> ## Documentation Index > Fetch the complete documentation index at: https://docs.getsales.io/llms.txt > Use this file to discover all available pages before exploring further. # Update agent > Change an AI SDR by sid: state, mode, name, is_default (true makes it the team's default), the Brief, knowledge, settings, the Rules, the hosts, setup, llm_config, golden_set (the Words). Each value replaces the stored one whole: read the agent first and send it back; the compaction's copies and the voice are read-only. The Rules, the hosts and the voice have doors of their own (update_agent_rules, update_agent_hosts, update_agent_voice); per-thread autonomy is update_conversation. Contract: - MCP tool `update_agent`, registry package `mcp.unibox/agents`, mount `unibox.agent`. - Operation `update`, response envelope `update`. - Flags: dangerous: the MCP layer gates it behind a preview/commit token, and the effect cannot be undone through this API. ## OpenAPI ````yaml /api-reference/unibox/openapi.yaml patch /api/agents/{sid} openapi: 3.0.3 info: title: 'GetSales public contract: gs.service.unibox' description: >- The team inbox and the AI SDR: every LinkedIn and email thread in one place (conversations, messages, the timeline events), the manual tasks a thread spawns, the sender profiles the team speaks through with their LinkedIn account and mailboxes, and the one agent per team with its scenarios, plans and runs. GENERATED. This document is projected from the Zod MCP tool registry in `product/mcp/gs.mcp` (one tool per public endpoint, 1:1). Do not edit it by hand; edit the tool definition and regenerate with `pnpm openapi:public`. Surface: the public `/api` contract of `gs.service.unibox`, 125 operations. This is the only OpenAPI document the platform publishes. Internal (`/internal`) and health endpoints are deliberately absent: they are not part of any contract, they can change without notice, and the service source is their only description. Conventions: - Auth is a bearer JWT, optionally narrowed by the `Team-SID` header. - Every success body is an MCP envelope: `success: true` plus one typed `operation` shape (`search`, `get`, `create`, `update`, `delete`, `metrics`, `group_by`, `action`), and a `meta` block with `trace_id` for support. - Every failure is the same `McpError` envelope with a code from a fixed 16-code taxonomy, so a client maps errors once. - Lists page with `page_size` (0 to 500, default 50) plus an opaque forward `cursor`; `page_size: 0` returns counts only. - On `GET` and `DELETE`, object-valued query parameters (`filter`, `sort`) travel as JSON text and array-valued ones repeat as `name[]=value`. - The MCP-only `_meta` field (usage analytics) never reaches the backend and is not part of this contract. version: '1.0' contact: name: GetSales url: https://getsales.io email: support@getsales.io license: name: Proprietary url: https://getsales.io/terms servers: - url: https://beta.getsales.io/unibox/v1 description: >- Production (the gateway path on the beta ring; the origin is provisioned per DEPLOY_MAP.md) security: - BearerJwt: [] TeamSid: [] tags: - name: agent_answers description: >- Registry package `mcp.unibox/agent_answers`, served on MCP mount `unibox.knowledge`. - name: agent_conversation_uploads description: >- Registry package `mcp.unibox/agent_conversation_uploads`, served on MCP mount `unibox.agent-memory`. - name: agent_examples description: >- Registry package `mcp.unibox/agent_examples`, served on MCP mount `unibox.agent-memory`. - name: agent_hints description: >- Registry package `mcp.unibox/agent_hints`, served on MCP mount `unibox.agent-memory`. - name: agent_plans description: >- Registry package `mcp.unibox/agent_plans`, served on MCP mount `unibox.agent`. - name: agent_runs description: >- Registry package `mcp.unibox/agent_runs`, served on MCP mount `unibox.agent-memory`. - name: agent_scenarios description: >- Registry package `mcp.unibox/agent_scenarios`, served on MCP mount `unibox.agent`. - name: agent_source_parses description: >- Registry package `mcp.unibox/agent_source_parses`, served on MCP mount `unibox.knowledge`. - name: agent_sources description: >- Registry package `mcp.unibox/agent_sources`, served on MCP mount `unibox.knowledge`. - name: agent_tests description: >- Registry package `mcp.unibox/agent_tests`, served on MCP mount `unibox.agent-memory`. - name: agents description: >- Registry package `mcp.unibox/agents`, served on MCP mount `unibox.website`. - name: conversation_events description: >- Registry package `mcp.unibox/conversation_events`, served on MCP mount `unibox.inbox`. - name: conversations description: >- Registry package `mcp.unibox/conversations`, served on MCP mount `unibox.inbox`. - name: messages description: >- Registry package `mcp.unibox/messages`, served on MCP mount `unibox.inbox`. - name: sender_profiles description: >- Registry package `mcp.unibox/sender_profiles`, served on MCP mount `unibox.sender-profiles`. - name: tasks description: Registry package `mcp.unibox/tasks`, served on MCP mount `unibox.inbox`. - name: timeline description: >- Registry package `mcp.unibox/timeline`, served on MCP mount `unibox.inbox`. paths: /api/agents/{sid}: patch: tags: - agents summary: Update agent description: >- Change an AI SDR by sid: state, mode, name, is_default (true makes it the team's default), the Brief, knowledge, settings, the Rules, the