tough-tongue/toughtongue
Build, refine, and analyze Tough Tongue AI voice agents for tough conversations — agents that automate them (sales calls, lead qualification, demos, screening, booking) and agents that train you for the ones you handle yourself (negotiations, interviews, coaching). Create scenarios, place phone calls, schedule meeting bots, and analyze sessions.
Creates, edits, and refines Tough Tongue AI Scenarios, the definitions behind voice agents (sales calls, lead qualification, demos, screening, support, booking) and practice roleplays (negotiations, interviews, coaching). Writes ai_instructions, ai_model_config, strategy, tools_config, and rubrik through ttai:create_scenario and ttai:update_scenario. Also resolves the personal or organization workspace, checks plan and balance, places or cancels SIP calls, schedules or cancels meeting bots, mints private Scenario links, and troubleshoots ttai MCP sign-in. Use when the user wants a voice agent or practice Scenario created or improved ("create a voice agent", "the agent ends calls too early", "make it sound more natural"), a call placed, a meeting bot sent, or a Tough Tongue AI account question answered. Not for reports across many sessions (ttai-session-analyst) or browser demo steps (ttai-browser-demo-builder).
Creates and maintains Agent Desktop apps for Tough Tongue AI voice agents: small React packages (README.md, code, an editable data or control file, and spec.json) that the agent opens and drives beside a live session, such as a board, checklist, scorecard, or presentation deck. Finds, creates, writes, verifies, and previews apps with ttai:list_resources, ttai:create_filebase, ttai:write_filebase, ttai:get_resource, and ttai:create_token, declares the app's controls so the voice agent knows how to operate it, then attaches it to a Scenario's agent_desktop tool with ttai:update_scenario. Use when the user says "build an app my voice agent can edit", "make a board the agent updates during the call", "a deck the agent presents", "attach this app to my scenario", or "preview my app". Not for designing the Scenario's conversation (ttai-agent) or analyzing sessions (ttai-session-analyst).
Scripts deterministic browser demo steps (tools_config.tools.browser.tool_settings.steps) on an existing Tough Tongue AI Scenario, so its voice agent clicks exact XPath selectors instead of improvising. Signs the demo browser in with ttai:authenticate_browser, converts a pasted browser recording or a walked-through flow into steps, saves them with ttai:update_scenario without losing the saved login, and repairs steps that click the wrong element. Use when the user says "record browser demo steps", "turn my recording into steps", "make my demo deterministic", "the demo clicks the wrong thing", or "log the demo browser in". Not for creating the Scenario (ttai-agent) or analyzing sessions (ttai-session-analyst).
Turns Tough Tongue AI sessions into evidence-backed reports. Reads sessions, scores, report cards, strengths, weaknesses, and transcripts from practice roleplays, AI phone calls, and meeting-bot calls for a Scenario, person, or date range, then writes team performance, Scenario health, or individual coaching reports with action items. Can also ingest an external call transcript or recording as a scored session (ttai:upload_session) and fill in missing analysis (ttai:analyze_session), each after the user confirms. Use when the user asks "how is my team doing?", "top improvement areas for scenario X", "lowest-scoring sessions", "coaching report for Priya", or "session trends this month". Not for changing a Scenario, rubric, or prompt (ttai-agent).