How EmaFusion™ Works
EmaFusion™ is Ema's proprietary system of models. It routes across 40+ large language models from 9+ providers (including OpenAI GPT and o-series, Anthropic Claude, Google Gemini, Meta Llama, Mistral, Moonshot Kimi, Alibaba Qwen, DeepSeek, and enterprise-trained custom models) to deliver optimal results for every sub-task an AI Employee performs.
Architecture
When a task is created, the EmaFusion™ model recognizes the sub-task type and selects the single best model for that task's framework from its broad catalog of providers. Unlike AI tools locked to one model, EmaFusion™ dynamically picks the right model for each sub-task. If that model's response falls below a confidence threshold, it cascades to the next-best candidate. Cross-model validation across multiple models only runs in select high-stakes scenarios; routing to a single best model is the default behavior.
Routing logic
- Task analysis: EmaFusion™ examines the incoming sub-task (e.g., conversation generation, structured query, reasoning, summarization).
- Model selection: Based on benchmarked performance, cost, and latency data, EmaFusion™ ranks candidate models and picks the single best one for the sub-task.
- Execution with cascading fallback: The selected model processes the task. If its response falls below the confidence threshold for the chosen optimization mode, EmaFusion™ cascades to the next-best model in the ranked list.
- Continuous improvement: Ema regularly benchmarks and updates model performance data, so routing decisions improve over time.
Supported model families
EmaFusion™ routes across a broad set of model families. The following are the primary families available in the current release:
| Provider | Models | Typical strengths |
|---|---|---|
| OpenAI (GPT) | GPT-5, GPT-5-mini, GPT-5.2, GPT-5.4, GPT-5.4-mini, GPT-5.6-Luna, GPT-5.6-Sol, GPT-5.6-Terra, GPT-4.1, GPT-4.1-mini, GPT-4o, GPT-4o-mini, and earlier variants | General-purpose generation, structured output, tool calling |
| OpenAI (o-series) | o1, o3, o3-mini, o4-mini | Advanced reasoning, step-by-step problem solving, math and code |
| Anthropic | Claude Opus (4.1 through 5), Claude Sonnet (4.5, 4.6, and Sonnet 5), Claude Haiku (3.x and 4.5) | Reasoning, long-context tasks, safety-sensitive content |
| Gemini Pro and Gemini Flash (2.5, 3, 3.1, and 3.5 variants, including Flash-Lite) | Structured queries, multimodal tasks, translation | |
| Meta | Llama 3.1, Llama 3.3 | Cost-effective generation, open-weight flexibility |
| Mistral | Mistral Large | Multilingual tasks, code generation |
| Moonshot | Kimi K2.6, Kimi K2.7, Kimi K3, Kimi K3 Fast | Long-context understanding, agentic tasks |
| Z.ai | GLM 5.1, GLM 5.2 | Reasoning, agentic tasks, cost efficiency |
| DeepSeek | DeepSeek V4 Pro, DeepSeek V4 Flash | Reasoning, code generation, cost efficiency |
| Alibaba | Qwen | Multilingual generation, code |
| Sarvam | Sarvam-M, Sarvam 30B, Sarvam 105B | Indic-language tasks, India data residency |
| Custom (BYOM) | Your private models | Domain-specific, compliance-restricted tasks |
Benefits
| Benefit | Description |
|---|---|
| Maximize accuracy, minimize cost | Uses the right model for each sub-task, avoiding the cost of always defaulting to a single premium model for every request. |
| Continuous improvement | Ema benchmarks and updates model performance regularly. New models are integrated as they become available. |
| Future-proof | New models are added with no vendor lock-in. Your AI Employees automatically benefit from advances in the LLM ecosystem. |
| Fewer hallucinations | Outputs can be cross-checked across multiple models, reducing the likelihood of hallucinated content. |
| Privacy by design | Ema automatically obfuscates sensitive data (names, emails, phone numbers) before sending to models. |
Bring your own model (BYOM)
Instead of routing through the EmaFusion™ catalog, an AI Employee can run only on the models from your own configured LLM providers. This is useful for:
- Keeping all traffic on a specific deployment, such as your own Azure OpenAI resource.
- Models accessed through your own accounts for compliance or cost reasons.
BYOM is an AI Employee-wide choice: it applies to every agent under the AI Employee, and individual agents cannot override it. See EmaFusion™ setup for instructions on configuring BYOM and providers.
Azure model discovery
For Azure OpenAI providers, the Models table shows only the models your Azure resource actually has deployed. Ema lists the deployments on your resource using your API key and keeps the table in sync automatically: once when you add the provider, at every restart, and once a day on a rolling schedule. To reflect a deployment you just created in the Azure portal without waiting for the next automatic pass, click Sync deployed models in the Models card. The table updates to match your current deployments immediately.
If your resource cannot be listed (for example, because it answers the deployment list with 404), Ema falls back to probing each model's candidate name individually. In that case the table keeps all discovered rows and hides undeployed ones behind the Show all discovered models toggle, so you can still enable a row and type a custom deployment name.
A model you turn off stays off across restarts and automatic syncs. Ema records the deployment name on every row, which is what lets a disabled row survive a restart: the secret store carries it back, so the next sync can tell an admin's deliberate off from a row that was simply never deployed.
Example use cases
- Customer Support AI Employee: Uses GPT-5.4 for conversation, Claude for reasoning, and Gemini for structured queries.
- Finance Analyst AI Employee: Routes to an enterprise-trained proprietary model for compliance-sensitive tasks, with fallback to GPT-4o for summaries.
- Healthcare AI Employee: Uses a private BYOM model with a HIPAA-compliant API for patient data.
- Voice AI Employee: Routes speech-to-text diarization to GPT-5.4 for high-accuracy transcription, with downstream agents using EmaFusion™'s balanced routing for response generation.
Configuration hierarchy
EmaFusion™ configuration is resolved through a two-level hierarchy: a default set at the AI Employee level, and optional per-agent overrides that replace the default for a specific agent in a workflow.
- AI Employee default. Every AI Employee has a default EmaFusion™ configuration (the selected models, optimization mode, and any BYOM settings) that all agents use unless they override it.
- Agent-level inheritance and override. Agents inherit the AI Employee default and can unbind from it with the Override default configuration toggle to set an agent-specific model or optimization mode.
For step-by-step configuration of the AI Employee default, per-agent overrides, and providers, see EmaFusion™ setup.
References
What's next
- EmaFusion™ setup: choose a model-selection mode and optimization priority, override per agent, and configure providers.
- EmaFusion™ overview: what EmaFusion™ is and why it matters.