hosts, setup, llm_config, golden_set (the Words). Each value replaces the stored one whole: read the agent first and send it back; the compaction's copies and the voice are read-only. The Rules, the hosts and the voice have doors of their own (update_agent_rules, update_agent_hosts, update_agent_voice); per-thread autonomy is update_conversation. Contract: - MCP tool `update_agent`, registry package `mcp.unibox/agents`, mount `unibox.agent`. - Operation `update`, response envelope `update`. - Flags: dangerous: the MCP layer gates it behind a preview/commit token, and the effect cannot be undone through this API. operationId: update_agent parameters: - name: sid in: path required: true description: The agent to change (ub_ag_…). schema: type: string minLength: 18 maxLength: 18 pattern: ^ub_ag_ description: The agent to change (ub_ag_…). requestBody: required: false content: application/json: schema: $ref: '#/components/schemas/UpdateAgentRequest' responses: '200': description: '`update` success envelope.' content: application/json: schema: $ref: '#/components/schemas/UpdateAgentResponse' 4XX: $ref: '#/components/responses/McpClientError' 5XX: $ref: '#/components/responses/McpServerError' components: schemas: UpdateAgentRequest: type: object description: Request body of `update_agent`. properties: state: type: string enum: - 'on' - 'off' description: >- on starts planning and acting, off stops it (classification keeps running either way). setup_required is system-owned and rejected. Going to on the first time needs the Brief complete (no slot left, every section answered): else a 422 naming what is left. mode: type: string enum: - copilot - autopilot - 'off' description: >- The FALLBACK autonomy mode only. A per-thread override or an owning automation still wins over it. name: type: string minLength: 1 maxLength: 255 description: Display name, 1..255 chars. is_default: type: boolean enum: - true description: >- true makes this agent the team's default; the previous default loses the flag in the same transaction, and the threads that follow the default re-project. false is refused on the default (the team always has one): make another agent the default instead. knowledge: type: object properties: booking_mode: type: string enum: - link - native description: >- link sends the host's link (default, the only live mode; the sender host's since block AC4, where the Playbook goal's link stood from 2026-10-19 and the knowledge's calendar link before); native (slots in thread) is accepted but inert. source_urls: type: array items: type: string maxLength: 2048 maxItems: 20 description: Up to 20 sites scraped into the knowledge pack. interview_transcript_ref: type: string nullable: true maxLength: 255 description: >- Reference to the gs.agents.sdr setup-interview session, max 255 chars. A pointer, never a copy of the transcript. description: >- REPLACES the stored knowledge pack wholesale (no deep merge): read it first and send every key you keep. Its old prose keys (offer, icp, tone_of_voice, general_context) are refused: the Brief holds them. brief: type: object properties: text: type: string maxLength: 49152 description: >- The whole Brief in markdown, max 49152 chars; it replaces the stored one. Keep the five headings; answer a slot by replacing its bracketed line. required: - text description: >- The Brief, replaced whole: read it first and send the whole text back with the change; the compaction's copies are read-only (422). setup: type: object properties: skipped: type: array items: type: string enum: - knowledge - golden_set - test maxItems: 3 description: >- REPLACES the skipped steps: knowledge, golden_set or test (the Brief and go_live are never skipped, 422). An empty list takes every skip back. description: The advised steps to go live the team skips, replaced whole. settings: type: object properties: max_auto_messages_per_conversation: type: integer minimum: 1 maximum: 20 description: >- Agent-authored sends allowed on one thread. 1..20, default 4; the gate parks the next send for approval once it is spent. followups_for_synced_threads: type: boolean description: >- Default false: threads an external sequencer already follows up on are left alone (double-touch protection). escalation_triggers: type: array items: type: string enum: - pricing_question - call_request - legal_or_security - multiple_reschedules - low_confidence - unknown_question - job_seeker - support_request description: >- Built-in hand-offs on; default: all but pricing_question and call_request. Six judged by the classifier, multiple_reschedules at the third, low_confidence under 0.5. A firing stops the agent; a task names it; the thread goes needs_you. classification_merge_seconds: type: integer minimum: 10 maximum: 600 description: >- Debounce window that merges an inbound burst into ONE classify run. 10..600, default 60. messages_recency_days: type: integer minimum: 1 maximum: 365 description: >- How far back the thread tail is read into LLM context. 