# The agent editor in the console > How the portal/agents screen maps onto agent_config, what each editor tab writes, the validated turn-detection ranges, the draft/Deploy lifecycle, and the three test buttons. The **Agents** screen in the TeleQuick console is the editor for one row of `agent_config` per agent. The left-hand list is every `agent_config` row that belongs to the active org, read directly from the database filtered on `org_id` and ordered by `created_at`. The first row is selected automatically when the screen loads. Selecting an agent opens the editor. The editor has three view modes and, inside the default one, four tabs: | View mode | What it shows | | ---------- | -------------------------------------------------------------------- | | `config` | The four-tab form described on this page. | | `pipeline` | The pipeline / flow builder for the agent's graph. | | `console` | The live agent console. | A page-level sub-nav switches between **Agents** (the pool plus this editor) and **Voices** (the org's cloned-voice manager). Voices live here because they are an agent asset. ## The agent pool and the four editor tabs The config view is split into four panes — **Conversation**, **Models & Voice**, **Actions**, and **Advanced**. The split is presentation only. All four panes edit the *same* pending-edit object over the selected row, and one **Save** writes them together through `adminAgents.updateConfig`. Switching tabs never discards an unsaved change made on another tab. Per-agent actions in the pool: | Control | Procedure | | ---------- | ----------------------------- | | New agent | `adminAgents.createConfig` | | Save | `adminAgents.updateConfig` | | Duplicate | `adminAgents.duplicateConfig` | | Deploy / Revert to draft | `adminAgents.setStatus` | | Delete | `adminAgents.deleteConfig` | Every write goes through these org-scoped, audited BFF procedures rather than a browser database client, so an agent write is always attributed and always scoped to the org you are acting in. Creating an agent is gated by the org's entitlement limit; the New Agent control is wrapped in the limit gate and will tell you when the pool is full. ## Create an agent: name rules and templates The agent **name** is a dispatch identifier, not a display label, so the modal enforces the charset its helper copy promises: - letters, digits and dashes only, - must start with a letter or a digit, - at most 64 characters, - required. A bad name is reported when you submit, not while you type. The **template** picker pre-fills `system_prompt` and `welcome_message` only. It sets nothing else: | Template | What it seeds | | ------------------- | ---------------------------------------------------------------- | | Blank | Empty prompt and empty welcome message. | | Customer support | Answer questions, troubleshoot, guide next steps. | | Receptionist | Greet callers, understand intent, route or take messages. | | 1-to-1 training | Guided practice, roleplay and coaching. | | Data collection | Conversationally fill out a structured questionnaire. | New agents are created with coherent cascaded defaults: `pipeline_mode` is `cascaded` and `turn_detection_type` is `silero`. ## What each tab covers | Tab | Sections in that pane | | --------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- | | Conversation | `name`, `description`, `system_prompt`, `welcome_message`. | | Models & Voice | `pipeline_mode`; the cascaded provider/model pairs (`llm_provider`/`llm_model`, `asr_provider`/`asr_model`, `tts_provider`/`tts_voice`) or the realtime model and voice; the voice picker; per-agent provider credential overrides. | | Actions | The agent's tool definitions and its telephony bindings. | | Advanced | `temperature`, `conversation_memory_messages`, turn detection, `noise_cancellation_model`, `background_audio_url`. | Per-agent credentials are columns on the same row — `openai_api_key`, `anthropic_api_key`, `gemini_api_key`, `elevenlabs_api_key`, `deepgram_api_key` and `ollama_endpoint`. They override whatever the org would otherwise use for that provider. `ollama_endpoint` must be an `http` or `https` URL. `background_audio_url` accepts `s3`, `file`, `https` or `http`. ## Cascaded and realtime pipelines `pipeline_mode` decides which half of the Models & Voice tab is meaningful. - **`cascaded`** runs three separate stages, so it reads the ASR, LLM and TTS provider/model selections and the TTS voice. - **`realtime`** runs a single speech-to-speech model, so it reads the realtime model and realtime voice lists instead. The two modes pair with different turn detectors. `cascaded` is the right shape for any non-realtime model and defaults to `silero`; realtime sessions use the provider's own `server_vad`. Changing `pipeline_mode` in the editor automatically flips `turn_detection_type` so the pair stays coherent — if you want a different detector, set it after changing the mode. ## Turn detection fields and their accepted ranges These ranges are enforced in the browser on Save because HTML `min`/`max` on a number input is bypassed by typing into it. Leaving a numeric field **empty** is valid: the server's default applies. | UI label | Column | Accepted values | | -------------- | ----------------------------- | ------------------------------------- | | Detector | `turn_detection_type` | `silero`, `server_vad`, `none` | | Threshold | `turn_detection_threshold` | 0 to 1 | | Prefix padding | `turn_detection_prefix_ms` | integer, 0 to 2000 | | Silence duration | `turn_detection_silence_ms` | integer, 0 to 5000 | | Hold time | `turn_detection_config.params.eou_hold_ms` | integer, 0 to 10000 | Semantic end-of-turn lives in the JSONB `turn_detection_config` column, not in its own columns. The editor exposes three of its `params` keys: `eou_enabled`, `eou_threshold` and `eou_hold_ms`. ## Preserving turn_detection_config `turn_detection_config` is a strict JSONB block with three top-level