full coverage
Full coverage means model choice is a documented product surface, whether that is a provider list, a routing policy that sends tasks between models, or bring your own model and bring your own key (BYOK). Partial usually means one alternative provider or a roadmap statement. Silence is the common case, and on this axis silence usually means the model is an implementation detail the vendor does not intend to expose.
How to read these numbers
Read this axis as a question about lock in rather than about capability. Multi agent platforms at 58 percent, agent builders at 49 percent and coding at 47 percent treat model choice as a feature because their buyers ask about cost and about the next release. Healthcare at 5 percent and GTM at 7 percent are the extremes, and the reason is that those products are sold as outcomes: nobody buys a prior authorization agent and then asks which model wrote the letter. That is a defensible product decision, but it does mean the vendor's model economics, and any future model change, are entirely theirs to control.
Leading platform for model flexibility & routing in each use case
Picked mechanically: the highest total coverage vendor in each lane that documents full evidence on this axis, one vendor per row. Scores are out of 14.
-
1. UiPath, for enterprise operations agents
13.5 / 14Full enterprise operations agents ranking · Compare the whole lane on all 14 axes
-
2. Automation Anywhere, for multi-agent platforms
13 / 14Full multi-agent platforms ranking · Compare the whole lane on all 14 axes
-
3. NICE CXone, for customer support agents
13 / 14Full customer support agents ranking · Compare the whole lane on all 14 axes
-
4. Salesforce, for GTM and revenue agents
13 / 14Full GTM and revenue agents ranking · Compare the whole lane on all 14 axes
-
5. Agno, for agent infrastructure platforms
12.5 / 14Full agent infrastructure platforms ranking · Compare the whole lane on all 14 axes
-
6. Boomi, for agent builders
12.5 / 14Full agent builders ranking · Compare the whole lane on all 14 axes
-
7. CrowdStrike, for security and SOC agents
12.5 / 14Full security and SOC agents ranking · Compare the whole lane on all 14 axes
-
8. Emergence AI, for browser and computer-use agents
12.5 / 14Full browser and computer-use agents ranking · Compare the whole lane on all 14 axes
-
9. Factory, for coding agents
12.5 / 14Full coding agents ranking · Compare the whole lane on all 14 axes
-
10. Dataiku, for data analyst agents
12 / 14Full data analyst agents ranking · Compare the whole lane on all 14 axes
-
11. Kubiya, for SRE and DevOps agents
12 / 14Full SRE and DevOps agents ranking · Compare the whole lane on all 14 axes
-
12. Innovaccer, for healthcare agents
11.5 / 14Full healthcare agents ranking · Compare the whole lane on all 14 axes
-
13. Cognigy, for voice agents
11 / 14Full voice agents ranking · Compare the whole lane on all 14 axes
Documented coverage by use case
Share of each lane documenting full coverage on this axis. Vendors that sit in two lanes count in both, the same rule the rankings and matrices use.
| Use case | Full coverage | Share |
|---|---|---|
| multi-agent platforms | 33 of 57 | 58% |
| agent builders | 56 of 114 | 49% |
| coding agents | 32 of 68 | 47% |
| agent infrastructure platforms | 56 of 179 | 31% |
| browser and computer-use agents | 13 of 49 | 27% |
| customer support agents | 20 of 115 | 17% |
| enterprise operations agents | 48 of 319 | 15% |
| SRE and DevOps agents | 5 of 36 | 14% |
| data analyst agents | 9 of 67 | 13% |
| voice agents | 11 of 88 | 13% |
| security and SOC agents | 8 of 92 | 9% |
| GTM and revenue agents | 10 of 144 | 7% |
| healthcare agents | 4 of 77 | 5% |
Recent verified changes from the vendors named above
Capability coverage is not a static picture. These are the most recent sourced change log entries for the platforms listed above, newest first, one per vendor. Scores on this page update as entries like these are verified.
-
Emergence AI agent capability
High impactEmergence AI released VCG, a high-performance verified coding agent specialized for Python. The agent is designed to autonomously write, verify, and execute Python code for complex enterprise workflows.
August 3, 2026 · Verified · All Emergence AI changes
-
UiPath agent capability
High impactUiPath upgraded Autopilot in Studio Desktop to function as a fully autonomous coding agent rather than a drafting tool. The agent can now plan, build, run, debug, and refactor automations directly within the Studio environment using official UiPath skills and command line interface tooling.
July 7, 2026 · Verified · All UiPath changes
-
Agno agent capability
High impactEleven Agno releases (v2.6.10 to 2.6.20) added tool-batch checkpointing and run forking, full CRUD on agent learnings, a StudioTool for dynamic agent composition, ClickHouse trace backends, custom scoped MCP tools, and five new model providers including Cloudflare AI Gateway.
July 1, 2026 · Verified · All Agno changes
-
Salesforce security / enterprise
High impactSalesforce announced that its Agentforce 360 platform has achieved Department of Defense Impact Level 5 (IL5) authorization. The platform is now embedded into Missionforce National Security to securely process highly sensitive workloads, including Controlled Unclassified Information and unclassified National Security Systems data.
August 5, 2026 · Verified · All Salesforce changes
-
NICE CXone security / enterprise
High impactNICE introduced NICE Witness, a new AI governance solution designed to create an impartial and cross-vendor record of AI activity and personnel actions. The solution captures data from the first call through dispatch and final review to ensure accountability in AI-assisted decisions.
August 3, 2026 · Verified · All NICE CXone changes
Full change log · updated weekly across the whole index
Questions buyers ask
Does a low score mean the platform is locked to one model?
It means the vendor does not document model choice as a buyer facing option. Many such platforms do swap models internally. The point is that you would not know, and you could not choose.
Why do bring your own model and bring your own key matter?
It moves inference cost and data handling onto your own provider account, which changes both the economics and the compliance conversation. It also makes the vendor's markup visible.
Is routing the same as multi model support?
Routing is stronger. Multi model support means you can pick one. Routing means the platform sends each task to an appropriate model, which is where the cost savings usually come from.
The other 13 axes
No single axis decides a shortlist. Buyers who care about this one usually check triggers & channel coverage and apis, sdks & mcp extensibility next, or open the full taxonomy to see how the 14 axes fit together.