1..365, default 30. custom_escalation_triggers: type: array items: type: string minLength: 3 maxLength: 255 maxItems: 10 description: >- The team's own hand-offs in words, each finishing: hand the thread to a person when the lead ... Up to 10, 3..255 chars, distinct; default none. They hand off like the built-in ones, the task titled : . Replaced whole. after_person_message: type: string enum: - plan_followups - only_when_asked description: >- After a person on the team writes in a thread the AI SDR works on, it stops sending there. plan_followups (default): it plans the follow-ups for them, in their words, as a plan waiting for their OK. only_when_asked: nothing until Make follow-ups. person_followups_count: type: integer minimum: 1 maximum: 3 description: >- How many follow-ups it plans after a person's message. 1..3, default 2. person_followups_every_days: type: integer minimum: 1 maximum: 30 description: >- Days between those follow-ups, counted from the person's message; each goes at ten in the morning of the workspace's day, never on a weekend. 1..30, default 3. person_followups_then: type: string enum: - task - agent_continues description: >- What ends them when none is answered: task (default) opens a task for the person and the thread is theirs again; agent_continues lets the AI SDR follow up on its own, under its caps. reply_split: type: string enum: - one_message - two_or_three description: >- How a long LinkedIn reply goes out (2026-10-19): two_or_three (default) cuts it at its paragraphs or sentences into two or three messages a few seconds apart, as a person sends them; one_message sends it whole. An email never splits. credits_cap_per_conversation: type: integer minimum: 1 maximum: 1000 description: >- The credits the agent may spend on one thread (its turns' model cost at 25 credits a dollar), 1..1000, default 40. At the cap the thread is handed to a person with a task; closing the task lets it go on, and the meter keeps counting. handoff_notify_email: type: boolean description: >- Default true: a hand-off (a trigger that fired, the credits cap) is also told by email to the thread's sender profile assignee, else the workspace owner. The task in the inbox is always there. reply_language: type: string enum: - lead - en - de - es - fr - pt - ru - ar - hi - zh description: >- The language the agent writes in (2026-10-19): lead (default) mirrors the language they write in; a code pins every reply to that language whatever they write. learning: type: object properties: from_history: type: boolean description: >- Default true: after a sender profile's history walk, its threads are paired by rule into the set. from_own_sends: type: boolean description: >- Default true: a person's own reply in a live thread joins the set. from_approved_edits: type: boolean description: >- Default true: an agent draft a person edited before it went joins the set, the person's words as the answer. edits_join: type: string enum: - after_ok - on_its_own description: >- after_ok (default): an edited draft waits under From your edits for a Keep; on_its_own: it joins at once. description: >- The golden set's roads (2026-10-20): what it learns from (the history walk, a person's own replies, the drafts a person edited) and whether an edit waits for a Keep. description: >- REPLACES the stored caps wholesale, same rule as knowledge. Changes apply from the next gate evaluation; plans already running are not re-edited. rules: type: object properties: reply_words: type: object properties: linkedin: type: object properties: min: type: integer minimum: 5 maximum: 200 description: The fewest words a reply runs on this channel, 5..200. max: type: integer minimum: 5 maximum: 200 description: The most, 5..200, at least the min. description: >- Default 15 to 60: short replies get an answer about twice as often. email: type: object properties: min: type: integer minimum: 5 maximum: 200 description: The fewest words a reply runs on this channel, 5..200. max: type: integer minimum: 5 maximum: 200 description: The most, 5..200, at least the min. description: >- Default 25 to 80: the middle half of the replies people write back by email in the corpus. description: The length band per channel, in words. meeting_ask: type: string enum: - suggest_call_link_on_request - ask_their_time - suggest_call_with_link description: >- How it asks for the meeting: suggest_call_link_on_request (default: a call suggested in one line, the link only when they ask or say yes), ask_their_time (their time asked for, no link), suggest_call_with_link (the call with the link in the same message). confirm_named_time: type: boolean description: >- Default true: a time they name is confirmed in one line and nothing else is asked; a person puts it on the calendar. answer_then_call: type: boolean description: >- Default true: a question before the call is answered in short, then the ask. acknowledge_low_signal: type: boolean description: >- Default true: a lead who only says thanks gets one friendly line and the thread resumes its workflow. reply_delay_minutes: type: object properties: min: type: integer minimum: 0 maximum: 60 max: type: integer minimum: 0 maximum: 60 description: >- The wait before a reply on autopilot, a uniform pick between the two, in minutes, 0..60; default 1 to 2. quiet_hours: type: object properties: from: type: string description: '"HH:MM" 24h.' to: type: string description: '"HH:MM" 24h; a to before the from spans midnight.' description: >- When no reply goes, in the lead's zone (the workspace's today); default 22:00 to 07:00. from equal to to is never quiet. weekends: type: boolean description: >- Default true: it replies on weekends; false keeps the weekend quiet. followups: type: integer minimum: 0 maximum: 6 description: >- How many follow-ups when the lead goes quiet, 0..6; default 3 (the corpus: blocks climb with the fourth). followup_days: type: integer minimum: 1 maximum: 14 description: Days between them, 1..14; default 4. something_new: type: boolean description: >- Default true: every follow-up brings something new (a proof, a shorter ask, an easy way out), never a bump. checks: type: object properties: unfilled_fields: type: boolean description: >- A placeholder a template left ({{first_name}}, [Company]); refused as unfilled_field. same_text_twice: type: boolean description: >- A text the thread already carries from us; refused as same_text_twice. link_before_reply: type: boolean description: >- A booking link before the lead ever wrote; refused as link_before_reply. stop_words: type: boolean description: The Stop words of the golden set; refused as words_caught. long_dashes: type: boolean description: An em or en dash; refused as words_caught. template_after_reply: type: boolean description: >- The sequence's template sent after the lead replied; the runner's check step. signature_block: type: boolean description: >- An email reply that ends in a signature block of its own (the mailbox appends the team's); refused as signature_block. Email only. description: >- The checks before it sends, each on (default) or off. Stop after a no is the platform's and always on. description: >- The Rules, replaced whole (a key left out takes its corpus default); update_agent_rules changes one field at a time. hosts: type: array items: type: object properties: id: type: string minLength: 1 maxLength: 32 description: >- Stable inside the list: sender for the sender profile's row, a minted handle (host_...) for a person; send it back to keep the row. kind: type: string enum: - sender - person description: Default person; one sender row is kept whatever the list says. member_sid: type: string nullable: true minLength: 18 maxLength: 18 pattern: ^us_mb_ description: >- A team member (us_mb_...) when the host is one; null for a free name. name: type: string nullable: true maxLength: 120 description: >- The name shown and said; a member's is read at the member when null. link: type: string nullable: true maxLength: 512 description: >- Their own booking link, a URL; the sender row's is the team's link to offer (the campaign's and the table's win over it). introduced_as: type: string nullable: true maxLength: 255 description: >- How the reply introduces them when they are not the sender ("Peter, our co-founder, runs the demos"); said once, the first time the call comes up. scenario_keys: type: array items: type: string maxLength: 64 maxItems: 40 description: >- The platform keys and the team's own rows' sids this host hosts; a key hosted by one host at most (the first that names it keeps it). A scenario nobody names is the sender's. maxItems: 20 description: >- The hosts, replaced whole, at most 20; update_agent_hosts is the same door on its own. goal: type: object nullable: true properties: kind: type: string enum: - call - signup - webinar - custom description: >- What the offer asks for: call (the stage after a yes books it), signup, webinar or custom (no stage after the yes, no link). words: type: string maxLength: 512 description: What it is, in the team's words; empty = the kind alone. required: - kind - words description: >- The goal, replaced whole: its kind (call, signup, webinar or custom; decides the stage after a yes) and its words ("a 20-minute call with Peter"); null puts the call with no words back. The link stays the sender host's: set it with update_agent_hosts. llm_config: type: object nullable: true properties: classification_model: type: string nullable: true maxLength: 128 description: >- Per-team override of the classify model, max 128 chars. null = platform default. agent_model: type: string nullable: true maxLength: 128 description: >- Per-team override of the strategize / draft model, max 128 chars. null = platform default. description: >- REPLACES the model routing wholesale; null clears it back to platform defaults. golden_set: type: object properties: words: type: array items: type: object properties: never: type: string minLength: 1 maxLength: 64 description: >- A word or a phrase the agent never writes, matched whole and in any case, max 64 chars. instead: type: string nullable: true maxLength: 128 description: 'What it says instead, max 128 chars; null: leave it out.' required: - never maxItems: 50 description: >- REPLACES the Words, up to 50; the same word in another case is kept once. Omit to keep them. description: >- The Words the agent never writes, each with what to say instead; the voice is formed from the replies and never sent here (422): a line of it is set with update_agent_voice. UpdateAgentResponse: type: object properties: success: type: boolean enum: - true operation: type: string enum: - update item: type: object properties: sid: type: string description: >- Agent sid (ub_ag_…). Stable for the life of the agent; a playtable or a workflow picks an agent by it. team_sid: type: string description: >- Owning team (ts_tm_…, external - gs.service.id). Many agents per team since block 10 (2026-10-30), at most 20. state: type: string enum: - setup_required - 'on' - 'off' description: >- setup_required = provisioned but disabled, inbox classifies only; on = planning and acting per the mode ladder; off = classification continues, nothing is planned or sent. mode: type: string enum: - copilot - autopilot - 'off' description: >- FALLBACK autonomy. The effective mode of a thread is the per-thread override, else the owning automation, else this. name: type: string description: Display name, 1..255 chars. The first agent ships as "AI SDR". is_default: type: boolean description: >- The team's default (block 10, 2026-10-30): exactly one agent per team carries it. A thread with no agent of its own, a playtable or a workflow that picks none, falls to it. Moved with update_agent {is_default: true}; never taken off directly. knowledge: type: object properties: booking_mode: type: string enum: - link - native description: >- link sends the host's link (default, the only live mode; the sender host's since block AC4, where the Playbook goal's link stood from 2026-10-19 and the knowledge's calendar link before); native (slots in thread) is accepted but inert. source_urls: type: array items: type: string maxLength: 2048 maxItems: 20 description: Up to 20 sites scraped into the knowledge pack. interview_transcript_ref: type: string nullable: true maxLength: 255 description: >- Reference to the gs.agents.sdr setup-interview session, max 255 chars. A pointer, never a copy of the transcript. description: >- The questions and answers it answers from, the booking mode, the sites read. Its prose became the Brief on 2026-10-20. brief: type: object properties: text: type: string maxLength: 49152 description: >- The Brief in markdown, the team's own words, max 49152 chars. A line in brackets ("- [a topic it should leave to you]") is a slot still open: the model never reads it. compact: type: string nullable: true maxLength: 8192 description: >- [ro] The copy the model reads, max 8192 chars, written by the compaction after a save that moved the text; null until it lands (the text without its slots is read meanwhile). digest: type: string nullable: true maxLength: 400 description: >- [ro] The classifier's digest, max 400 chars, written by the same compaction; null until it lands. required: - text - compact - digest description: >- The Brief (2026-10-20): the team's one markdown document every turn reads. A row stored before it reads its old offer, ICP, goal, general context and tone composed into the five sections. settings: type: object properties: max_auto_messages_per_conversation: type: integer minimum: 1 maximum: 20 description: >- Agent-authored sends allowed on one thread. 1..20, default 4; the gate parks the next send for approval once it is spent. followups_for_synced_threads: type: boolean description: >- Default false: threads an external sequencer already follows up on are left alone (double-touch protection). escalation_triggers: type: array items: type: string enum: - pricing_question - call_request - legal_or_security - multiple_reschedules - low_confidence - unknown_question - job_seeker - support_request description: >- Built-in hand-offs on; default: all but pricing_question and call_request. Six judged by the classifier, multiple_reschedules at the third, low_confidence under 0.5. A firing stops the agent; a task names it; the thread goes needs_you. classification_merge_seconds: type: integer minimum: 10 maximum: 600 description: >- Debounce window that merges an inbound burst into ONE classify run. 10..600, default 60. messages_recency_days: type: integer minimum: 1 maximum: 365 description: >- How far back the thread tail is read into LLM context. 1..365, default 30. custom_escalation_triggers: type: array items: type: string minLength: 3 maxLength: 255 maxItems: 10 description: >- The team's own hand-offs in words, each finishing: hand the thread to a person when the lead ... Up to 10, 3..255 chars, distinct; default none. They hand off like the built-in ones, the task titled : . Replaced whole. after_person_message: type: string enum: - plan_followups - only_when_asked description: >- After a person on the team writes in a thread the AI SDR works on, it stops sending there. plan_followups (default): it plans the follow-ups for them, in their words, as a plan waiting for their OK. only_when_asked: nothing until Make follow-ups. person_followups_count: type: integer minimum: 1 maximum: 3 description: >- How many follow-ups it plans after a person's message. 1..3, default 2. person_followups_every_days: type: integer minimum: 1 maximum: 30 description: >- Days between those follow-ups, counted from the person's message; each goes at ten in the morning of the workspace's day, never on a weekend. 1..30, default 3. person_followups_then: type: string enum: - task - agent_continues description: >- What ends them when none is answered: task (default) opens a task for the person and the thread is theirs again; agent_continues lets the AI SDR follow up on its own, under its caps. reply_split: type: string enum: - one_message - two_or_three description: >- How a long LinkedIn reply goes out (2026-10-19): two_or_three (default) cuts it at its paragraphs or sentences into two or three messages a few seconds apart, as a person sends them; one_message sends it whole. An email never splits. credits_cap_per_conversation: type: integer minimum: 1 maximum: 1000 description: >- The credits the agent may spend on one thread (its turns' model cost at 25 credits a dollar), 1..1000, default 40. At the cap the thread is handed to a person with a task; closing the task lets it go on, and the meter keeps counting. handoff_notify_email: type: boolean description: >- Default true: a hand-off (a trigger that fired, the credits cap) is also told by email to the thread's sender profile assignee, else the workspace owner. The task in the inbox is always there. reply_language: type: string enum: - lead - en - de - es - fr - pt - ru - ar - hi - zh description: >- The language the agent writes in (2026-10-19): lead (default) mirrors the language they write in; a code pins every reply to that language whatever they write. learning: type: object properties: from_history: type: boolean description: >- Default true: after a sender profile's history walk, its threads are paired by rule into the set. from_own_sends: type: boolean description: >- Default true: a person's own reply in a live thread joins the set. from_approved_edits: type: boolean description: >- Default true: an agent draft a person edited before it went joins the set, the person's words as the answer. edits_join: type: string enum: - after_ok - on_its_own description: >- after_ok (default): an edited draft waits under From your edits for a Keep; on_its_own: it joins at once. description: >- The golden set's roads (2026-10-20): what it learns from (the history walk, a person's own replies, the drafts a person edited) and whether an edit waits for a Keep. description: >- The behavior caps the mode gate and the planners enforce server-side. created_by: type: object properties: actor_type: type: string enum: - user - support - api_key - system - agent actor_sid: type: string nullable: true team_sid: type: string actor_name: type: string nullable: true description: >- The OAuth client that acted ("Claude", "n8n"); null for a user, an API key or a system job. oauth_client_sid: type: string nullable: true description: The acting OAuth client (id_oc_*); null off the OAuth path. reason: type: string nullable: true description: >- Why a system actor wrote the row (snapshot_capture_job, ...); null otherwise. permissions: type: object additionalProperties: {} description: >- Internal audit context: the grant set the actor held at write time. Not a contract. cluster_id: type: integer nullable: true description: 'Internal audit context: the cluster that served the write.' trace_id: type: string nullable: true description: >- Internal audit context: the trace id of the request that wrote the row. required: - actor_type - actor_sid - team_sid - permissions description: >- Actor that provisioned the row (actor_type is system: the bootstrap job). rules: type: object properties: reply_words: type: object properties: linkedin: type: object properties: min: type: integer minimum: 5 maximum: 200 description: >- The fewest words a reply runs on this channel, 5..200. max: type: integer minimum: 5 maximum: 200 description: The most, 5..200, at least the min. description: >- Default 15 to 60: short replies get an answer about twice as often. email: type: object properties: min: type: integer minimum: 5 maximum: 200 description: >- The fewest words a reply runs on this channel, 5..200. max: type: integer minimum: 5 maximum: 200 description: The most, 5..200, at least the min. description: >- Default 25 to 80: the middle half of the replies people write back by email in the corpus. description: The length band per channel, in words. meeting_ask: type: string enum: - suggest_call_link_on_request - ask_their_time - suggest_call_with_link description: >- How it asks for the meeting: suggest_call_link_on_request (default: a call suggested in one line, the link only when they ask or say yes), ask_their_time (their time asked for, no link), suggest_call_with_link (the call with the link in the same message). confirm_named_time: type: boolean description: >- Default true: a time they name is confirmed in one line and nothing else is asked; a person puts it on the calendar. answer_then_call: type: boolean description: >- Default true: a question before the call is answered in short, then the ask. acknowledge_low_signal: type: boolean description: >- Default true: a lead who only says thanks gets one friendly line and the thread resumes its workflow. reply_delay_minutes: type: object properties: min: type: integer minimum: 0 maximum: 60 max: type: integer minimum: 0 maximum: 60 description: >- The wait before a reply on autopilot, a uniform pick between the two, in minutes, 0..60; default 1 to 2. quiet_hours: type: object properties: from: type: string description: '"HH:MM" 24h.' to: type: string description: '"HH:MM" 24h; a to before the from spans midnight.' description: >- When no reply goes, in the lead's zone (the workspace's today); default 22:00 to 07:00. from equal to to is never quiet. weekends: type: boolean description: >- Default true: it replies on weekends; false keeps the weekend quiet. followups: type: integer minimum: 0 maximum: 6 description: >- How many follow-ups when the lead goes quiet, 0..6; default 3 (the corpus: blocks climb with the fourth). followup_days: type: integer minimum: 1 maximum: 14 description: Days between them, 1..14; default 4. something_new: type: boolean description: >- Default true: every follow-up brings something new (a proof, a shorter ask, an easy way out), never a bump. checks: type: object properties: unfilled_fields: type: boolean description: >- A placeholder a template left ({{first_name}}, [Company]); refused as unfilled_field. same_text_twice: type: boolean description: >- A text the thread already carries from us; refused as same_text_twice. link_before_reply: type: boolean description: >- A booking link before the lead ever wrote; refused as link_before_reply. stop_words: type: boolean description: >- The Stop words of the golden set; refused as words_caught. long_dashes: type: boolean description: An em or en dash; refused as words_caught. template_after_reply: type: boolean description: >- The sequence's template sent after the lead replied; the runner's check step. signature_block: type: boolean description: >- An email reply that ends in a signature block of its own (the mailbox appends the team's); refused as signature_block. Email only. description: >- The checks before it sends, each on (default) or off. Stop after a no is the platform's and always on. description: >- The Rules (block AC4, 2026-10-26): what every reply keeps to; a row written before them reads as the corpus defaults. Read and changed on get_agent_rules / update_agent_rules too. hosts: type: array items: type: object properties: id: type: string minLength: 1 maxLength: 32 description: >- Stable inside the list: sender for the sender profile's row, a minted handle (host_...) for a person; send it back to keep the row. kind: type: string enum: - sender - person description: >- sender: the sender profile itself (one row, always kept); person: a colleague. member_sid: type: string nullable: true minLength: 18 maxLength: 18 pattern: ^us_mb_ description: >- A team member (us_mb_...) when the host is one; null for a free name. name: type: string nullable: true maxLength: 120 description: >- The name shown and said; a member's is read at the member when null. link: type: string nullable: true maxLength: 512 description: >- Their own booking link, a URL; the sender row's is the team's link to offer (the campaign's and the table's win over it). introduced_as: type: string nullable: true maxLength: 255 description: >- How the reply introduces them when they are not the sender ("Peter, our co-founder, runs the demos"); said once, the first time the call comes up. scenario_keys: type: array items: type: string maxLength: 64 maxItems: 40 description: >- The platform keys and the team's own rows' sids this host hosts; a key hosted by one host at most (the first that names it keeps it). A scenario nobody names is the sender's. required: - id - kind - member_sid - name - link - introduced_as - scenario_keys description: >- Who hosts the meetings (block AC4): the sender row first, always, then colleagues; replaced whole on update_agent_hosts. goal: type: object nullable: true properties: kind: type: string enum: - call - signup - webinar - custom description: >- What the offer asks for: call (the stage after a yes books it), signup, webinar or custom (no stage after the yes, no link). words: type: string maxLength: 512 description: What it is, in the team's words; empty = the kind alone. required: - kind - words description: >- The agent's goal (block 10 step 10.3, 2026-10-30): the kind of what the offer asks for (call, signup, webinar, custom) and its words. Null = a call with no words. The link is never here: it is the sender host's (hosts[0].link), and a custom goal carries none. golden_set: type: object properties: words: type: array items: type: object properties: never: type: string minLength: 1 maxLength: 64 description: >- A word or a phrase the agent never writes, matched whole and in any case, max 64 chars. instead: type: string nullable: true maxLength: 128 description: >- What it says instead, max 128 chars; null: leave it out. required: - never description: The Words, up to 50, one entry per word in any case. voice: type: object nullable: true properties: summary: type: string nullable: true description: >- The team's voice in a few sentences, as the model reads it; null while the set has not formed one and a person set a line alone (block AC5). length: type: string nullable: true description: How long their replies run. questions: type: string nullable: true description: How they ask. register: type: string nullable: true description: The register they write in. sign_off: type: string nullable: true description: How they sign off. formed_from: type: integer nullable: true description: How many replies it was formed from. formed_at: type: string nullable: true description: ISO 8601 UTC, when it was formed. model: type: string nullable: true description: What formed it. pinned: type: array items: type: string description: >- The lines a person set (update_agent_voice, block AC5), among length, questions, register, sign_off: theirs, kept when the voice forms again. required: - summary description: >- The voice formed from the golden set, a minute after it changed, with the lines a person set (update_agent_voice); null until it has rows or a line. required: - words - voice description: >- The golden set's Words and voice (2026-10-20); the rows are search_agent_examples. A row written before it reads as no Words and no voice. setup: type: object properties: skipped: type: array items: type: string enum: - brief - knowledge - golden_set - test - go_live description: >- The advised steps the team skipped on the way to go live, in the steps' order. required: - skipped description: >- The advised steps to go live the team skipped (2026-10-20); include readiness says where each step stands. llm_config: type: object nullable: true properties: classification_model: type: string nullable: true maxLength: 128 description: >- Per-team override of the classify model, max 128 chars. null = platform default. agent_model: type: string nullable: true maxLength: 128 description: >- Per-team override of the strategize / draft model, max 128 chars. null = platform default. description: >- Per-team model routing; null (the normal case) = platform defaults. setup_completed_at: type: string nullable: true description: >- ISO 8601 UTC, stamped the first time state left setup_required. null = setup never finished. created_at: type: string description: ISO 8601 UTC. updated_at: type: string description: ISO 8601 UTC. deleted_at: type: string nullable: true description: >- ISO 8601 UTC. Null on every agent a search lists; stamped by delete_agent. required: - sid - team_sid - state - mode - name - is_default - knowledge - brief - settings - created_by - rules - hosts - goal - golden_set - setup - llm_config - setup_completed_at - created_at - updated_at - deleted_at updated_fields: type: array items: type: string previous_values: type: object additionalProperties: {} kept_fields: type: array items: type: string description: >- The fields this write did not change because the person's own value stands on them (stamped person); read the item for what landed. meta: type: object properties: trace_id: type: string description: UUID v7; same 128-bit value as the X-Trace-Id header. span_id: type: string pattern: ^[0-9a-f]{16}$ description: 16 hex chars, root span of this request. timestamp: type: string description: ISO 8601 UTC (Y-m-dTH:i:sZ), response time. duration_ms: type: integer minimum: 0 description: Server-side wall clock. team_sid: type: string nullable: true description: >- The team this call ran in (the token team, or the team_sid override). Null when unauthenticated; absent from pre-2026-08-20 backends. actor_type: type: string nullable: true description: >- user | agent | api_key | system. Null when unauthenticated; absent from pre-2026-08-20 backends. required: - trace_id - span_id - timestamp - duration_ms required: - success - operation - item - updated_fields - previous_values - meta McpError: type: object properties: success: type: boolean enum: - false error: type: object properties: code: type: string enum: - validation_failed - nothing_to_update - not_found - relation_not_found - invalid_transition - limit_exceeded - payment_required - duplicate_rejected - conflict - delete_blocked - unauthorized - forbidden - rate_limited - internal_error - service_unavailable - not_implemented message: type: string recoverable: type: boolean suggestion: type: string field_errors: type: object additionalProperties: type: array items: type: object properties: rule: type: string message: type: string required: - rule - message blockers: type: array items: type: object properties: type: type: string description: >- Machine-readable blocker type (active_flow, pending_tasks, …). severity: type: string enum: - hard - soft description: >- hard = external action required; soft = acknowledge is enough. description: type: string entity_sid: type: string nullable: true count: type: integer resolution: type: string description: 'Hard: tool name to call. Soft: code for acknowledge[].' resolution_hint: type: string required: - type - severity - description - entity_sid - resolution - resolution_hint context: type: object additionalProperties: {} required: - code - message - recoverable meta: type: object properties: trace_id: type: string description: UUID v7; same 128-bit value as the X-Trace-Id header. span_id: type: string pattern: ^[0-9a-f]{16}$ description: 16 hex chars, root span of this request. timestamp: type: string description: ISO 8601 UTC (Y-m-dTH:i:sZ), response time. duration_ms: type: integer minimum: 0 description: Server-side wall clock. team_sid: type: string nullable: true description: >- The team this call ran in (the token team, or the team_sid override). Null when unauthenticated; absent from pre-2026-08-20 backends. actor_type: type: string nullable: true description: >- user | agent | api_key | system. Null when unauthenticated; absent from pre-2026-08-20 backends. required: - trace_id - span_id - timestamp - duration_ms required: - success - error responses: McpClientError: description: >- MCP error envelope. `error.code` is one of validation_failed, nothing_to_update, not_found, relation_not_found, invalid_transition, limit_exceeded, payment_required, duplicate_rejected, conflict, delete_blocked, unauthorized, forbidden, rate_limited, not_implemented. content: application/json: schema: $ref: '#/components/schemas/McpError' McpServerError: description: >- MCP error envelope with `error.code` internal_error or service_unavailable. content: application/json: schema: $ref: '#/components/schemas/McpError' securitySchemes: BearerJwt: type: http scheme: bearer bearerFormat: JWT description: >- Access token issued by gs.service.id. Its `access_identity` claim carries `team_sid`, `actor_sid` and `actor_type`, and that team scope is authoritative. TeamSid: type: apiKey in: header name: Team-SID description: >- Team scope for tokens that do not carry one. Ignored when the token already names a team. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.